Appearance
Skills Library
Ready-made skills that connect your AI tool or agent to OriginalVoices audience research workflows. Each skill guides the AI through a structured research process using Digital Twins. Compatible with Claude, Manus, and other AI tools that support the Agent Skills standard.
Before you start
These skills require the OriginalVoices MCP server to be connected to your AI tool or agent. If you haven't set that up yet, follow the integration guide first.
To install: Download the .md file, then upload it to your AI agent (e.g. in Claude: Customize > Skills > Click + > Upload a skill).
Deep Customer Research
Conduct comprehensive qualitative research on any topic. Asks 10-12 carefully designed questions covering behaviour, pain points, emotions, priorities, decision-making, unmet needs, trust signals, and willingness to pay — all in a single pass.
Use when: You need to deeply understand what customers think and feel about a product, category, brand, or market. Great for validating product-market fit, informing strategy, or exploring audience sentiment.
View full skill
markdown
---
name: deep-customer-research
description: "Use this skill to conduct deep qualitative customer research on any topic. Triggers include: requests to understand customer pain points, unmet needs, motivations, or emotions around a product, category, brand, or market. Also use when validating product-market fit, exploring how an audience feels about a trend, or gathering insights to inform product strategy, positioning, or roadmap decisions. Uses OriginalVoices Digital Twins (ask_twins) to ask 10-12 comprehensive questions in a single pass covering behaviour, pain points, emotions, priorities, decision-making, unmet needs, trust signals, and willingness to pay."
---
# Deep Customer Research Agent
## Overview
Deeply understand what your customers really think and feel about any topic. This workflow uses OriginalVoices Digital Twins to conduct comprehensive qualitative research in a single pass — asking 10-12 carefully designed questions that cover the full landscape of motivations, emotions, behaviours, and unmet needs.
## Workflow Steps
### Step 1: Define the Research Topic & Audience
Gather from the user:
- **Research topic or question**: What do they want to understand? (e.g. "How do parents feel about screen time management apps?")
- **Target audience**: Who should we hear from? Be as specific as possible — age, location, interests, lifestyle, values. (e.g. "Parents aged 28-45 in the US with children under 12 who are concerned about their kids' screen time")
### Step 2: Design the Question Set
Craft 10-12 open-ended questions that cover the full research landscape in a single round. The questions should progress from broad context through to specific opinions and forward-looking needs.
**Question design framework — cover all of these areas:**
| Area | Purpose | Example |
|------|---------|---------|
| Current behaviour | How they deal with the problem today | "How do you currently handle [problem]?" |
| Pain points | What frustrates them | "What frustrates you most about [topic]?" |
| Emotional drivers | What feelings are at play | "How does [problem/topic] make you feel day-to-day?" |
| Priorities | What matters most | "When it comes to [category], what matters most to you and why?" |
| Decision-making | How they choose | "When choosing a [product/solution], what do you look for first?" |
| Current solutions | What they use now and why | "What tools/products/approaches do you currently use for [problem]? What works and what doesn't?" |
| Unmet needs | Gaps in what's available | "What's missing from the [products/solutions] you've tried?" |
| Ideal outcome | What great looks like | "What would an ideal solution to [problem] look like for you?" |
| Triggers | What would make them act | "What would make you switch from your current approach to something new?" |
| Trust & credibility | What builds confidence | "What would a [product/brand] need to do to earn your trust in this space?" |
| Social influence | Role of others | "How do recommendations from friends, reviews, or social media influence your decisions about [category]?" |
| Willingness to pay / trade-offs | Value perception | "What would you be willing to pay or give up for a [product] that truly solved [problem]?" |
### Step 3: Ask All Questions in a Single Call
Send all 10-12 questions to the Digital Twins in one `ask_twins` call.
```
ask_twins(
audience: "[detailed audience description]",
questions: [
"How do you currently handle [problem]? Walk me through what a typical experience looks like.",
"What frustrates you most about [topic/problem]?",
"How does dealing with [problem] make you feel on a day-to-day basis?",
"When it comes to [category], what matters most to you and why?",
"When choosing a [product/solution] in this space, what do you look for first?",
"What tools, products, or approaches do you currently use for [problem]? What works and what doesn't?",
"What's missing from the [products/solutions] you've tried so far?",
"If you could design the perfect solution to [problem], what would it look like?",
"What would make you switch from your current approach to something completely new?",
"What would a brand or product need to do to earn your trust in this space?",
"How do recommendations from friends, reviews, or social media influence your decisions about [category]?",
"What would you be willing to pay or give up for something that truly solved [problem] for you?"
]
)
```
### Step 4: Analyse & Synthesise
Review all Digital Twin responses and compile findings:
- **Key themes**: Patterns across respondents and across questions
- **Emotional landscape**: Dominant feelings (frustration, anxiety, hope, guilt, indifference)
- **Current behaviour map**: How the audience navigates this space today
- **Pain point ranking**: Most intense and most common frustrations
- **Unmet needs**: Clearest gaps between what's available and what's wanted
- **Decision drivers**: What influences choice and action
- **Trust signals**: What builds or breaks confidence
- **Surprising insights**: Anything unexpected or counterintuitive
### Step 5: Deliver the Research Report
1. **Executive Summary** — Top-line findings in 2-3 sentences
2. **Key Themes** — 3-5 most significant patterns, with supporting quotes from Digital Twins
3. **Emotional Landscape** — What emotions drive behaviour in this space
4. **Current Behaviour & Pain Points** — How the audience deals with the problem today and what's broken
5. **Unmet Needs & Ideal Outcomes** — Gaps and what "great" looks like to the audience
6. **Decision Drivers & Trust Signals** — What influences choice and earns confidence
7. **Opportunities** — Actionable insights for product, marketing, or strategy
8. **Recommendations** — Specific next steps based on the research
## Tips for Best Results
- **Be specific with audiences**: "Women aged 25-35 in the UK interested in fitness who have tried meal planning apps" yields far better results than "women interested in health"
- **Ask open-ended questions**: Start with "How", "What", "Why", "Walk me through..."
- **Adapt the question template**: The 12 questions above are a framework — tailor them to the specific topic
- **Let the Twins speak**: Include direct quotes from Digital Twins in findings — they carry authenticity and emotional weight
- **Don't lead**: Ask "What matters to you about X?" not "Don't you think X is important?"
- **Look for tension**: The most valuable insights often sit in contradictionsICP Discovery
Find your ideal customer profile by testing your product or concept across 5+ distinct demographic segments simultaneously. Instead of guessing who to target, let real people tell you who cares most — and why.
Use when: You don't know who to target, you're entering a new market, launching a new product, want to validate target market assumptions, or need to compare audience receptivity across segments before committing budget.
View full skill
markdown
---
name: icp-discovery
description: "Use this skill to discover the ideal customer profile (ICP) and target audience for a product, concept, or idea by testing it across multiple demographic segments. Triggers include: requests to find the best audience for a product, identify an ICP, discover who a product resonates with most, explore which demographic segments respond best to a concept, validate target market assumptions, find product-market fit, or uncover unexpected audience opportunities. Also use when a user doesn't know who to target, is entering a new market, launching a new product, or wants to compare audience receptivity across segments before committing budget. Uses OriginalVoices Digital Twins (ask_twins) to test the same product/concept across 5+ distinct demographic segments simultaneously, then ranks segments by fit and extracts messaging guidance for the top ICP."
---
# ICP & Target Audience Discovery Agent
## Overview
Find your ideal target audience by testing your product, concept, or idea across multiple demographic segments simultaneously. Instead of guessing who to target, this workflow puts your offering in front of 5+ distinct audiences and lets real people tell you who cares most — and why. You'll walk away with a ranked list of segments, deep messaging guidance for your top ICP, and a clear picture of how every segment responded.
## Workflow Steps
### Step 1: Understand the Product/Concept
Ask the user to either:
- **Describe** their product, concept, or idea in a few sentences, or
- **Share a link** to a landing page, product page, or pitch deck
That's all that's needed. From the description or link, extract a clear 1-2 sentence summary of what it is and what problem it solves. This summary will be used in the questions to each segment.
### Step 2: Select Candidate Segments
Based on the product/concept, propose 5-7 distinct demographic segments that represent a diverse cross-section of potential audiences. Good segments vary across multiple dimensions — not just age.
**Segment design principles:**
- Vary by age, gender, life stage, interests, income, and lifestyle
- Include at least one "unexpected" segment the user might not have considered
- Ensure segments don't overlap heavily
**Example segment set for a meal planning app:**
1. Busy working parents aged 30-45 with young children
2. Health-conscious young adults aged 20-30 living in cities
3. Men aged 35-45 interested in health and fitness
4. University students aged 18-24
5. Women aged 45-60
### Step 3: Build the Question Set
Design 4-6 questions that test receptivity, relevance, emotional response, and purchase intent. These same questions will be asked to every segment for direct comparison.
**Core questions (adapt to the specific product/concept):**
```
questions: [
"I'd like to tell you about [product/concept: 1-2 sentence description]. What's your initial reaction? Does this sound like something you'd be interested in? Why or why not?",
"How relevant is [the problem this solves] to your life right now? Is this something you actively think about or struggle with?",
"If [product/concept] existed and worked as described, how likely would you be to try it? What would hold you back?",
"What would [product/concept] need to do or say to convince you it's worth your time or money?",
"How would you describe [product/concept] to a friend? What would you say it is and who it's for?",
"What's the first thing you'd want to know before deciding whether to try [product/concept]?"
]
```
### Step 4: Run Segment-by-Segment Research
Make a separate `ask_twins` call for each segment, using the same questions every time. This ensures clean, comparable data across all segments.
```
# Segment 1
ask_twins(
audience: "Busy working parents aged 30-45 with young children in the US",
questions: [
"I'd like to tell you about [product description]. What's your initial reaction? Does this sound like something you'd be interested in? Why or why not?",
"How relevant is [problem] to your life right now? Is this something you actively think about?",
"If this existed and worked as described, how likely would you be to try it? What would hold you back?",
"What would it need to do or say to convince you it's worth your time or money?",
"How would you describe this to a friend? What would you say it is and who it's for?",
"What's the first thing you'd want to know before deciding whether to try this?"
]
)
# Segment 2
ask_twins(
audience: "Health-conscious Gen Z adults aged 20-28 living in cities",
questions: [
# Same questions as above
]
)
# ... Repeat for all segments
```
### Step 5: Score & Rank Each Segment
For each segment, evaluate responses across these dimensions:
| Dimension | What to Look For |
|-----------|-----------------|
| **Interest level** | Enthusiasm vs. indifference. Did they light up or shrug? |
| **Problem relevance** | Is the problem real and active in their life, or theoretical? |
| **Purchase intent** | Would they actually try/buy it, or is it a polite "maybe"? |
| **Emotional resonance** | Did it trigger a strong emotional response (excitement, relief, hope)? |
| **Objection severity** | Are their hesitations minor (price, timing) or fundamental (don't need it)? |
| **Natural language fit** | Did they describe the product in a way that could become marketing copy? |
| **Word-of-mouth potential** | Could they easily explain it to a friend? Did their description sound compelling? |
**Rank all segments from strongest to weakest fit** based on a holistic assessment of these dimensions.
### Step 6: Deep-Dive on Top ICP
For the #1 ranked segment, extract detailed messaging guidance:
- **Why they care**: The core motivation driving their interest
- **Their language**: Exact words and phrases they used to describe the product and problem
- **Key benefit**: The single benefit that resonated most
- **Primary objection**: The main thing holding them back — and how to address it
- **Emotional hook**: The feeling that drives them (relief, excitement, validation, fear)
- **How they'd describe it**: Their "friend description" becomes the basis for positioning
- **Trust signals needed**: What they said they'd want to know or see before trying it
- **Recommended messaging angle**: A 1-2 sentence positioning statement built from their actual words
### Step 7: Deliver the Full Report
**1. Executive Summary**
- The #1 target audience and why, in 2-3 sentences
- The biggest surprise from the research
**2. Segment Rankings**
| Rank | Segment | Interest | Relevance | Intent | Key Insight |
|------|---------|----------|-----------|--------|-------------|
| 1 | [Top segment] | High | High | High | [One-line insight] |
| 2 | [Second segment] | ... | ... | ... | ... |
| ... | ... | ... | ... | ... | ... |
**3. Top ICP Deep-Dive**
- Detailed messaging guidance (from Step 6)
- 3-5 direct quotes from Digital Twins that capture why this segment is the best fit
- Recommended positioning statement
- Suggested ad/marketing angles
**4. Segment-by-Segment Breakdown**
For each segment (including lower-ranked ones):
- **Overall fit**: High / Medium / Low
- **What resonated**: What they liked or responded to
- **What didn't land**: Where the product/concept fell flat
- **Key quote**: One representative quote
- **Verdict**: Should you target this segment? (Yes / Secondary / No — with reasoning)
**5. Messaging Matrix**
| Segment | Lead Message | Emotional Hook | Key Objection | Recommended? |
|---------|-------------|----------------|---------------|-------------|
| [Segment 1] | ... | ... | ... | Primary |
| [Segment 2] | ... | ... | ... | Secondary |
| [Segment 3] | ... | ... | ... | Deprioritise |
| ... | ... | ... | ... | ... |
**6. Strategic Recommendations**
- Primary ICP to target and the messaging angle to lead with
- Secondary audiences worth testing with smaller budget
- Segments to avoid and why
- Suggested next steps (e.g. "Run the Google Ad Copy workflow targeting your primary ICP")
## Tips for Best Results
- **Test at least 5 segments**: Fewer than 5 doesn't give enough contrast. 6-7 is ideal
- **Include a wildcard segment**: Always test one audience you wouldn't obviously target — surprises happen
- **Keep questions identical across segments**: Consistency is what makes comparison valid
- **Don't oversell the product**: Describe it factually in 1-2 sentences. Let the audience's genuine reaction tell the story
- **Watch for "polite interest" vs. real excitement**: Some audiences will say "sounds nice" without any real intent. Look for strong emotional language, specific use cases they imagine, and unprompted enthusiasm
- **The "friend description" question is gold**: How someone would explain your product to a friend is often better positioning than anything a marketer would write
- **Low-ranking segments are still valuable**: Understanding who doesn't care — and why — is just as strategic as finding who doesCreative Brief
Generate a creative brief grounded in real audience insight using OriginalVoices Digital Twins. Instead of writing briefs based on assumptions, this workflow researches the target audience first, then synthesises findings into a structured brief — so creative teams start with validated human understanding.
Use when: You need to write a creative brief, brief a creative team or agency, define campaign direction, or prepare a brief for designers, copywriters, or content creators. Ideal for kicking off any creative project with audience truth instead of guesswork.
View full skill
markdown
---
name: creative-brief
description: "Use this skill to generate a creative brief grounded in real audience insight. Triggers include: requests to write a creative brief, brief a creative team or agency, define a campaign brief, establish creative direction, or prepare a brief for designers, copywriters, or content creators. Uses OriginalVoices Digital Twins (ask_twins) to deeply understand the target audience's language, emotions, motivations, and preferences — then synthesises findings into a structured creative brief that gives creative teams a validated human foundation to build from, not assumptions."
---
# Creative Brief
## Overview
Generate a creative brief grounded in real audience insight using OriginalVoices Digital Twins. Instead of writing briefs based on assumptions or internal opinions, this workflow builds the brief from validated audience understanding — so creative teams start with what actually matters to real people.
## Workflow Steps
### Step 1: Gather Inputs
Collect from the user:
- **Product or service**: What is being promoted or communicated?
- **Campaign objective**: What should this creative achieve? (e.g. awareness, trial, conversion, repositioning)
- **Target audience**: Who is this for? Be as specific as possible — demographics, interests, lifestyle, values
- **Deliverables**: What will the creative team produce? (e.g. social ads, video, landing page, packaging, brand campaign)
- **Brand guidelines** (if any): Existing tone, visual identity, or messaging guardrails
- **Competitors or context** (optional): Who else is in the space? What's the competitive landscape?
- **Budget/timeline context** (optional): Any constraints that shape the brief
### Step 2: Audience Research via Digital Twins
Conduct deep audience research to build the brief on validated insight, not guesswork. Ask 10-12 questions covering emotional drivers, language, pain points, aspirations, preferences, and what makes the audience act.
```
ask_twins(
audience: "[detailed target audience description]",
questions: [
"When you think about [product category], what matters most to you? What do you actually care about?",
"What frustrates you most about [product category / current solutions]? What do brands in this space get wrong?",
"How does [the problem this product solves] make you feel day-to-day? What emotions come up?",
"When you see ads or content about [category], what catches your attention? What makes you stop scrolling?",
"What kind of tone or voice feels right for a [category] brand talking to someone like you? What feels off?",
"Can you describe a moment when you realised you really needed a better [product/solution]? What was happening?",
"What would make you trust a new brand in this space enough to try it? What signals credibility to you?",
"If a product like [product] truly delivered, how would your life or routine be different? What would change?",
"What words or phrases do you use when talking about [problem/category] with friends or family?",
"When you see [category] advertising, what turns you off immediately? What feels fake or irrelevant?",
"What would a brand need to say or show to make you feel like they genuinely understand people like you?",
"Who or what influences your decisions about [category]? Where do you go for recommendations?"
]
)
```
**Note:** Tailor questions to the specific product and campaign. If the brief is for a visual campaign, add questions about imagery and aesthetics. If it's for a specific channel, ask about that channel's consumption habits.
### Step 3: Identify the Key Insight
From the research, identify the single most important human truth — the insight that should anchor the entire brief. A strong insight:
- Reveals a tension, desire, or unmet need the audience feels deeply
- Is specific enough to inspire creative work (not generic)
- Creates an "of course" reaction — it feels true and recognisable
- Connects the audience's world to what the product can deliver
**Test your insight:** If you could say it about any brand in any category, it's too generic. If it only makes sense for this audience and this product, you've found it.
### Step 4: Deliver the Creative Brief
Structure the brief as follows:
**1. Background & Context**
- What's the situation? Why is this creative needed now?
- Product/service overview
- Competitive landscape (informed by what the audience actually said about alternatives)
**2. Objective**
- What must this creative achieve?
- Primary KPI or success metric
**3. Target Audience Profile**
- Demographics and psychographics
- How they think and feel about the category (grounded in Twin responses)
- Their language — actual words and phrases they use
- What they care about most, in their own words
- Key emotional drivers
**4. Key Insight**
- The single human truth that anchors this brief
- Supporting evidence from audience responses
**5. Single-Minded Message**
- The one thing the audience should think, feel, or do after seeing this creative
- Must flow directly from the insight
**6. Support Points**
- 3-4 reasons to believe
- Product truths that validate the message
- Proof points or credibility signals the audience said matter to them
**7. Tone & Manner**
- How the creative should feel (grounded in what the audience said resonates)
- What to avoid (grounded in what the audience said turns them off)
- Audience quotes that capture the right tone
**8. Audience Do's and Don'ts**
| Do (resonates with this audience) | Don't (falls flat or alienates) |
|---|---|
| [Specific thing that works, with quote] | [Specific thing to avoid, with quote] |
| [Another thing that works] | [Another thing to avoid] |
| [Continue based on findings] | [Continue based on findings] |
**9. Mandatories & Guardrails**
- Brand guidelines to follow
- Legal or compliance requirements
- Channel-specific constraints
**10. Deliverables & Format**
- What the creative team needs to produce
- Dimensions, formats, or specifications
## Tips for Best Results
- **Lead with audience language**: Use the actual words Twins used — they reveal how real people think and talk about this category
- **One insight, not five**: The best briefs are ruthlessly focused. Pick the most powerful insight and build everything around it
- **Tensions are gold**: If the audience revealed a tension (e.g. "I want X but I'm afraid of Y"), that's often the strongest creative territory
- **Specificity inspires creativity**: "Busy mums who feel guilty about screen time" inspires better work than "parents aged 25-45"
- **Include raw quotes**: Creative teams connect with real voices more than summarised findings
- **Don't prescribe executions**: The brief should inspire creative solutions, not dictate them. Define the "what" and "why", let the creative team own the "how"
## Common Pitfalls to Avoid
- **Brief by committee**: Cramming every stakeholder's opinion into the brief dilutes focus
- **Generic insights**: "People want quality at a good price" isn't an insight — it's a truism
- **Multiple messages**: If the brief has more than one key message, it has no key message
- **Skipping the audience**: Writing the brief first and then looking for audience data to support it defeats the purpose
- **Internal language in the brief**: If the audience wouldn't use a word, it shouldn't be in the insight or message
- **Confusing features with benefits**: The audience cares about outcomes, not specifications
## Creative Brief Quality Checklist
Before delivering, verify:
- [ ] Insight is specific to this audience and product (not interchangeable)
- [ ] Single-minded message is truly single-minded (one idea, not three)
- [ ] Audience profile uses their actual language, not marketing speak
- [ ] Tone guidance is grounded in what the audience said, not internal preference
- [ ] Do's and Don'ts are backed by real audience quotes
- [ ] Brief would inspire creative work (not just inform it)
- [ ] A creative team could start working from this brief aloneCreative Testing
Test and validate creative concepts — ads, copy, taglines, scripts, packaging, or any creative output — with real audience feedback before you spend budget. Supports testing up to 10-12 concepts in a single session.
Use when: You want to test ad concepts, validate marketing copy or taglines, compare creative directions, get audience reactions to campaign ideas, pre-test scripts or email copy, or evaluate any creative output with a target audience before launch.
View full skill
markdown
---
name: creative-testing
description: "Use this skill to pre-test and validate creative concepts using real audience feedback. Triggers include: requests to test ad concepts, validate marketing copy or taglines, compare creative directions, get audience reactions to campaign ideas, pre-test scripts or email copy, or evaluate any creative output with a target audience before launch. Supports testing up to 10-12 concepts at once. Uses OriginalVoices Digital Twins (ask_twins) to gather honest gut reactions from the target audience, revealing which concepts resonate most and why — so you can commit budget with confidence."
---
# Creative Testing
## Overview
Test and validate creative concepts — ads, marketing copy, taglines, scripts, packaging, or any creative output — using real audience feedback from OriginalVoices Digital Twins. Get honest reactions before you spend budget, not after. Supports testing up to 10-12 concepts in a single session.
## Workflow Steps
### Step 1: Gather Inputs
Only two things are required:
- **Creative concepts**: The concepts to test (up to 10-12). Full text, descriptions, or summaries of each
- **Target audience**: Who is this creative intended for?
### Step 2: Get Audience Reactions
Present the creative concepts to Digital Twins and gather open-ended gut reactions. For smaller sets (2-4 concepts), you can include them all in one question for direct comparison. For larger sets, group them into batches or test individually.
**For 2-4 concepts (direct comparison):**
```
ask_twins(
audience: "[detailed target audience description]",
questions: [
"I'm going to show you a few [ad concepts/taglines/etc]. Please read them all and tell me which one resonates most with you and why.\n\nConcept A: [full text]\n\nConcept B: [full text]\n\nConcept C: [full text]",
"What is your gut reaction to Concept A: '[concept A]'? What does it make you think or feel?",
"What is your gut reaction to Concept B: '[concept B]'? What does it make you think or feel?",
"What is your gut reaction to Concept C: '[concept C]'? What does it make you think or feel?"
]
)
```
**For 5-12 concepts (batched):**
Split into groups and ask for reactions to each:
```
ask_twins(
audience: "[detailed target audience description]",
questions: [
"What is your gut reaction to this [ad/tagline/concept]? What does it make you think or feel?\n\n'[concept 1]'",
"What is your gut reaction to this [ad/tagline/concept]? What does it make you think or feel?\n\n'[concept 2]'",
"What is your gut reaction to this [ad/tagline/concept]? What does it make you think or feel?\n\n'[concept 3]'",
# ... continue for each concept
"Looking at all of these together, which one stands out to you most and why?\n\n[list all concepts]"
]
)
```
### Step 3: Analyse & Compare
For each concept, compile:
- **Overall preference**: Which concepts were preferred and by how much
- **Strengths**: What people liked
- **Weaknesses**: What didn't land or caused hesitation
- **Emotional resonance**: What feelings each concept triggered
- **Suggested improvements**: What the audience said would make it better
### Step 4: Deliver the Verdict
1. **Winner & Why** — Which concept performed best overall, and the key reason
2. **Concept-by-Concept Breakdown** — Strengths, weaknesses, and audience quotes for each
3. **Key Insight** — The most important thing learned about what the audience responds to
4. **Recommendations** — Proceed as-is, iterate, or combine elements from multiple concepts
5. **Improvement Suggestions** — Specific changes the audience recommended
## Tips for Best Results
- **Present concepts in full**: Show the actual copy the audience would see
- **Gut reactions are gold**: Initial reactions are the most honest — that's why we lead with them
- **Don't reveal which concept you prefer**: Let the audience react without bias
- **Quote the Twins directly**: Real quotes carry more weight in creative reviews than summaries
- **Test at similar polish levels**: Comparing rough draft to polished concept is unfair
- **Batch smartly**: For large sets, always include a final "which stands out most" question so you get a clear overall rankingFacebook Ad Copy
Generate Facebook and Instagram ad copy grounded in real audience insight. Instead of relying on generic AI output, this workflow first talks to your target audience, then creates 10-15 ad variations rooted in what real people actually said.
Use when: You need Facebook or Meta ad campaigns, want to refresh stale ad creative, build ad sets for different audience segments, or generate audience-tested ad variations.
View full skill
markdown
---
name: facebook-ad-copy
description: "Use this skill to generate Facebook and Instagram ad copy grounded in real audience insight. Triggers include: requests to create Facebook or Meta ad campaigns, write primary text and headlines for Facebook ads, refresh stale social ad creative, build ad sets for different audience segments, or generate audience-tested ad variations. Uses OriginalVoices Digital Twins (ask_twins) to deeply research the target audience's language, preferences, concerns, and experiences, then generates 10-15 audience-informed ad variations rooted in what real people actually said — not AI guesswork."
---
# Facebook Ad Copy Agent
## Overview
Generate Facebook and Instagram ad copy informed by real audience insight. Instead of relying on AI guesswork to write ads, this workflow first talks to your target audience to understand their language, preferences, concerns, and experiences — then uses those insights to create ads that speak to what real people actually care about.
## Workflow Steps
### Step 1: Gather Inputs
Only two things are required:
- **Target audience**: Who are these ads for? (e.g. "Women aged 25-40 in the US interested in skincare and wellness")
- **Product/concept**: Either a description in their own words, or a link to a product page / landing page / pitch deck
Optional:
- **Number of ad variations**: How many do they want? Default to 10-15 if not specified
- **Tone or brand voice preferences**: Any specific tone to match?
### Step 2: Audience Research
This is the most important step. Use `ask_twins` to understand the audience's world — their language, what they care about, what frustrates them, what grabs their attention, and how they relate to the problem space. Ask broad questions about the general topic area, not just about the specific product.
```
ask_twins(
audience: "[detailed target audience description]",
questions: [
"What's your biggest frustration or challenge when it comes to [general topic area, e.g. skincare, fitness, cooking, managing finances]?",
"What matters most to you when choosing a [product category]? What do you look for?",
"Have you tried any [products/solutions in this space] before? What was your experience — what worked and what didn't?",
"What concerns or hesitations would you have about trying a new [product in this category]?",
"What would a brand need to say or show to earn your trust in this space?",
"How do you typically discover new [products in this category]? What influences your decisions?"
]
)
```
**Why this matters:** These questions surface the real language people use, the emotions they feel, the objections they hold, and the experiences that shape their decisions. This is what makes the ads resonate — not generic marketing copy.
### Step 3: Analyse Audience Insights
Review all responses and extract:
- **Pain points in their own words**: The exact language they use to describe frustrations
- **Preferences and priorities**: What they look for and value in this category
- **Experiences and context**: What they've tried before and how it went
- **Concerns and objections**: What would hold them back from trying something new
- **Trust signals**: What builds or breaks confidence
- **Emotional drivers**: The feelings that motivate action (relief, excitement, validation, fear of missing out)
### Step 4: Generate Ad Variations
Using the audience insights, generate 10-15 ad variations (or the number requested). Every ad should be directly traceable to something the audience actually said — a pain point, a preference, a phrase, an emotion.
**Facebook Ad Copy Structure:**
- **Primary text**: Main body copy (125 chars visible before "See more"; full text up to 1,000+)
- **Headline**: Appears below the image/video (up to 40 chars recommended)
- **Description**: Below the headline (up to 30 chars recommended)
- **CTA button**: Shop Now, Learn More, Sign Up, Get Offer, etc.
