ICP research skill
Generate ideal customer profiles for B2B SaaS clients through systematic research and structured output.
Report structure
The final ICP report follows this numbered section order:
| Section |
Purpose |
| Header |
Research date, website, category, confidence score (1-5) |
| 1. Executive summary |
High-level synthesis of findings and strategic recommendations |
| 2. TAM analysis |
Market sizing with targeting strategy per layer (TAM/SAM/SOM/ICP) |
| 3. Firmographics analysis |
Geographic, industry, company segment patterns, and technographics |
| 4. Roles and personas |
Core use case, Champion deep-dive, Economic Buyer deep-dive, buying journey |
| 5. Negative ICP |
Who is NOT a fit, disqualification criteria, and red flags |
| 6. Customer proof points |
Named customers, outcomes, and evidence with URLs |
| 7. Voice of customer synthesis |
Language patterns, pain points, and outcome terminology |
| 8. ICP segment definitions |
Scoring matrix, in-market signals, segment deep-dives |
| 9. Intent signals and buying triggers |
Observable signals indicating purchase readiness |
| 10. Recommendations |
Prioritization and messaging by segment |
| 11. Data gaps |
Missing information and follow-up suggestions |
| 12. Source appendix |
All sources with access dates, URLs, and confidence levels |
Confidence score calculation: Count High/Medium/Low data points. Score 5 if >70% High, Score 4 if >50% High, Score 3 if mixed, Score 2 if >50% Low, Score 1 if >70% Low.
Sorting rules
Apply consistently across all tables:
| Dimension |
Sort order |
| Decision role |
Champion → Economic Buyer → User → Influencer |
| Company size |
Enterprise → Mid-market → SMB → Startup |
| Frequency |
Very high → High → Medium → Low |
| Confidence |
High → Medium → Low |
| Customer concentration |
High → Medium → Low |
| Priority |
1 → 2 → 3 → 4 |
| Industry presence |
Strong → Moderate → Emerging |
Workflow
The research runs in 3 phases. Read the premium reference for the full step-by-step.
Phase summary:
- Data extraction — discover key pages (customers, case studies, solutions, pricing, integrations, G2, LinkedIn) → extract raw data with URL+date per source → normalize attributes (geography, industry, company size, team size, tech stack)
- Analysis and synthesis — identify patterns per segment → build Champion + Economic Buyer deep-dives → identify negative ICP + intent signals → collect proof points → document technographics → calculate TAM with targeting strategy → identify ICP as highest-priority segment below SOM
- Structured output — generate the 12 numbered sections, apply sorting rules, include rich descriptions with URLs and dates
Input requirements
Required
- Website URL — primary company website
Optional (improves quality)
| Input |
Purpose |
| Case studies URL |
Direct link to case studies page |
| Testimonials URL |
Direct link to testimonials |
| Market context |
Category, competitors, GTM approach |
| Sales call notes |
Win/loss context, objections |
| Existing ICP docs |
Validate or expand current understanding |
Anti-hallucination guardrails
- Never invent customer names. Only cite publicly referenced customers.
- Quote verbatim. Use exact customer language in quotes.
- Mark confidence levels. Tag data as High/Medium/Low confidence.
- Cite sources with URLs and dates. Include URL and access date for every claim.
- Acknowledge gaps. Explicit "Not available" for missing data.
| Confidence |
Definition |
| High |
Direct from official source, verifiable |
| Medium |
Third-party source, multiple signals |
| Low |
Single indirect source, inferred |
Quality
Pre-delivery checklist (coverage / personas / segments / evidence): the premium reference.
Related context
Built from:
MMYY-company-context.md (company profile)MMYY-competitor-*.md (competitor profiles for market context)- Win/loss analysis if available
Feeds into:
/icp-behavioural (synthetic personas built on ICP foundation)/positioning (positioning targets ICP pain points)/product-messaging (messaging speaks to ICP personas)/content-strategy (content targets ICP channels and topics)
1---2name: icp-research3description: ICP research skill4---56# ICP research skill78Generate ideal customer profiles for B2B SaaS clients through systematic research and structured output.910## Report structure1112The final ICP report follows this numbered section order:1314| Section | Purpose |15|---------|---------|16| Header | Research date, website, category, confidence score (1-5) |17| 1. Executive summary | High-level synthesis of findings and strategic recommendations |18| 2. TAM analysis | Market sizing with targeting strategy per layer (TAM/SAM/SOM/ICP) |19| 3. Firmographics analysis | Geographic, industry, company segment patterns, and technographics |20| 4. Roles and personas | Core use case, Champion deep-dive, Economic Buyer deep-dive, buying journey |21| 5. Negative ICP | Who is NOT a fit, disqualification criteria, and red flags |22| 6. Customer proof points | Named customers, outcomes, and evidence with URLs |23| 7. Voice of customer synthesis | Language patterns, pain points, and outcome terminology |24| 8. ICP segment definitions | Scoring matrix, in-market signals, segment deep-dives |25| 9. Intent signals and buying triggers | Observable signals indicating purchase readiness |26| 10. Recommendations | Prioritization and messaging by segment |27| 11. Data gaps | Missing information and follow-up suggestions |28| 12. Source appendix | All sources with access dates, URLs, and confidence levels |2930**Confidence score calculation:** Count High/Medium/Low data points. Score 5 if >70% High, Score 4 if >50% High, Score 3 if mixed, Score 2 if >50% Low, Score 1 if >70% Low.3132---3334## Sorting rules3536Apply consistently across all tables:3738| Dimension | