Appearance
Skills Library
Ready-made skills that connect your AI assistant 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.
To install: Download the .md file, then upload it to your AI assistant (e.g. in Claude: Settings > Skills > 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
- Make each segment specific enough to be meaningful (not just "young people")
- 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 doesFacebook 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 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 for Google Search, Display, or Performance Max campaigns.
Use when: You need Google Search or Display ad campaigns, want to write Responsive Search Ad (RSA) headlines and descriptions, refresh underperforming Google ad copy, or generate audience-informed ad variations for A/B testing.
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 10-15 audience-informed ad variations rooted in what real people actually said — not AI guesswork."
---
# Google Ad Copy Agent
## Overview
Generate Google 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. "Small business owners aged 30-50 in the US looking for accounting software")
- **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
- **Campaign type**: Search, Display, Performance Max? Default to Search if not specified
### 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, 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. managing finances, finding the right software, staying fit]?",
"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?",
"If you were searching on Google for something like this, what would you type? What words would you use?"
]
)
```
**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
- **Search language**: The words and phrases they'd actually type into Google
- **Emotional drivers**: The feelings that motivate action (relief, confidence, frustration, urgency)
### 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.
**Google Search Ad Format:**
- **Headlines**: Up to 30 characters each (provide 10-15 for RSAs)
- **Descriptions**: Up to 90 characters each (provide 4 for RSAs)
- **Display path**: Up to 15 characters each segment
**Spread variations across different angles, drawing from the research:**
- **Pain point ads**: Lead 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: [
"If you searched Google for [search term] and saw these ads, which would you click? A: '[headline + description A]' B: '[headline + description B]' C: '[headline + description C]'. Tell me why.",
"Reading this ad: '[headline + description]' — does this speak to what you actually care about? What would you change?"
]
)
```
### Step 6: Deliver Final Ad Set
Present the full set of ad variations with:
- Each ad in full (headlines, descriptions, display path)
- The audience insight driving each ad clearly labelled
- Ads grouped by angle (pain point, benefit, trust, experience, objection)
- Character counts verified for Google Ads limits
- Validation results (if done)
- Top 3-5 recommended ads to test first
- A/B testing suggestions (which ads to test against each other)
## Google Ads Character Limits
| Element | Max Characters |
|---------|---------------|
| Headline | 30 |
| Description | 90 |
| Display path (each) | 15 |
| RSA Headlines | Up to 15 (min 3) |
| RSA Descriptions | Up to 4 (min 2) |
## 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
- **Use audience language**: If Twins say "I just want something that actually works", put that in the ad — not "Experience seamless performance"
- **One insight per ad**: Each ad should be built on one clear audience insight, not five crammed together
- **Search language is gold**: The "what would you type into Google" question often surfaces phrasing that aligns perfectly with high-intent search queries
- **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 research
- **Respect character limits**: Google is strict — verify every headline is ≤30 chars and every description is ≤90 charsPre-Test & Validate Creative
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: pre-test-and-validate-creative
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."
---
# Pre-Test & Validate Creative
## 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 ranking