**Spread variations across different angles, drawing from the research:**
- **Pain point ads**: Open with a frustration the audience described, in their words
- **Benefit-first ads**: Lead with the outcome or feeling they said they want most
- **Social proof / trust ads**: Built around the trust signals and credibility markers they mentioned
- **Experience-based ads**: Reference the common experiences they shared (what they've tried, what failed)
- **Objection-handling ads**: Directly address a concern or hesitation from the research
For each ad, note which audience insight it's built on.
### Step 5: Validate with Audience (Optional but Recommended)
Test 3-5 of the strongest ads back with the audience.
```
ask_twins(
audience: "[same target audience]",
questions: [
"Imagine you're scrolling through Facebook and you see this ad: '[primary text + headline]'. Would you stop scrolling? Would you click? Why or why not?",
"Which of these ad openings grabs you most? A: '[opening A]' B: '[opening B]' C: '[opening C]'. Tell me why.",
"Is there anything in these ads that feels off, unbelievable, or would make you keep scrolling?"
]
)
```
### Step 6: Deliver Final Ad Set
Present the full set of ad variations with:
- Each ad in full (primary text, headline, description, CTA)
- The audience insight driving each ad clearly labelled
- Ads grouped by angle (pain point, benefit, trust, experience, objection)
- Validation results (if done)
- Top 3-5 recommended ads to test first
- A/B testing suggestions (which ads to test against each other)
## Facebook Ad Copy Guidelines
| Element | Recommended | Max |
|---------|-------------|-----|
| Primary text | 125 chars (before truncation) | ~1,000+ chars |
| Headline | 27-40 chars | 255 chars |
| Description | 27-30 chars | 255 chars |
## Tips for Best Results
- **The research makes the ads**: The audience research step is what separates these ads from generic AI output. Don't rush it
- **Write how people talk**: If the audience says "I just want something that actually works", put that in the ad — not "Experience seamless efficacy"
- **Front-load the hook**: First 125 characters are all that shows before "See more"
- **One insight per ad**: Each ad should be built on one clear audience insight, not five crammed together
- **Include the "why" for each ad**: Labelling which insight drives each ad helps the user understand why it should work and makes it easier to iterate
- **Variety matters**: 15 ads that all say the same thing in different words aren't useful. Spread across genuinely different angles and motivations from the researchGoogle Ad Copy
Generate Google Responsive Search Ad (RSA) assets grounded in real audience insight. Creates 15 headlines and 4 descriptions optimized for Quality Score, with proper character limits, keyword integration, and table format ready for Google Ads.
Use when: You need Google Search ad campaigns, want RSA-ready assets, need to improve Quality Score and ad relevance, or generate audience-tested variations for better performance.
View full skill
markdown
---
name: google-ad-copy
description: "Use this skill to generate Google ad copy grounded in real audience insight. Triggers include: requests to create Google Search or Display ad campaigns, write Responsive Search Ad (RSA) headlines and descriptions, refresh underperforming Google ad copy, or generate audience-informed ad variations for A/B testing. Uses OriginalVoices Digital Twins (ask_twins) to deeply research the target audience's language, preferences, concerns, and experiences, then generates audience-informed RSA assets rooted in what real people actually said — not AI guesswork."
---
# Google Ad Copy Agent
## Overview
Generate Google Responsive Search Ad (RSA) assets informed by real audience insight. This workflow researches your target audience first, then creates RSA-ready headlines and descriptions that speak to what real people actually care about — ensuring higher relevance scores and better performance.
## Workflow Steps
### Step 1: Gather Inputs
Required:
- **Target audience**: Who are these ads for? (e.g. "Small business owners aged 30-50 in the US looking for accounting software")
- **Product/offer**: Description or link to product page / landing page
- **Primary keywords**: 2-3 main search terms you're targeting (for relevance and Quality Score)
Optional:
- **Landing page URL**: To ensure message match
- **Unique value prop**: What makes this different from competitors
### Step 2: Audience Research
Use `ask_twins` to understand the audience's world — their language, pain points, and search behavior. This informs ad copy that resonates.
```
ask_twins(
audience: "[detailed target audience description]",
questions: [
"What's your biggest frustration when it comes to [problem/category]?",
"What matters most to you when choosing a [product category]?",
"If you were searching on Google for [solution], what exact words would you type?",
"What would make you click on an ad for [product type]? What would make you scroll past?",
"What concerns or doubts would you have before trying a new [product/solution]?",
"What would a headline need to say to grab your attention and feel relevant to you?"
]
)
```
### Step 3: Extract Key Insights
Analyze responses and identify:
- **Search language**: Exact phrases they'd type into Google (use these in headlines)
- **Pain points**: Their top frustrations (lead with these)
- **Value drivers**: What matters most (benefits to emphasize)
- **Trust factors**: What builds confidence (use in descriptions)
- **Attention triggers**: What makes them click vs scroll past
### Step 4: Generate RSA Assets
Create **15 headlines** and **4 descriptions** using the audience insights. Follow Google RSA format strictly.
**Headlines (30 characters max each):**
- Include primary keyword in at least 3 headlines (for relevance)
- Vary approaches: pain point, benefit, question, social proof, urgency
- Mix short (15-20 chars) and long (25-30 chars) for better combinations
- Use audience's exact language where possible
- Every headline must be unique and work independently
**Descriptions (90 characters max each):**
- Description 1: Lead benefit + CTA
- Description 2: Address objection + unique value
- Description 3: Social proof + CTA
- Description 4: Alternative angle (pain point or different benefit)
**Format each asset with:**
- Character count verification (must be exact)
- Audience insight it's based on
- Strategic note (e.g., "keyword headline", "pain point hook")
### Step 5: Structure for Google Ads
Deliver assets in this format:
**HEADLINES (15 required)**
| # | Headline | Chars | Insight | Strategy |
|---|----------|-------|---------|----------|
| H1 | [headline text] | 28 | [insight] | Keyword + benefit |
| H2 | [headline text] | 22 | [insight] | Pain point |
| ... | ... | ... | ... | ... |
**DESCRIPTIONS (4 required)**
| # | Description | Chars | Insight | Strategy |
|---|-------------|-------|---------|----------|
| D1 | [description text] | 87 | [insight] | Benefit + CTA |
| D2 | [description text] | 89 | [insight] | Objection handling |
| D3 | [description text] | 84 | [insight] | Social proof |
| D4 | [description text] | 90 | [insight] | Alternative angle |
**PINNING RECOMMENDATIONS:**
- Pin H1 to position 1 only if it must always show (e.g., brand name + keyword)
- Otherwise let Google optimize combinations
- Never pin more than 2-3 assets total
### Step 6: Validate Top Performers (Optional)
Test 3-5 strongest headline + description combinations with the audience:
```
ask_twins(
audience: "[same target audience]",
questions: [
"You're searching Google for '[search term]' and see this ad: Headline: '[H1]' Description: '[D1]'. Would you click? Why or why not?",
"Between these ads, which grabs you most? A: '[H2 + D2]' B: '[H5 + D3]' C: '[H8 + D1]'. Why?"
]
)
```
Update assets based on feedback before finalizing.
### Step 7: Quality Score Checklist
Before delivering, verify:
- ✓ Primary keyword appears in at least 3 headlines
- ✓ All headlines ≤30 characters (Google rejects otherwise)
- ✓ All descriptions ≤90 characters
- ✓ Headlines are diverse (not 15 variations of the same thing)
- ✓ Descriptions work with any headline combination
- ✓ Copy matches landing page messaging
- ✓ Clear CTA in at least 2 descriptions
- ✓ Assets use audience's actual language from research
## RSA Best Practices
**Headline Strategy:**
- 3-5 headlines with primary keyword (for relevance)
- 3-5 headlines addressing different pain points
- 2-3 benefit-focused headlines
- 2-3 social proof or trust-building headlines
- 1-2 question or curiosity headlines
**Description Strategy:**
- Lead with the strongest benefit (based on research)
- Address the top objection from audience research
- Include social proof or trust signals
- Provide alternative angle for variety
**Character Optimization:**
- Shorter headlines (15-22 chars) pair well with longer ones
- Max out description length (85-90 chars) to provide context
- Front-load important words (first 15 chars of headlines are critical)
**Keyword Integration:**
- Include keywords naturally, not stuffed
- Use exact phrases from "what would you search for" responses
- Match search intent (don't promise what landing page doesn't deliver)
## Common Pitfalls to Avoid
- **Keyword stuffing**: Google's algorithm detects this and lowers Quality Score
- **Generic headlines**: "Best Software" performs worse than specific benefits from research
- **Over-pinning**: Pinning too many assets limits Google's optimization
- **Identical variations**: "Get Started Today" and "Start Today" waste asset slots
- **Ignoring character limits**: Google truncates or rejects — verify every asset
- **Feature dumping**: Lead with benefits and outcomes the audience cares about
- **No CTA**: Every description should guide the user to act
## Output Checklist
Final deliverable includes:
1. ✓ 15 unique headlines (all ≤30 chars)
2. ✓ 4 unique descriptions (all ≤90 chars)
3. ✓ Character count verified for every asset
4. ✓ Table format ready to copy into Google Ads
5. ✓ Insight source documented for each asset
6. ✓ Pinning recommendations (if any)
7. ✓ Quality Score checklist completed
8. ✓ Top 3-5 predicted best-performing combinations highlightedVideo Script Generation
Generate video scripts for creators or AI, informed by real audience insight. This workflow researches your target audience to understand what hooks them, what tone resonates, what keeps them watching, and what drives engagement — then writes complete video scripts optimized for that audience.
Use when: You need to write video scripts, create content for YouTube/TikTok/Instagram, generate video narration, write video copy, or create scripts for video ads.
View full skill
markdown
---
name: video-script-generation
description: "Use this skill to generate video scripts for creators or AI, informed by real audience insight. Triggers include: requests to write video scripts, create content for YouTube/TikTok/Instagram, generate video narration, write video copy, or create scripts for video ads. Uses OriginalVoices Digital Twins (ask_twins) to understand what hooks the audience, what tone resonates, what keeps them watching, and what drives engagement — then writes complete video scripts optimized for that audience."
---
# Video Script Generation Agent
## Overview
Generate video scripts for creators or AI, informed by real audience insight. This workflow researches your target audience to understand what hooks them in the first seconds, what tone and pacing they prefer, what keeps them watching, and what drives engagement — then uses those insights to write complete video scripts that resonate and perform.
## Workflow Steps
### Step 1: Define Video Context
Gather from the user:
- **Video topic/concept**: What is the video about? (e.g. "How to choose the right CRM", "Product demo for productivity app", "Brand story video")
- **Target audience**: Who is this video for? (e.g. "Small business owners", "Gen Z interested in personal finance", "Marketing managers")
- **Video goal**: What should it achieve? (Education, product awareness, entertainment, conversion, brand building)
- **Platform**: Where will this video be published? (YouTube, TikTok, Instagram Reels, LinkedIn, website, video ad)
- **Video length**: Target duration (e.g. "30 seconds", "60 seconds", "3-5 minutes", "10+ minutes")
- **Product/brand info** (if applicable): What needs to be mentioned or featured?
- **Tone preference** (optional): Any specific tone requirements? (Educational, entertaining, inspirational, etc.)
### Step 2: Research Audience Video Preferences
One comprehensive research call to understand what will make this video effective for this audience.
```
ask_twins(
audience: "[detailed target audience]",
questions: [
"When you're watching videos about [topic], what makes you stop scrolling and actually watch in the first 3-5 seconds?",
"For videos about [topic], do you prefer: A) Fast-paced, energetic style, or B) Slower, more detailed style? Why?",
"What tone do you prefer for videos about [topic]? A) Casual and conversational, B) Professional and informative, C) Entertaining and humorous?",
"When watching a video about [topic], how long should it be? Would you watch a 5-minute video, or do you prefer under 60 seconds?",
"What makes you keep watching a video about [topic] vs. clicking away or scrolling past? What keeps your attention?",
"What information or value would you expect from a video about [topic]? What should it teach or show you?",
"Do you prefer videos that: A) Tell a story, B) Give step-by-step instructions, C) Show quick tips, or D) Explain concepts?",
"When watching videos about [topic], do you prefer to see: A) A person talking to camera, B) Voiceover with visuals, C) Text on screen with music, or D) Doesn't matter?",
"What would make you comment on, share, or save a video about [topic]? What creates that reaction?",
"What turns you off in videos about [topic]? What makes you stop watching immediately?",
"For videos about [topic], would you rather: A) Get straight to the point, or B) Have some build-up or context first?",
"If a video about [topic] has a call-to-action at the end (subscribe, visit website, buy something), does that feel natural or pushy?"
]
)
```
### Step 3: Analyse Video Content Insights
Review audience responses and extract:
**Hook Strategy:**
- What captures attention in the first 3-5 seconds
- What makes them stop scrolling
- Hook styles that work vs. don't work
**Tone & Style:**
- Preferred tone (casual, professional, entertaining)
- Pacing preference (fast vs. slow)
- Energy level
**Content Structure:**
- Preferred format (story, how-to, tips, explanation)
- Optimal length for this topic and audience
- Information depth they want
**Engagement Drivers:**
- What keeps them watching
- What makes them engage (comment, share, save)
- What creates value for them
**Turnoffs:**
- What makes them stop watching
- What feels pushy or off-putting
- What to avoid
**CTA Approach:**
- Whether CTAs feel natural or pushy
- How to integrate them effectively
### Step 4: Write the Complete Video Script
**IMPORTANT**: Using the insights from Step 3, now write the complete video script ready to record. Output the full script with hooks, narration, and timing notes.
**Script structure:**
**[0:00-0:05] HOOK (First 3-5 seconds)**
- Open with the hook that stops them scrolling (based on research)
- Address their problem, curiosity, or interest immediately
- Make it impossible to scroll past
**[0:05-0:XX] INTRO (If appropriate for length)**
- Quick context or credibility (if needed)
- Set expectations for what they'll learn/get
- Keep it brief - only if research showed they want build-up
**[0:XX-X:XX] MAIN CONTENT**
- Deliver on the hook's promise
- Use their preferred tone and pacing (from research)
- Structure based on format preference (story, how-to, tips, explanation)
- Include the information they said they expect
- Keep attention with variety, value, or entertainment
- Match the depth they want (quick tips vs. detailed explanation)
**[X:XX-X:XX] PAYOFF/CONCLUSION**
- Summarize key takeaway or deliver final value
- Reinforce the benefit they got from watching
- Create satisfaction or curiosity
**[X:XX-END] CALL-TO-ACTION (If appropriate)**
- Natural CTA based on video goal (subscribe, visit website, try product, etc.)
- Integrate smoothly based on research (don't be pushy if they said that's a turnoff)
- Make it feel like a natural next step
**Writing guidelines:**
- Write in spoken language (how people talk, not formal writing)
- Use their preferred tone (casual/professional/entertaining from research)
- Match pacing preference (short punchy sentences for fast-paced, longer for detailed)
- Include [timing markers] so creators know pacing
- Include [VISUAL NOTES] in brackets if helpful for context, but focus on the script
- Write exactly what should be said/shown on screen
- Make it ready to record or input into AI video tools
**Output the complete script now** - from hook through CTA, ready to use.
### Step 5: Deliver Video Script Package
**PRIMARY DELIVERABLE - Complete Video Script:**
Output the full, production-ready video script including:
- Timing markers [0:00-0:05]
- Hook
- Intro (if appropriate)
- Main content narration/dialogue
- Payoff/conclusion
- Call-to-action (if appropriate)
- [Visual notes] where helpful
- Ready to record or use in AI video generation tools
**THEN provide supporting materials:**
**1. Script Overview:**
- **Target length**: Estimated final video duration
- **Tone**: Casual/professional/entertaining based on research
- **Format**: Story/how-to/tips/explanation
- **Platform optimization**: Specific to YouTube/TikTok/Instagram/etc.
**2. Key Insights Used:**
- **Hook strategy**: What captures their attention (with research quote)
- **Tone & pacing**: What style resonates with them
- **Content structure**: What format they prefer
- **Engagement drivers**: What keeps them watching
- **CTA approach**: How to ask for action without being pushy
**3. Audience Video Profile:**
- What hooks them in the first seconds
- Preferred tone and pacing
- Optimal video length for this topic
- What keeps them watching vs. clicking away
- What drives engagement (shares, comments, saves)
**4. Production Notes:**
- Delivery tips based on tone preference
- Pacing guidance (fast vs. slow)
- Visual suggestions (if audience expressed preference)
- Platform-specific considerations
**5. Optimization Recommendations:**
- Alternative hooks to test
- Engagement tactics based on what drives shares/comments
- CTA variations to try
- A/B test suggestions
## Video Script Framework
| Script Element | Audience Insight Source | Optimization Approach |
|----------------|------------------------|----------------------|
| **Hook (0-5 sec)** | What stops them scrolling | Lead with their problem/curiosity/interest |
| **Intro** | Whether they want build-up | Skip if they want to "get to the point"; brief if they want context |
| **Tone** | Casual/professional/entertaining preference | Match their preferred style throughout |
| **Pacing** | Fast vs. slow preference | Short sentences for fast; longer, detailed for slow |
| **Content structure** | Story/how-to/tips/explanation | Organize based on format preference |
| **Depth** | How much information they want | Match detail level to their expectations |
| **Length** | Optimal duration for topic | Stay within their attention span sweet spot |
| **Engagement hooks** | What keeps them watching | Use variety, value, or entertainment tactics |
| **CTA** | Whether CTAs feel natural or pushy | Integrate smoothly or skip if it's a turnoff |
## Tips for Best Results
- **First 5 seconds are everything**: The hook must stop the scroll based on research
- **Write how people talk**: Spoken language, not written language
- **Match their energy**: Fast-paced and punchy, or calm and detailed
- **Deliver on the hook**: Whatever you promise in the first 5 seconds, deliver quickly
- **Cut ruthlessly**: If research says they want it short, every word must earn its place
- **Use pattern interrupts**: Variety keeps attention (questions, facts, stories, etc.)
- **Natural CTAs**: If they said pushy feels bad, make it a soft suggestion
- **Platform matters**: TikTok scripts ≠ YouTube scripts ≠ LinkedIn scripts
## Common Video Script Pitfalls
- **Slow hook**: Taking too long to get to the point when they want it fast
- **Wrong tone**: Being too casual for professional topics or too formal for entertainment
- **Too long**: Ignoring research that says they prefer 60 seconds when you write 5 minutes
- **Buried value**: Saving the best for last when they'll click away before they get there
- **Generic opening**: "Hey guys, today we're talking about..." when they need a strong hook
- **Pushy CTA**: Hard-selling when research says they hate that
- **Written language**: Sounding like an essay instead of natural speech
- **No payoff**: Building up without delivering satisfaction at the end
## Red Flags (Revise Script)
- Hook doesn't address what they said stops them scrolling
- Tone doesn't match their preference (too casual, formal, or salesy)
- Length exceeds their attention span for this topic
- Pacing is off (too fast when they want detail, too slow when they want quick tips)
- CTA feels forced when they said pushy is a turnoff
- Content doesn't deliver what they said they expect from videos on this topic
## Green Lights (Strong Script)
- Hook immediately addresses what captures their attention
- Tone and pacing match their preferences exactly
- Length fits their attention span for this topic
- Delivers the information or value they expect
- Structure matches format preference (story, how-to, tips)
- Keeps momentum with variety and engagement tactics
- CTA feels natural and appropriate for their expectations
- Written in spoken, natural language
- Platform-optimized for where it'll be publishedLanding Page Optimization
Optimize your landing page for conversion using real audience insight. Consolidates landing page research into one comprehensive call (12 questions) covering headline testing, trust signals, CTA preferences, and conversion drivers.
Use when: You want to improve conversion rates, test landing page copy, validate value propositions, optimize hero sections, test different messaging angles, or reduce bounce rates.
View full skill
markdown
---
name: landing-page-optimization
description: "Use this skill to optimize landing page messaging, structure, and conversion elements using real audience insight. Triggers include: requests to improve conversion rates, test landing page copy, validate value propositions, optimize hero sections, test different messaging angles, or reduce bounce rates. Uses OriginalVoices Digital Twins (ask_twins) to understand what resonates with visitors, what creates confusion or doubt, and what drives action — then generates optimized landing page variants grounded in real user responses."
---
# Landing Page Optimization Agent
## Overview
Optimize your landing page for conversion using real audience insight. This workflow researches how your target audience evaluates landing pages — what grabs attention, what creates trust, what triggers doubt, and what drives action — then uses those insights to craft landing page elements that convert.
## Workflow Steps
### Step 1: Gather Context
Collect from the user:
- **Current landing page**: URL or description of what the page currently says/shows
- **Target audience**: Who is this page for? (e.g. "Startup founders looking for project management tools")
- **Primary goal**: What action should visitors take? (sign up, purchase, book demo, etc.)
### Step 2: Research Landing Page Preferences & Conversion Drivers
One comprehensive research call covering current messaging evaluation, problem awareness, headline testing, trust signals, and CTA preferences.
```
ask_twins(
audience: "[detailed target audience]",
questions: [
"When you land on a website for a [product/service type], what do you look for first? What makes you stay vs. leave immediately?",
"What's the biggest challenge or frustration you face with [problem space]? When looking for a solution, what does success look like to you?",
"You land on a page with this headline: '[Test Headline A]'. Does this grab your attention? What about: '[Test Headline B]'? Which works better and why?",
"If a website opened with: '[Value prop angle 1]', would you keep reading or bounce? What's your immediate reaction?",
"What would be more compelling: A) '[Benefit-focused message]' or B) '[Problem-focused message]'? Why?",
"What concerns or hesitations do you typically have when considering a new [product category]? What would reduce those concerns?",
"What would make you trust this [product/service] enough to [take desired action]? What would you need to see?",
"How important are these elements: security badges, money-back guarantees, testimonials, customer logos, case studies? Which matter most?",
"Which call-to-action is more appealing: A) '[CTA option 1]' or B) '[CTA option 2]'? Why?",
"Would you rather: A) Start a free trial immediately or B) Book a demo first? What's your preference and why?",
"What would make you hesitate to click a '[primary CTA]' button? What would you be worried about?",
"If a form asked for [list of fields], would that feel like too much information upfront? What would you be comfortable sharing?"
]
)
```
**If there's an existing landing page to audit, include these additional questions:**
```
"Imagine landing on a page with this headline: '[current headline]'. Does this grab your attention? Why or why not?",
"The page says '[current value proposition]'. Is it immediately clear what this does and who it's for?",
"What questions would you have after reading this page? What would you want to know more about?"
```
### Step 3: Extract Key Insights
Analyze responses and identify:
**Hero Section Insights:**
- What grabs attention vs. what's ignored
- Most compelling headline angle
- Clearest value proposition framing
- What needs to be communicated immediately
**Trust & Credibility:**
- Which trust elements matter most
- What testimonial styles resonate
- Key objections that need addressing
**CTA & Conversion:**
- Optimal CTA copy and positioning
- Form friction points to reduce
- Optimal offer structure (trial, demo, immediate purchase)
**Content Hierarchy:**
- What information they need first
- What must be above the fold
- What can wait for below the fold
### Step 4: Generate Optimized Landing Page Variants
Create 3-5 landing page variants, each grounded in different insights from research.
**For each variant, deliver:**
- **Headline** — Hook that grabs attention (based on what resonated)
- **Subheadline** — Clarifies value prop (addresses top questions/concerns)
- **Value propositions** — 3-5 key benefits (in their language)
- **Social proof** — Type and positioning (testimonials, logos, stats)
- **Primary CTA** — Button copy and offer (based on what drives action)
- **Trust elements** — What to include above fold (security, guarantees, etc.)
- **Key sections** — Recommended page structure
**Label each variant with:**
- **Target insight** — Which research finding drives this variant
- **Best for** — What type of visitor or use case
- **Key hypothesis** — What makes this variant different and why it should work
**Spread variants across different angles:**
- Problem-focused (lead with pain point)
- Benefit-focused (lead with outcome)
- Trust-first (emphasize credibility and social proof)
- Direct/minimal (for audiences who prefer no-fluff)
- Story-driven (if research shows they value context)
### Step 5: Validate Top Variants (Optional)
Test 2-3 strongest variants back with the audience:
```
ask_twins(
audience: "[same audience]",
questions: [
"You land on a page with this headline: '[Variant A headline]' and description: '[Variant A subheadline]'. What's your immediate reaction? Would you keep reading?",
"Between these page openings, which would make you more likely to explore further? A: '[Variant A hero]' B: '[Variant B hero]'. Why?",
"On a scale of 1-10, how clear is it what this product does based on: '[Variant summary]'? What would make it clearer?",
"Would you feel ready to [take desired action] after reading this, or would you need more information? What's missing?"
]
)
```
Update variants based on feedback before finalizing.
### Step 6: Deliver Optimization Report
**1. Executive Summary:**
- Top recommended variant and expected impact
- Key finding (most important insight from research)
**2. Key Insights from Research:**
- What messaging resonates vs. what creates confusion
- Top objections and concerns to address
- Trust signals that matter most
- Optimal CTA and offer structure
**3. Landing Page Variants (3-5 full variants):**
- Complete copy for each (headline, subheadline, value props, CTA, etc.)
- Insight driving each variant
- When to use each (audience segment, traffic source, etc.)
**4. A/B Testing Plan:**
- Which variants to test first
- What elements to test (headline, CTA, social proof, etc.)
- Success metrics to track
**5. Quick Wins:**
- Simple changes that can be implemented immediately
**6. Common Pitfalls to Avoid:**
- Based on what the audience reacted negatively to
## Landing Page Element Guidelines
| Element | Best Practice |
|---------|---------------|
| **Headline** | Lead with strongest hook from testing; 6-12 words; avoid jargon |
| **Subheadline** | Clarify value prop; address top question; 10-20 words |
| **Value props** | Use audience's language; focus on outcomes; 3-5 bullets |
| **CTA** | Action-oriented; address friction points; repeat 2-3 times |
| **Social proof** | Above fold; match format that resonates |
| **Trust elements** | Address top concerns; position near CTA |
## Tips for Best Results
- **Clarity beats cleverness** — If they struggle to understand what the product does, clever copy won't convert
- **Address objections explicitly** — If research surfaced concerns, address them on the page
- **Use their language** — Use exact phrases from Digital Twin responses
- **Hierarchy matters** — Put the most important information (based on research) above the fold
- **Don't bury the CTA** — If they're ready to act, make it easy
- **Test drastically different variants** — Test genuinely different messaging angles, not just headline variations
- **Optimize for your audience** — Let research guide you, not generic "best practices"
## Common Pitfalls to Avoid
- **Feature dumping** — Listing features when audience cares about outcomes
- **Assuming understanding** — If research shows confusion, clarify immediately
- **Ignoring objections** — Address concerns explicitly, don't hope they resolve themselves
- **Weak CTAs** — Be specific based on what research shows they need ("Start Free 14-Day Trial" not "Get Started")
- **Too much friction** — Don't ask for information they're not comfortable providing yet
- **Generic social proof** — Testimonials must address specific concerns from research
## When to Use This Skill
- Landing page has low conversion rates and you don't know why
- Testing multiple messaging angles before committing to design
- Validating value propositions with target audience
- Understanding what trust signals matter most
- Optimizing hero section and above-the-fold content
- Reducing bounce rates from paid traffic
- Creating audience-specific landing page variantsEmail Campaign Copy
Generate email marketing campaigns informed by real subscriber insight. Consolidates email research into one comprehensive call (10 questions) covering subject lines, opening hooks, CTA drivers, and frequency tolerance.
Use when: You need email campaigns, want to improve open rates, write welcome sequences, create newsletters, launch announcements, or re-engagement emails.
View full skill
markdown
---
name: email-campaign-copy
description: "Use this skill to generate email marketing copy grounded in real audience insight. Triggers include: requests to write email campaigns, create newsletter content, improve email open rates, write welcome sequences, launch announcement emails, or re-engagement campaigns. Uses OriginalVoices Digital Twins (ask_twins) to understand what makes the audience open emails, what messaging resonates, what triggers action, and what causes unsubscribes — then generates audience-informed email variations rooted in real subscriber perspectives."
---
# Email Campaign Copy Agent
## Overview
Generate email marketing campaigns informed by real subscriber insight. This workflow researches how your target audience engages with email — what captures their attention, what they value, and what drives action — then creates emails that speak to what real people actually care about.
## Workflow Steps
### Step 1: Gather Campaign Context
Collect from the user:
- **Target audience**: Who is this email for? (e.g. "SaaS customers in their first 30 days")
- **Email type/goal**: Welcome series, product launch, newsletter, re-engagement, promotion, etc.
- **Key message or offer**: What's the main point?
- **Number of variations**: How many? (Default: 5-8)
Optional:
- **Current performance**: Open rates, click rates, unsubscribe rates
- **Tone/brand voice**: Any specific voice to match?
### Step 2: Research Audience Email Behavior & Preferences
One comprehensive research call covering email behavior, topic relevance, subject line testing, and messaging preferences.
```
ask_twins(
audience: "[detailed target audience]",
questions: [
"When you open your inbox, what makes you decide to open a marketing email vs. delete it? What grabs your attention in a subject line?",
"What's your biggest frustration with marketing emails? What makes you unsubscribe?",
"If you received an email about [topic/offer], what would make it feel valuable vs. just more noise? What would you want to know immediately?",
"You see these subject lines in your inbox. Which would you most likely open? A: '[Subject A]' B: '[Subject B]' C: '[Subject C]'. Why?",
"Imagine opening an email that starts with: '[Opening line A]'. Would you keep reading? What about: '[Opening line B]'? Which grabs you more?",
"Would you prefer: A) A short, direct email (2-3 paragraphs) that gets to the point quickly, or B) A longer, story-driven email? Why?",
"What would make you actually click a CTA button in this email vs. just reading and closing it?",
"What concerns or hesitations would you have about [offer/product/concept being promoted]?",
"How do you feel about email frequency from [brands in this category]? How often is too often?",
"If an email subject line said '[test subject line]', would that feel like clickbait or would it make you curious? Be honest."
]
)
```
### Step 3: Extract Key Insights
Analyze responses and identify:
**Subject Line Drivers:**
- What triggers opens (benefit, curiosity, urgency, personalization)
- What feels spammy or manipulative
- Optimal tone and length
**Email Body Preferences:**
- Optimal opening hook
- Tone that resonates (casual, direct, story-driven)
- Preferred length and structure
**CTA & Action:**
- What drives clicks
- How to frame the ask without being pushy
**Friction Points:**
- What causes unsubscribes
- Frequency tolerance
- What feels like noise
### Step 4: Generate Email Variations
Create 5-8 email variations, each built on different insights from research.
**For each email, deliver:**
- **Subject line** (6-10 words, grounded in what drives opens)
- **Preview text** (40-100 chars, complements subject line)
- **Email body**:
- Opening hook (2-3 sentences)
- Core message (3-5 short paragraphs or bullets)
- CTA (clear, specific, action-oriented)
- Sign-off
- **Insight label** — Which research finding drives this email
- **Best use case** — When/why to use this variant
**Spread variations across different angles:**
- Value-first (lead with clear benefit)
- Problem-aware (open with pain point)
- Direct/no-fluff (straight to the point)
- Social proof (credibility and trust)
- Story-driven (context or scenario)
- Curiosity-driven (only if research shows it resonates)
### Step 5: Validate Top Variants (Optional)
Test 3-5 strongest emails back with the audience:
```
ask_twins(
audience: "[same audience]",
questions: [
"You receive this email. Subject: '[Subject]'. Would you open it? If you opened it and saw: '[Opening]', would you keep reading?",
"Between these emails, which would you engage with? A: '[Email A summary]' B: '[Email B summary]'. Why?",
"Does this email feel valuable or like noise? What makes you say that?",
"Would you click this CTA: '[CTA copy]'? What would make you more likely to click?"
]
)
```
Update emails based on feedback before finalizing.
### Step 6: Deliver Email Campaign Set
**1. Campaign Overview:**
- Audience insights summary
- Key findings (what resonates, what to avoid)
- Recommended approach
**2. Email Variations (5-8 complete emails):**
- Subject line + preview text
- Full body copy + CTA
- Insight driving each email
- Best use case
**3. Subject Line Library:** 10-15 tested subject lines ranked by predicted performance
**4. A/B Testing Plan:**
- Which emails to test first
- What elements to test (subject, opening, CTA, length)
- Success metrics to track
**5. Do's and Don'ts (based on research):**
- ✅ What resonates with this audience
- ❌ What triggers unsubscribes
## Email Best Practices
| Element | Guideline |
|---------|-----------|
| **Subject line** | 6-10 words; clear benefit or curiosity without clickbait |
| **Preview text** | Complement subject line; don't repeat; add context |
| **Opening hook** | First 2 sentences determine if they keep reading |
| **Email body** | Short paragraphs (2-3 sentences); scannable; whitespace |
| **CTA** | One primary CTA; clear action; repeat if email is long |
| **Length** | Match audience preference (research will reveal) |
| **Frequency** | Align with tolerance from research |
## Tips for Best Results
- **Subject lines make or break opens** — Test multiple angles; what works for one audience won't work for another
- **The first sentence is everything** — If the opening doesn't hook them, they're gone
- **Use their language** — Pull exact phrases from Digital Twin responses
- **Clarity over cleverness** — If they need to re-read to understand, simplify
- **One clear goal per email** — One CTA, one purpose
- **Respect their inbox** — If research shows frequency concerns, acknowledge it
- **Test drastically different approaches** — Not just subject variations; test fundamentally different structures and tones
## Common Pitfalls to Avoid
- **Clickbait subject lines** — Drives unsubscribes even if it increases opens
- **Burying the point** — If they prefer direct communication, get to it quickly
- **Too many CTAs** — Multiple asks dilute focus and reduce clicks
- **Generic messaging** — "We're excited to announce..." isn't grounded in insight
- **Ignoring mobile** — Most emails are opened on mobile; keep it scannable
- **Over-sending** — Sending more when research shows low tolerance backfires
- **No clear value** — If it doesn't answer "what's in it for me?", it's noise
## Email Sequence Considerations
For multi-email sequences (welcome series, onboarding, launch):
- **Map the journey** — What do they need to know first, second, third?
- **Vary the approach** — Don't repeat the same structure in every email
- **Build on previous emails** — Reference what they've learned or done
- **Respect timing** — Space emails based on frequency tolerance
- **Clear exit** — Make it easy to unsubscribe; forcing people to stay backfiresIdea Validation
Validate a business idea, product concept, or value proposition with real audience feedback before investing time or money. Tests whether the problem is real, how painful it is, and whether your solution would genuinely change behaviour — delivering a clear Go / Pivot / Kill verdict with evidence.
Use when: You have a startup idea, product concept, or new business proposition and want honest signal on whether it has legs. Great for founders, product teams, or anyone who wants to de-risk before building.
View full skill
markdown
---
name: idea-validation
description: "Use this skill to validate a business idea, product concept, or value proposition with real audience feedback before investing time or money. Triggers include: requests to validate a startup idea, test a product concept, check if an idea has legs, assess market demand, validate a value proposition, or get honest feedback on a new business concept. Uses OriginalVoices Digital Twins (ask_twins) to understand whether the problem is real, how painful it is, how people solve it today, and whether the proposed idea would genuinely change their behaviour — delivering a clear Go / Pivot / Kill verdict with evidence."
---
# Idea Validation
## Overview
Validate a business idea, product concept, or value proposition with real audience feedback before you invest time or money building it. This workflow uses OriginalVoices Digital Twins to test whether the problem is real, how people deal with it today, and whether your proposed solution would genuinely change their behaviour — so you get a clear signal before you commit.
## Workflow Steps
### Step 1: Gather the Idea
Collect from the user:
- **The idea**: What is the product, service, or concept? (A short description is fine — even a one-liner)
- **The problem it solves**: What pain point or need does it address?
- **Target audience**: Who is this for? Be as specific as possible — demographics, interests, lifestyle, situation
- **How it works** (optional): Any details on the proposed solution, pricing model, or delivery method
- **What exists today** (optional): Known competitors or alternatives the audience might already use
### Step 2: Validate with Digital Twins
Test the idea with the target audience using 10-12 questions that progress from problem validation through to purchase intent. This sequence is deliberate — it establishes whether the problem is real before introducing the solution.
```
ask_twins(
audience: "[detailed target audience description]",
questions: [
"When it comes to [problem area], what's the biggest challenge or frustration you deal with? How often does it come up?",
"How do you currently handle [problem]? Walk me through what you do today.",
"What's the worst part about your current approach? What do you wish was different?",
"Have you ever looked for a better solution to [problem]? What did you find, and why did you stick with (or abandon) it?",
"On a scale of 1-10, how painful is this problem in your life right now? What makes it that level?",
"I'd like to get your reaction to an idea: [describe the idea clearly and concisely, in plain language]. What's your immediate gut reaction?",
"Does this idea solve a real problem for you, or is it more of a 'nice to have'? Be honest.",
"What questions or concerns come to mind when you hear about this idea? What would hold you back from trying it?",
"If this existed today, what would it need to do to get you to switch from your current approach?",
"What would you expect to pay for something like this? What would feel like a fair price?",
"Would you recommend this to someone you know? Who would you tell about it and what would you say?",
"If you could change one thing about this idea to make it perfect for you, what would it be?"
]
)
```
**Important:** Present the idea in plain language, the way you'd explain it to a friend. Avoid marketing speak or inflated claims — you want honest reactions, not polite nods.
### Step 3: Assess the Signals
Analyse responses across five validation dimensions:
**Problem Validation**
- Is the problem real and frequent, or theoretical?
- How painful is it (mild annoyance vs. genuine frustration)?
- Are people actively looking for solutions?
**Solution Fit**
- Did the idea spark genuine interest or polite indifference?
- Does it solve the problem as the audience experiences it?
- Did anyone say "I need this" or "where can I get this"?
**Switching Willingness**
- Would they actually change their current behaviour?
- What barriers to adoption came up?
- How entrenched are current habits or solutions?
**Value Perception**
- Do price expectations align with a viable business model?
- Is it seen as a "must-have" or "nice-to-have"?
- Would they pay for it, or only use it if free?
**Word of Mouth Potential**
- Would they tell others about it?
- Can they articulate the value clearly?
- Who would they recommend it to?
### Step 4: Deliver the Validation Verdict
**1. Verdict: Go / Pivot / Kill**
| Verdict | When to use |
|---------|------------|
| **Go** | Problem is real and painful, solution sparked genuine excitement, audience would pay and switch |
| **Pivot** | Problem is real but the proposed solution missed the mark — the audience pointed to a better direction |
| **Kill** | Problem isn't painful enough, audience is indifferent to the solution, or insurmountable barriers exist |
**2. Evidence Summary**
| Dimension | Signal | Strength (Strong / Mixed / Weak) |
|-----------|--------|----------------------------------|
| Problem exists | [What the audience said] | [Rating] |
| Problem is painful | [Pain level and frequency] | [Rating] |
| Solution resonates | [Gut reactions] | [Rating] |
| Would switch | [Switching willingness] | [Rating] |
| Would pay | [Price expectations] | [Rating] |
| Would recommend | [Word of mouth signals] | [Rating] |
**3. Strongest Signals**
- What resonated most (with supporting quotes)
- The clearest signs of demand or excitement
**4. Biggest Risks**
- What concerned the audience most
- Barriers to adoption they raised
- Gaps between the idea and what they actually need
**5. Audience-Suggested Improvements**
- Changes the audience said would make the idea better
- Features or aspects they specifically asked for
- What would turn it from "interesting" to "essential"
**6. Recommended Next Steps**
For **Go**:
- Priority features to build first (based on what the audience valued most)
- Messaging angles that resonated
- Audience segments that showed strongest interest
For **Pivot**:
- What direction the audience pointed toward
- Which elements to keep vs. rethink
- Suggested reframing of the idea
For **Kill**:
- Why the idea doesn't have sufficient demand
- Whether a different audience might respond better
- Salvageable elements worth exploring elsewhere
## Tips for Best Results
- **Test the problem before the solution**: The question sequence is deliberate — if the problem isn't real, the solution doesn't matter
- **Present the idea simply**: If you can't explain it in 2-3 sentences, the audience won't get it either. That's a signal in itself
- **Listen for energy, not politeness**: "That's interesting" is lukewarm. "Where can I get this?" is validation
- **Pain level matters**: A real problem that's mildly annoying won't drive behaviour change. Look for genuine frustration
- **Switching cost is the hidden killer**: Even great ideas fail if the cost of changing behaviour is too high
- **Price expectations reveal truth**: If the audience expects it to be free, they don't value it enough to sustain a business
## Validation Signal Guide
### Strong Positive Signals
- Audience describes the problem with emotion and specific examples
- Gut reaction to the idea is enthusiastic, not just polite
- They ask "when can I get this?" or "does this exist?"
- They immediately think of someone they'd tell about it
- Price expectations align with a viable model
- They describe current workarounds that are painful or expensive
### Warning Signs (Consider Pivoting)
- Problem is real but the solution doesn't quite fit how they experience it
- Interest is conditional — "I'd use it if..." with significant conditions
- They like the idea but wouldn't pay for it
- They can't articulate who they'd recommend it to
- Current solutions are "good enough" even if imperfect
### Red Flags (Consider Killing)
- Audience struggles to relate to the problem
- Gut reaction is indifferent or confused
- "That's interesting" without follow-up enthusiasm
- They wouldn't switch from their current approach
- Price expectation is zero or far below viability
- No one they'd recommend it to
- The problem exists but isn't painful enough to drive action
## Common Pitfalls to Avoid
- **Confirmation bias**: Don't cherry-pick positive responses and ignore concerns. The warnings are the most valuable part
- **Solution-first thinking**: If you skip problem validation and jump straight to "do you like my idea?", you'll get polite answers, not honest ones
- **Ignoring switching costs**: People may love the idea in theory but never change their actual behaviour
- **Confusing interest with intent**: "That sounds cool" is not the same as "I would pay for that"
- **Testing with the wrong audience**: A great idea tested with the wrong people will look like a bad idea. Be specific about who you're testing with
- **Over-describing the idea**: The more you explain and sell, the less honest the reaction. Keep it simple and let the audience respond naturallyFeature Concept Testing
Validate feature concepts with real user insight before committing engineering resources. Tests whether a feature solves a real problem, how users would actually use it, and whether they'd pay for it.
Use when: You want to validate feature ideas, test product concepts, understand if users would use a feature, gauge interest in new functionality, or reduce risk of building unwanted features.
View full skill
markdown
---
name: feature-concept-testing
description: "Use this skill to test and validate new feature concepts before building them. Triggers include: requests to validate feature ideas, test product concepts, understand if users would use a feature, gauge interest in new functionality, or reduce risk of building unwanted features. Uses OriginalVoices Digital Twins (ask_twins) to understand whether a feature solves a real problem, how users would actually use it, what concerns they have, and whether they'd pay for it — preventing wasted engineering effort on features nobody wants."
---
# Feature Concept Testing Agent
## Overview
Validate feature concepts with real user insight before committing engineering resources. This workflow tests whether a feature idea solves a real problem, how users would actually use it, and what makes it valuable — so you build features people want instead of features that seem good in theory.
## Workflow Steps
### Step 1: Define the Feature Concept
Gather from the user:
- **Target audience**: Who is this feature for? (e.g. "Power users of project management software")
- **Feature description**: What does it do? (functionality, not technical implementation)
- **Problem it solves**: What user problem or need does this address?
- **Context**: Where does it fit? When would users encounter it?
### Step 2: Validate Problem & Feature Concept
One comprehensive research call covering problem validation, feature appeal, usage scenarios, value perception, and concerns.
```
ask_twins(
audience: "[detailed target audience]",
questions: [
"What's your biggest challenge when it comes to [problem area this feature addresses]? How do you handle it today?",
"How often do you encounter [problem]? How painful is it when it happens?",
"Imagine [product] added a feature that lets you [feature description]. How useful would that be for you?",
"Would [feature] solve a real problem for you? What problem would it solve?",
"When would you use [feature]? Walk me through a specific scenario where you'd use it.",
"How often would you realistically use [feature]? Daily, weekly, monthly, or rarely?",
"How would [feature] be different from how you currently solve [problem]? Would it be meaningfully better?",
"Would using [feature] feel natural in your workflow, or would it feel like extra steps?",
"What concerns or hesitations would you have about [feature]? What could go wrong?",
"Is [feature] something you need, something nice to have, or something you probably wouldn't use?",
"If a competitor offered [feature] and [current product] didn't, would you switch?",
"Would you be willing to pay extra for [feature]? Why or why not?"
]
)
```
**Optional: Test Alternative Approaches**
```
ask_twins(
audience: "[same audience]",
questions: [
"Instead of [feature concept], what if [product] did [alternative approach]? Would that be better?",
"Would you prefer: A) [Feature as described], or B) [Simpler version]? Why?",
"If you could design the perfect solution to [problem], what would it look like?"
]
)
```
### Step 3: Analyse Feature Validation Insights
Review responses and assess:
**Problem-Solution Fit:**
- Is the problem real and painful?
- Does the feature actually solve it?
- Is it meaningfully better than alternatives?
**Usage Likelihood:**
- Would users actually use it?
- How often? Does it fit their workflow?
**Value Perception:**
- Must-have vs. nice-to-have?
- Would they pay for it?
- Would they switch products for it?
**Concerns & Risks:**
- What objections exist?
- What would prevent adoption?
### Step 4: Deliver Feature Validation Report
**1. Executive Recommendation:**
- Build / Iterate / Don't Build
- Confidence level (high, medium, low)
- Key rationale (2-3 sentences)
**2. Problem Validation:**
- Is the problem real? (supporting quotes)
- How painful and frequent?
- Current workarounds and costs
**3. Feature Assessment:**
- Does it solve the problem? (user interpretation)
- Would users use it? (frequency, scenarios)
- Differentiation vs. existing solutions
**4. Value Analysis:**
- What value does it create?
- Must-have vs. nice-to-have sentiment
- Willingness to pay (if tested)
**5. Concerns & Objections:**
- Top concerns (with quotes)
- Adoption risks
- Dealbreakers vs. acceptable limitations
**6. Recommendations:**
If **Build**:
- Key requirements to meet user needs
- Potential MVP scope
- Critical success factors
If **Iterate**:
- What to change about the concept
- Alternative approaches to test
If **Don't Build**:
- Why it failed validation
- What to focus on instead
**7. Next Steps:**
- If validated: Prototyping, design, MVP scope
- If needs iteration: What to test next
- If not validated: Where to focus effort instead
## Feature Validation Framework
| Criterion | Strong Signal | Weak Signal |
|-----------|---------------|-------------|
| **Problem intensity** | "This is incredibly frustrating, happens constantly" | "Minor annoyance occasionally" |
| **Solution fit** | "This would solve my problem perfectly" | "Not sure this would help" |
| **Usage frequency** | "I'd use this daily/multiple times per week" | "Might use it once in a while" |
| **Workflow fit** | "This fits naturally into how I work" | "I'd have to remember to use it" |
| **Value perception** | "Game-changer" / "I'd pay for this" | "That's nice I guess" |
| **Adoption likelihood** | "I'd start using this immediately" | "I'd stick with current approach" |
**Strong validation**: Multiple strong signals → Build with confidence
**Moderate validation**: Mixed signals → Iterate, test again
**Weak validation**: Mostly weak signals → Don't build
## Tips for Best Results
- **Test the problem first** — If the problem isn't real, the feature doesn't matter
- **Watch for polite enthusiasm** — "That sounds cool" ≠ "I would use this" ≠ "I need this"
- **Look for specificity** — Vague positivity means nothing; specific use cases indicate real intent
- **Frequency matters** — Features used daily can be simple; features used monthly must be instantly intuitive
- **Follow the energy** — Strong emotional reactions are more valuable than lukewarm interest
- **Test the simplest version** — Test the core concept first, not a feature with 10 capabilities
## Common Pitfalls to Avoid
- **Confusing interest with intent** — "That's interesting" doesn't mean they'll use it
- **Describing features, not outcomes** — Talk about what users can achieve, not technical functionality
- **Ignoring current behavior** — If they don't solve this problem today, a feature won't change that
- **Building for edge cases** — One vocal user's need doesn't represent the broader audience
- **Confirmation bias** — Ask questions that challenge your idea, not just validate it
## Red Flags (Don't Build)
- Users struggle to describe when/how they'd use the feature
- The problem isn't painful or frequent
- Users say "that's cool" but can't articulate why it's valuable
- Current workarounds are simple and acceptable
- Users say "I guess I might use it" instead of "I need this"
- Concerns and objections outweigh enthusiasm
## Green Lights (Build)
- Users describe specific, frequent scenarios where they'd use it
- The problem is painful and current workarounds are costly
- Users say "this would change how I work"
- Multiple users independently describe similar use cases
- Users ask when it will be available
- Feature fits naturally into existing workflows
- Users would pay for it or switch products for itBrand Messaging Validation
Validate your brand messaging with real audience insight before locking it in. Understand how target audiences interpret brand statements, what creates emotional resonance, what causes confusion, and what differentiates you meaningfully.
Use when: You want to test brand positioning, validate taglines or slogans, understand brand perception, refine mission statements, test brand voice, or differentiate from competitors.
View full skill
markdown
---
name: brand-messaging-validation
description: "Use this skill to validate and refine brand messaging, positioning, and taglines using real audience insight. Triggers include: requests to test brand positioning, validate taglines or slogans, understand brand perception, refine mission statements, test brand voice, or differentiate from competitors. Uses OriginalVoices Digital Twins (ask_twins) to understand how target audiences interpret brand messaging, what resonates emotionally, what creates confusion, and what drives brand affinity — ensuring brand statements connect with real people, not just internal stakeholders."
---
# Brand Messaging Validation Agent
## Overview
Validate your brand messaging with real audience insight before locking it in. This workflow helps you understand how your target audience interprets your brand statements, what creates emotional resonance, what causes confusion, and what differentiates you meaningfully — so you can build brand messaging that actually connects instead of sounding like every other company.
## Workflow Steps
### Step 1: Define What You're Testing
Gather from the user:
- **Target audience**: Who is this brand for? (e.g. "Health-conscious millennials", "Small business owners in creative industries")
- **Current or proposed brand messaging**:
- Brand positioning statement
- Tagline/slogan (if applicable)
- Mission/vision statements (if testing)
- Key brand values or pillars
- Tone of voice examples (if testing)
- **Category context**: What space does the brand operate in? Who are main competitors?
### Step 2: Comprehensive Brand Messaging Validation
One comprehensive research call covering category values, positioning interpretation, tagline resonance, brand values authenticity, differentiation, and emotional connection.
```
ask_twins(
audience: "[detailed target audience]",
questions: [
"When you think about [product category / industry], what matters most to you? What do you look for in brands you trust?",
"What frustrates you about most brands in the [category] space? What do they get wrong?",
"Here's how a brand describes itself: '[positioning statement]'. What's your immediate reaction? What do you think this brand is about?",
"Based on that description, is it clear what this brand does and who it's for? What's confusing or unclear, if anything?",
"Does that description make this brand sound different from other [category] brands? What makes it stand out, or does it blend in?",
"[If testing tagline] When you read this tagline: '[tagline]', what does it make you think or feel? Does it feel memorable or forgettable?",
"This brand says it stands for: [list 3-4 brand values]. Do these values matter to you? Which ones resonate and why?",
"Do those values feel authentic for a [category] brand, or do they feel like generic corporate speak that every brand claims?",
"[If testing tone] Here are two ways this brand might communicate: A: '[Example A]' B: '[Example B]'. Which feels more right for what they do?",
"Compared to [competitor name] or other [category] brands you know, does this brand feel genuinely different? What makes you say that?",
"When you read this brand's messaging, how does it make you feel? Does it feel like it 'gets you' and understands people like you?",
"Based on how this brand presents itself, would you feel proud to use or recommend it? What would hold you back?",
"If you had to describe this brand to a friend in one sentence, what would you say? What would you remember about it?",
"[If testing alternatives] Between these positioning options: A: '[Option A]' B: '[Option B]', which appeals to you more and why?"
]
)
```
**Note:** Adjust questions based on what's being tested. If not testing a tagline, remove tagline questions. If not testing tone, remove tone questions. If testing alternatives, include comparison questions.
### Step 3: Analyse Brand Messaging Insights
Review responses and assess:
**Clarity:**
- Do people understand what the brand does and who it's for?
- What creates confusion or ambiguity?
**Resonance:**
- What messaging landed emotionally?
- What values or statements people connected with?
- What felt hollow or generic?
**Differentiation:**
- Does the brand feel distinct from competitors?
- What makes it stand out (or fail to stand out)?
- Is differentiation meaningful or superficial?
**Authenticity:**
- Does the messaging feel genuine or corporate?
- Do stated values feel believable?
- Does tone match expectations for the category?
**Memorability:**
- What stuck with people?
- What would they remember or repeat?
### Step 4: Deliver Brand Messaging Report
**1. Executive Summary:**
- Overall verdict on current messaging
- Top 3 strengths
- Top 3 areas for improvement
- Recommended direction (Keep / Refine / Rethink)
**2. Positioning Assessment:**
- How audience interprets the positioning
- What lands clearly vs. what's confusing
- Emotional response and brand personality perception
- Differentiation from competitors
- Supporting quotes
**3. Tagline/Slogan Analysis** (if tested):
- Resonance and memorability
- What it communicates (intended vs. actual)
- Comparison with alternatives (if tested)
- Refinement suggestions
**4. Brand Values Validation:**
- Which values resonate (ranked by importance)
- Which feel authentic vs. generic
- Values that drive affinity vs. values that don't matter
- Supporting quotes
**5. Tone & Voice** (if tested):
- Whether tone lands as intended
- Audience preference between options
- Category fit and authenticity
**6. Differentiation Analysis:**
- How brand is perceived vs. competitors
- What makes it stand out (or doesn't)
- Meaningful differentiation vs. superficial claims
**7. Emotional Connection:**
- Primary feelings the messaging evokes
- Whether brand feels relatable and "gets them"
- Factors that build (or block) affinity
**8. Audience Insights:**
- What this audience cares about in the category
- What builds trust and loyalty
- What turns them off
- Key emotional drivers
**9. Recommendations:**
- Refined positioning statement (if needed)
- Alternative tagline options (if current one didn't land)
- Brand value prioritization (which to lead with)
- Tone adjustments
- Messaging do's and don'ts (✅ what works / ❌ what doesn't)
**10. Next Steps:**
- If validated: Move forward with confidence
- If needs refinement: Specific changes to make and retest
- If messaging missed: Strategic pivot recommendations
## Brand Messaging Framework
Strong brand messaging answers these questions clearly:
| Question | What It Tests |
|----------|--------------|
| **Who are we?** | Category/space clarity |
| **Who are we for?** | Target audience clarity |
| **What do we do?** | Core offering clarity |
| **Why does it matter?** | Value/outcome clarity |
| **What makes us different?** | Differentiation clarity |
| **Why should you trust us?** | Credibility signals |
| **What should you feel?** | Emotional tone |
If your messaging doesn't clearly answer these, use the research to refine until it does.
## Tips for Best Results
- **Be willing to hear "no"**: If messaging doesn't resonate, it's better to know now than after a launch
- **Specificity beats aspiration**: "We help X do Y so they can Z" beats "We're transforming the future of [industry]"
- **Watch for comprehension gaps**: If people don't understand what you do, nothing else matters
- **Generic values don't differentiate**: "Innovation, integrity, excellence" — every brand claims these
- **Differentiation must be meaningful**: "We care more" isn't differentiation; "We're the only [category] for [specific need]" is
- **Emotional connection drives loyalty**: People may buy on features but stay loyal to brands they feel connected to
- **Test competitors too**: Understanding how audience perceives competitors reveals positioning opportunities
## Common Pitfalls to Avoid
- **Internal language**: Jargon that means nothing to customers (e.g., "synergy", "ecosystem", "best-in-class")
- **Mission statement syndrome**: Long, jargon-filled statements that say everything and nothing
- **Category clichés**: Every [category] brand claims to be "innovative", "customer-first", "transforming the industry"
- **Vague value propositions**: "Better solutions for modern businesses" — better how? Modern in what way?
- **Fake differentiation**: Claiming to be different without specifying what makes you different
- **Value-free values**: Stating values without tying them to actions
- **Testing in a vacuum**: Asking "Do you like this?" instead of "Would this influence your decision?"
## Red Flags (Rethink Messaging)
- Audience can't articulate what the brand does
- Positioning feels generic and interchangeable with competitors
- Values feel like empty corporate speak
- Tagline is forgettable or confusing
- Emotional response is neutral or negative
- People struggle to describe the brand in their own words
## Green Lights (Strong Messaging)
- Audience clearly understands what the brand does and who it's for
- Messaging evokes specific, positive emotions
- Differentiation is clear and meaningful
- Values feel authentic and tied to actions
- Tagline is memorable and captures essence
- People can easily explain the brand to others
- Brand feels relatable and "gets them"Content Generation Optimization
Generate SEO and AEO-optimized content informed by real audience insight. Research what your target audience wants to know, what tone resonates, and what makes content engaging, then write blog posts, articles, or guides that rank well and actually get read.
Use when: You need to write blog posts, create SEO content, generate articles, write guides, or create audience-aligned content.
View full skill
markdown
---
name: content-generation-optimization
description: "Use this skill to generate SEO and AEO-optimized content (blog posts, articles, guides) informed by real audience insight. Triggers include: requests to write blog posts, create SEO content, generate articles, write guides, or create audience-aligned content. Uses OriginalVoices Digital Twins (ask_twins) to understand what the audience wants to know, what tone resonates, what questions they have, and what makes content engaging — then uses those insights to write content that ranks well, gets read, and drives results."
---
# Content Generation Optimization Agent
## Overview
Generate SEO and AEO-optimized content informed by real audience insight. This workflow researches your target audience to understand what they want to know, what tone resonates, and what makes content engaging — then uses those insights to write blog posts, articles, or guides that rank well in search engines, appear in AI answer engines, and actually get read.
## Workflow Steps
### Step 1: Define Content to Generate
Gather from the user:
- **Topic/headline**: What is this content about? (e.g. "How to choose the right CRM for small businesses")
- **Target audience**: Who is this for? (e.g. "Small business owners with 5-20 employees")
- **Content goal**: What should this achieve? (SEO rankings for specific keywords, lead generation, education, thought leadership, AEO visibility)
- **Desired length**: Word count or depth (e.g. "1,500-2,000 words", "comprehensive guide", "quick how-to")
- **Content type**: Blog post, guide, article, how-to, listicle, case study, etc.
- **SEO keywords** (if applicable): Primary and secondary keywords to target
- **Specific requirements**: Tone, structure, sections to include, CTAs, etc.
### Step 2: Research Audience to Inform Content
One comprehensive research call to understand what will make this content valuable, engaging, and optimized for the audience.
```
ask_twins(
audience: "[detailed target audience]",
questions: [
"When you're looking for information about [topic], what are you trying to learn or accomplish? What's your main goal?",
"What specific questions do you have about [topic] that you want answered?",
"What frustrates you about most articles or content on [topic]? What do they get wrong, miss, or over-explain?",
"When reading about [topic], do you prefer: A) Casual, conversational tone, or B) Professional, formal tone? Why?",
"How deep should content on [topic] go? Would you read a comprehensive 2,000-word guide, or do you prefer short, actionable advice?",
"What makes you trust that content about [topic] is credible and worth your time? (data, examples, author credentials, case studies, etc.)",
"What would make you actually read an article about [topic] all the way through vs. just skimming?",
"If you were searching for '[topic]' on Google, what would you type? What would you expect to find?",
"What examples, case studies, or real-world scenarios would make content about [topic] more useful to you?",
"What would make you bookmark or share an article about [topic] with someone else?",
"Are there common mistakes or misconceptions about [topic] you see repeated that you wish someone would address?",
"What's missing from most content on [topic]? What do you wish someone would explain better?"
]
)
```
### Step 3: Analyse Insights & Plan Content Structure
Review audience responses and extract:
**Key Questions to Answer:**
- What specific questions the audience has
- What they're trying to accomplish
- What's missing from existing content
**Tone & Style:**
- Casual vs. professional
- Depth: comprehensive vs. concise
- Structure: how-to, storytelling, data-driven, etc.
**Credibility Signals:**
- What builds trust (data, examples, credentials, case studies)
- What examples or scenarios resonate
**Engagement Hooks:**
- What makes them read vs. skim
- What makes them share or bookmark
- Pain points and frustrations to address
**SEO/AEO Optimization:**
- How they search for this topic (keywords, questions)
- What they expect to find
- How to structure for featured snippets and AI answers
### Step 4: Write the Complete Blog Post/Article
**IMPORTANT**: Using the insights from Step 3, now write the complete, publish-ready blog post or article. Output the full written content, not just an outline or summary.
**Structure your written content as follows:**
**Headline:**
- Compelling, click-worthy headline that includes the primary keyword
- Based on what makes the audience interested (from research)
**Introduction (2-3 paragraphs):**
- Open with a hook that addresses their pain point or goal (from research)
- Establish what they'll learn and why it matters to them
- Set expectations for depth and value
- Make them want to keep reading
**Body (Main Content):**
- Use H2 and H3 headers that answer their specific questions (from research)
- Answer the key questions they have in order of importance
- Address frustrations with existing content they mentioned
- Write in their preferred tone (casual/professional based on research)
- Include credibility signals they care about (data, examples, case studies)
- Correct common misconceptions they mentioned
- Use short paragraphs, bullets, and formatting for scannability
- Naturally incorporate SEO keywords
- Structure answers clearly for featured snippets and AI answer engines
**Examples/Evidence (throughout body):**
- Include real-world scenarios or case studies that resonate with them
- Add data or statistics that build credibility (if they value data)
- Use practical examples they can relate to their situation
**Conclusion (2-3 paragraphs):**
- Summarize the key takeaways
- Provide clear, actionable next steps
- Include CTA aligned with content goal (newsletter signup, product trial, related content, etc.)
**Write the complete article now** - from headline through conclusion. Make it ready to publish.
### Step 5: Deliver the Content
**PRIMARY DELIVERABLE - The Complete Written Blog Post/Article:**
Output the full, publish-ready blog post or article you wrote in Step 4, including:
- Headline
- Complete introduction
- Full body with all sections and headers
- Examples and evidence throughout
- Complete conclusion with CTA
- Ready to copy and publish
**THEN provide supporting materials:**
**1. Content Brief:**
- **Target audience**: Who this is for
- **Primary goal**: SEO, lead gen, education, etc.
- **Word count**: Actual length
- **Tone**: Casual/professional based on research
- **Primary keyword**: Main SEO target
- **Secondary keywords**: Supporting terms
**2. Key Insights Used:**
- Top 3-5 audience insights that shaped the content
- Questions answered (from research)
- Pain points addressed
- Credibility signals included
- Engagement hooks used
**3. SEO/AEO Optimization Summary:**
- **Target keywords**: Primary and secondary
- **Search intent**: What audience is looking for
- **Featured snippet opportunity**: How content is structured to capture it
- **AEO optimization**: How it's structured for AI answer engines
- **Internal linking opportunities**: Related content to link to
- **Meta description suggestion**: Based on audience search behavior
**4. Performance Recommendations:**
- How to measure success (traffic, rankings, engagement, conversions)
- Distribution channels (where to promote based on audience research)
- Potential updates or follow-ups based on content gaps identified
## Content Generation Framework
| Content Element | Audience Insight Source | Optimization |
|----------------|------------------------|--------------|
| **Headline** | What makes them click | Include primary keyword, promise value |
| **Introduction** | Pain points and goals | Hook with their frustration/goal, set expectations |
| **Structure** | Questions they have | H2/H3 headers that answer specific questions |
| **Tone** | Casual vs. professional preference | Match their preferred style |
| **Examples** | What makes it relatable | Use scenarios they mentioned or similar |
| **Credibility** | What builds trust | Include data/examples/credentials they value |
| **Depth** | How comprehensive they want | Match preferred length and detail level |
| **SEO** | How they search | Natural keyword usage, semantic relevance |
| **AEO** | Questions they ask | Clear, direct answers; structured data |
| **CTA** | What makes them take action | Aligned with content goal and their needs |
## Tips for Best Results
- **Write for the audience, optimize for search**: Use insights to inform content, then layer in SEO naturally
- **Answer the real questions**: Don't assume - use the specific questions from research
- **Match their depth preference**: Don't write 3,000 words if they want quick, actionable advice
- **Use their language**: Incorporate words and phrases they used in responses
- **Address frustrations**: Call out what existing content gets wrong and do it better
- **Build credibility their way**: If they value data, include data; if they value stories, include stories
- **Structure for skimming**: Use headers, bullets, short paragraphs - they said what makes them read vs. skim
- **Optimize for featured snippets**: Use clear question-answer format for key questions
- **Make it actionable**: Include practical next steps they can take
## Common Content Generation Pitfalls
- **Writing without research**: Assuming what the audience wants instead of asking them
- **Keyword stuffing**: Optimizing for SEO at the expense of readability and value
- **Wrong tone**: Being too casual when they want professional, or too formal when they want conversational
- **Too shallow or too deep**: Not matching their preferred depth and detail level
- **Missing the real questions**: Answering questions you think they have vs. questions they actually have
- **Generic examples**: Using examples that don't resonate with this specific audience
- **Ignoring frustrations**: Repeating the same mistakes existing content makes
- **No clear structure**: Making them work to find information instead of making it scannable
- **Weak introduction**: Not hooking them with their actual pain points or goals
## Red Flags (Revise Content)
- Content doesn't answer the key questions from research
- Tone doesn't match audience preference
- Missing credibility signals they care about
- Too generic - could apply to any audience
- Doesn't address frustrations they mentioned
- Not structured for how they actually search
- Introduction doesn't hook with their pain points
## Green Lights (Strong Content)
- Directly answers questions from audience research
- Tone matches their preference (casual/professional)
- Includes credibility signals they trust
- Addresses pain points and frustrations they mentioned
- Structured for both readability and SEO/AEO
- Uses examples and scenarios that resonate
- Introduction hooks with their actual goals/frustrations
- Actionable and practical based on their needsProduct Description Optimization
Optimize existing product descriptions for ecommerce using real audience insight. Test descriptions with target buyers to understand what matters, what information they need, and what drives purchase decisions — then refine descriptions to convert better.
Use when: You want to improve product descriptions, optimize ecommerce copy, increase conversion rates, refine product pages, make product descriptions resonate with target audiences, or test product messaging.
View full skill
markdown
---
name: product-description-optimization
description: "Use this skill to optimize existing product descriptions for ecommerce using real audience insight. Triggers include: requests to improve product descriptions, optimize ecommerce copy, increase conversion rates, refine product pages, make product descriptions resonate with target audiences, or test product messaging. Uses OriginalVoices Digital Twins (ask_twins) to understand what matters to buyers, what information they need, what language resonates, and what drives purchase decisions — then optimizes existing descriptions to convert better."
---
# Product Description Optimization Agent
## Overview
Optimize existing product descriptions for ecommerce using real audience insight. This workflow researches your target audience to understand what matters when they're buying, what information they need to make a decision, what language resonates, and what builds trust — then uses those insights to refine and improve your existing product descriptions for better conversion.
## Workflow Steps
### Step 1: Gather Product & Description
Collect from the user:
- **Product name**: What is being sold
- **Product category**: Type of product (e.g. "skincare", "home decor", "tech accessories", "fitness equipment")
- **Target audience**: Who is this product for? (e.g. "Women 25-40 interested in clean beauty", "Remote workers setting up home offices")
- **Current product description**: The existing description to optimize (copy the full text)
- **Product price point** (optional): Budget, mid-range, premium
- **Key product features**: Main features or benefits (if not clear from description)
- **Optimization goal**: What should improve? (conversion rate, clarity, trust, differentiation, SEO, etc.)
### Step 2: Test Existing Description with Audience
One comprehensive research call to get specific feedback on the existing product description and understand how to optimize it.
```
ask_twins(
audience: "[detailed target audience]",
questions: [
"Here's a product description for [product name]: '[paste full current description]'. What's your initial reaction? Does this make you want to buy it?",
"Based on that description, is it clear what this product is and what it does? What's confusing or unclear, if anything?",
"What do you like about this product description? What stands out as good or compelling?",
"What's missing from this description? What information would you need to see before you'd feel confident buying this product?",
"Does this description answer the questions you'd have about [product category] products, or are there things you're still wondering about?",
"What concerns or hesitations would you have about buying this product based on this description? What makes you unsure?",
"Does the tone and style of this description feel right for [product category], or does it feel off? (too casual, too formal, too salesy, etc.)",
"Would you rather this description be: A) Shorter and more to the point, B) Longer with more detail, or C) About right as is?",
"What would make this description more convincing or trustworthy? What's missing that would build your confidence?",
"If you were comparing this product to similar [product category] options, does this description make it stand out, or does it blend in?",
"What would make you click 'Add to Cart' after reading this? What needs to change to make you more likely to buy?",
"Is there anything in this description that turns you off or makes you less interested in buying?"
]
)
```
### Step 3: Analyse Description Feedback
Review audience responses and extract specific insights about the existing description:
**What's Working:**
- What they liked or found compelling
- What stood out as good
- What's clear and effective
**What's Missing:**
- Information they need that isn't there
- Questions that aren't answered
- Details that would build confidence
**What's Unclear:**
- Confusing or ambiguous parts
- What they didn't understand
- Where clarity is needed
**Concerns & Objections:**
- Hesitations they have after reading it
- What makes them unsure about buying
- Red flags or turnoffs in the current description
**Tone & Style Feedback:**
- Whether current tone feels right or off
- If it's too long, too short, or about right
- If it feels too casual, formal, or salesy
**Differentiation:**
- Whether it stands out or blends in with competitors
- What would make it more distinctive
**Optimization Priorities:**
- What needs to change to make them more likely to buy
- What would make them click "Add to Cart"
- What would build trust and credibility
### Step 4: Optimize the Product Description
**IMPORTANT**: Using the insights from Step 3, now optimize the existing product description with light tweaks and additions. Keep what's working, add what's missing, adjust what needs improvement.
**Optimization approach - LIGHT TOUCH:**
**Keep what's working:**
- Preserve elements they liked or found compelling
- Maintain the original structure if it's effective
- Keep tone/style if it resonated
**Add what's missing:**
- Insert key information they said they need (1-2 sentences or bullets)
- Add answers to questions they have
- Include trust signals or details they want (materials, care instructions, sizing, etc.)
**Tweak what's off:**
- Adjust language that felt too technical, salesy, or unclear
- Rephrase confusing parts for clarity
- Soften or strengthen tone if needed
**Address concerns:**
- Add 1-2 lines that proactively handle objections or hesitations
- Include reassurances about quality, durability, or fit if those were concerns
**Optimization guidelines:**
- Make minimal changes to preserve what's working
- Add missing information naturally (don't force it)
- Keep the original format unless feedback suggests changing it
- Focus on filling gaps, not complete rewrites
- Maintain the brand voice while improving clarity
**Output the optimized description now** - with changes clearly integrated into the original structure.
### Step 5: Deliver Optimization Package
**PRIMARY DELIVERABLE - Optimized Product Description:**
Output the complete, optimized product description ready to use, including:
- Product title (if optimization improves it)
- Full optimized description
- Formatted and ready to publish
**THEN provide supporting materials:**
**1. Optimization Summary:**
- **What changed**: Key changes made and why
- **Key insights applied**: Top 3-5 audience insights that shaped the optimization
- **Expected impact**: What should improve (clarity, trust, conversion, etc.)
**2. Before vs. After Comparison:**
- **Original**: [excerpt of key changes from original]
- **Optimized**: [how it was improved]
- **Why it's better**: Based on audience insight
**3. Description Feedback Summary:**
- **What worked**: What they liked about the original
- **What was missing**: Information gaps they identified
- **What was unclear**: Confusing or ambiguous parts
- **Concerns raised**: Hesitations or objections from the description
- **Tone feedback**: Whether style felt right or needed adjustment
- **Purchase drivers**: What would make them click "Add to Cart"
**4. Additional Recommendations:**
- Other elements to optimize (product images, reviews display, guarantees, FAQs)
- A/B test suggestions (if applicable)
- Related products or upsell opportunities based on what matters to audience
## Product Description Optimization Framework
| Element | Audience Insight Source | Optimization Approach |
|---------|------------------------|----------------------|
| **Opening hook** | What drives purchase decision | Lead with most compelling benefit/value |
| **Information hierarchy** | What they need to see to buy | Prioritize essential info first |
| **Tone** | Casual vs. professional preference | Match their preferred style |
| **Features vs. benefits** | What they care about most | Balance based on preference |
| **Trust signals** | What builds credibility | Include certifications, materials, guarantees they value |
| **Length** | Short/bullets vs. storytelling | Match preferred format |
| **Language** | Words that attract or repel | Use resonant language, avoid turnoffs |
| **Objection handling** | Concerns and hesitations | Address red flags proactively |
| **CTA** | What makes them click "Add to Cart" | Create urgency or clear next step |
## Tips for Best Results
- **Light touch wins**: Keep what's working, add what's missing - don't rewrite everything
- **Add, don't replace**: Insert missing information naturally into the existing structure
- **Preserve the voice**: Maintain the brand's tone while improving clarity and completeness
- **Fill specific gaps**: Add the exact information they said was missing (care instructions, sizing, durability)
- **Be specific**: "Machine washable" beats "easy care"; "True to size" beats "great fit"
- **Answer unasked questions**: Include info they said descriptions often miss
- **Tweak, don't transform**: Adjust unclear language rather than rewriting entire sections
- **Test minimal changes**: Sometimes adding one bullet point converts better than rewriting paragraphs
## Common Product Description Pitfalls
- **Feature dumping**: Listing features without explaining why they matter
- **Generic language**: "Premium quality", "best in class" without proof
- **Missing key information**: Not answering questions buyers have
- **Wrong tone**: Too casual for premium products, too formal for lifestyle brands
- **No trust signals**: Missing certifications, materials, guarantees buyers need
- **Ignoring objections**: Not addressing common concerns or hesitations
- **Too long or too short**: Not matching audience preference for description length
- **Overly salesy**: Hype and superlatives that reduce credibility
## Red Flags (Original Description Issues)
- Missing information buyers said they need
- Tone doesn't match audience preference
- Leads with features when audience cares about benefits (or vice versa)
- No trust signals included (materials, certifications, guarantees)
- Doesn't address common objections or concerns
- Uses language that turns off the target audience
- Too vague or generic
## Green Lights (Strong Optimization)
- Leads with what matters most to the audience
- Includes all information they need to buy confidently
- Tone and style match their preferences
- Addresses their objections and concerns proactively
- Includes trust signals they care about
- Answers questions descriptions typically miss
- Feels authentic and credible, not oversold
- Clear next step (CTA) aligned with purchase driversApp Store Description
Create or optimize app store descriptions (Apple App Store and Google Play Store) using real audience insight. Research target users to understand what drives downloads, what information they scan for, what language resonates, and what triggers hesitation — then write new descriptions or optimize existing ones for better conversion.
Use when: You want to write a new app store listing from scratch, optimize an existing app description, improve app store conversion rates, increase downloads, write app subtitles or short descriptions, or test app store messaging with target users.
View full skill
markdown
---
name: app-store-description
description: "Use this skill to create or optimize app store descriptions (Apple App Store, Google Play Store) using real audience insight. Triggers include: requests to write app store listings, optimize app descriptions, improve app store conversion rates, increase app downloads, refine app store pages, write app subtitles or short descriptions, or test app store messaging with target users. Works for both new apps that need a description from scratch and existing apps that need optimization. Uses OriginalVoices Digital Twins (ask_twins) to understand what makes target users download an app, what information they need, what language resonates, and what builds trust — then creates or optimizes app store descriptions grounded in real user perspectives."
---
# App Store Description Agent
## Overview
Create or optimize app store descriptions (Apple App Store and Google Play Store) using real audience insight. This workflow researches your target users to understand what drives them to download apps, what information they scan for, what language resonates, and what triggers hesitation — then uses those insights to write new descriptions or optimize existing ones for better conversion.
## Workflow Steps
### Step 1: Gather App & Listing Details
Collect from the user:
- **App name**: The app's name
- **App category**: Category on the store (e.g. "Productivity", "Health & Fitness", "Finance", "Education")
- **Target audience**: Who is this app for? (e.g. "Freelancers aged 25-40 who struggle with invoicing", "Parents of toddlers looking for educational screen time")
- **App store platform**: Apple App Store, Google Play, or both
- **Current description** (if optimizing): The existing app store description to improve
- **Key features**: Core features or capabilities (if not clear from description)
- **Key differentiator**: What makes this app different from competitors
- **Pricing model**: Free, freemium, paid, subscription
- **Goal**: New description from scratch, or optimize an existing one
**If creating from scratch, also gather:**
- **Problem it solves**: What user problem does this app address?
- **Core value proposition**: The main reason someone should download it
### Step 2: Research App Download Behaviour & Preferences
One comprehensive research call to understand what drives app download decisions and how the target audience evaluates app store listings.
**If optimizing an existing description:**
```
ask_twins(
audience: "[detailed target audience]",
questions: [
"When you're browsing the app store for a [app category] app, what do you look at first? What makes you tap on an app to learn more?",
"Here's the current description for an app called [app name]: '[paste current description]'. What's your initial reaction? Would this make you want to download it?",
"Based on that description, is it clear what this app does and why you'd use it? What's confusing or unclear?",
"What do you like about this description? What stands out as good or compelling?",
"What's missing from this description? What would you need to know before downloading a [app category] app?",
"What concerns or hesitations would you have about downloading this app based on this description?",
"Does the tone of this description feel right for a [app category] app? Does it feel trustworthy?",
"What would make this description more convincing? What would push you to hit the download button?",
"When comparing [app category] apps, what do you look for in the description to decide between options? What makes one stand out over another?",
"What are the biggest frustrations you have with [problem the app solves]? What words would you use to describe that frustration?",
"If you saw this app was [pricing model], would the description justify that? What would need to be different?",
"Is there anything in this description that turns you off or makes you less likely to download?"
]
)
```
**If creating a new description from scratch:**
```
ask_twins(
audience: "[detailed target audience]",
questions: [
"When you're browsing the app store for a [app category] app, what do you look at first? What makes you tap on an app to learn more?",
"What are the biggest frustrations you have with [problem the app solves]? What words would you use to describe that frustration?",
"What would an ideal [app category] app do for you? What would make you think 'I need this'?",
"When reading an app description, what information do you need to see before you'll download? What's essential vs. nice-to-have?",
"What makes you trust an app enough to download it? What signals credibility in the app store?",
"What would make you choose one [app category] app over another? What's the deciding factor?",
"How do you feel about [app category] apps that are [pricing model]? What would the description need to say to justify that?",
"What turns you off when reading app descriptions? What makes you skip an app and keep scrolling?",
"When it comes to [problem the app solves], what matters most to you? Speed, simplicity, features, design, price?",
"What [app category] apps do you currently use? What do you like and dislike about how they describe themselves?",
"If an app said it could [core value proposition], what would your reaction be? Would you believe it? What would make it credible?",
"What words or phrases would grab your attention in an app description for something that helps with [problem]?"
]
)
```
### Step 3: Analyse Audience Insights
Review responses and extract insights specific to app store description optimization:
**Download Drivers:**
- What makes them tap "Get" or "Install"
- What information is essential before downloading
- What language grabs their attention
**Current Description Feedback (if optimizing):**
- What's working and should be kept
- What's missing or unclear
- What turns them off or creates doubt
**App Store Browsing Behaviour:**
- What they scan first in a listing
- How much of the description they actually read
- What makes them compare further vs. move on
**Language & Tone:**
- Words and phrases that resonate
- Tone preferences (professional, casual, energetic, minimal)
- Language that feels trustworthy vs. overhyped
**Concerns & Objections:**
- Hesitations about downloading
- Pricing sensitivity and value perception
- Trust signals they need to see
**Competitive Differentiation:**
- What they look for when comparing apps
- What would make this app stand out
- What competitors do well or poorly in their descriptions
### Step 4: Write or Optimize the App Store Description
Using the insights from Step 3, create the app store listing elements.
**App Store Listing Elements to Deliver:**
**1. Subtitle / Short Description (required)**
- Apple App Store subtitle: up to 30 characters
- Google Play short description: up to 80 characters
- Lead with the strongest hook from research
**2. Full Description**
Structure the description using what the audience said matters most:
**First paragraph (above the fold — this is critical):**
- Open with the problem or outcome that resonated most
- Make it immediately clear what the app does and who it's for
- Use the audience's own language where possible
**Feature/benefit section:**
- Lead with benefits, supported by features
- Prioritize based on what the audience said matters most
- Use short, scannable lines or bullet points
**Social proof / trust section (if applicable):**
- Include trust signals the audience said they need
- Reference credibility markers (awards, press, user count, ratings)
**Closing / CTA:**
- Address the top objection or hesitation
- End with a clear reason to download now
**Platform-specific guidelines:**
| Element | Apple App Store | Google Play |
|---------|----------------|-------------|
| **Subtitle** | 30 characters max | N/A |
| **Short description** | N/A | 80 characters max |
| **Full description** | 4,000 characters max | 4,000 characters max |
| **Formatting** | Plain text only (no markdown, no HTML) | Supports limited HTML and emoji |
| **Keyword strategy** | Keywords field separate — don't stuff description | Keywords in description help ranking |
**If optimizing — apply a LIGHT TOUCH:**
- Keep elements the audience liked
- Add missing information they said they need
- Adjust tone or language based on feedback
- Address concerns they raised
- Reorder sections based on what they scan first
**If creating from scratch:**
- Build entirely around what the audience said drives downloads
- Use their language and frame the problem the way they describe it
- Front-load the most compelling hook
- Include every piece of information they said is essential
### Step 5: Deliver the App Store Description Package
**PRIMARY DELIVERABLE — App Store Description:**
Output the complete, ready-to-publish listing for each platform requested:
- Subtitle or short description
- Full description (within character limits)
- Formatted for the specific platform
**THEN provide supporting materials:**
**1. Optimization Summary:**
- **Key insights applied**: Top 3-5 audience insights that shaped the description
- **What changed** (if optimizing): Key changes made and why
- **Expected impact**: What should improve (clarity, conversion, differentiation)
**2. Before vs. After (if optimizing):**
- **Original**: Key sections from the original
- **Optimized**: How they were improved
- **Why it's better**: Grounded in audience insight
**3. Audience Insight Summary:**
- **Download drivers**: What makes them install
- **Information needs**: What they must see before downloading
- **Language that resonates**: Words and phrases that grabbed attention
- **Turn-offs**: What made them skip or hesitate
- **Trust signals**: What builds credibility
- **Competitive factors**: What makes an app stand out
**4. Keyword Suggestions:**
- Terms and phrases the audience naturally used when describing the problem and solution
- Language patterns to incorporate into metadata and keywords fields
**5. Additional Recommendations:**
- Screenshot and preview suggestions based on what the audience said they look for
- Rating/review strategy aligned with audience trust signals
- A/B test suggestions for description variants
- Localization considerations if audience feedback suggests it
## App Store Description Framework
| Element | Audience Insight Source | Approach |
|---------|------------------------|----------|
| **Subtitle / short description** | What grabs attention first | Lead with strongest hook in their language |
| **Opening line** | Top problem or desired outcome | Start with what resonated most |
| **Feature order** | What they said matters most | Prioritize by audience preference |
| **Benefit framing** | How they describe success | Use outcome language, not feature language |
| **Trust signals** | What builds download confidence | Include what they said they need to see |
| **Tone** | Professional vs. casual preference | Match their expectation for the category |
| **Length** | How much they actually read | Front-load value, keep scannable |
| **CTA / closing** | What hesitations they have | Address top objection, give reason to act |
## Tips for Best Results
- **First three lines are everything**: Most users see only the first 1-3 lines before "Read More" — make them count
- **Use their language**: Mirror the exact words your audience uses to describe the problem and desired outcome
- **Benefits over features**: "Track expenses in 10 seconds" beats "Built-in expense tracker"
- **Be specific**: "Used by 50,000 freelancers" beats "Trusted by thousands"
- **Address the pricing objection**: If it's paid or subscription, justify value in the description
- **Platform matters**: Google Play rewards keyword-rich descriptions for ASO; Apple does not
- **Scannable format**: Short paragraphs, line breaks, and bullet points (where supported)
- **Light touch when optimizing**: Keep what's working, fix what's not — don't rewrite for the sake of it
## Common App Store Description Pitfalls
- **Burying the value**: Most compelling benefit hidden in paragraph three instead of line one
- **Feature dumping**: Lists of features with no explanation of why they matter to the user
- **Generic opening**: "Welcome to [App Name]!" wastes the most valuable real estate
- **Overpromising**: Claims that feel too good to be true reduce trust
- **Ignoring the fold**: Assuming users will tap "Read More" — most won't
- **Wrong tone for category**: A finance app that sounds like a game, or a fitness app that reads like a textbook
- **No differentiation**: Description could apply to any competitor in the category
- **Keyword stuffing**: Cramming keywords at the expense of readability (especially on Google Play)
- **Ignoring pricing context**: Not addressing value for money when charging a subscription
## Red Flags (Description Issues)
- First three lines don't clearly explain what the app does
- No mention of the core problem or user need
- Features listed without benefits
- Tone doesn't match what the audience expects for the category
- Missing trust signals the audience said they need
- Doesn't address top concerns or objections
- Reads like marketing copy rather than a genuine description
- No differentiation from competing apps
## Green Lights (Strong Description)
- Opens with the problem or outcome the audience cares about most
- Clear what the app does within the first three lines
- Uses language the audience naturally uses
- Features framed as benefits with outcomes
- Includes trust signals the audience values
- Addresses pricing and value perception
- Tone matches audience expectations
- Stands out from competitors based on what users said matters
- Scannable and front-loaded for the "above the fold" reality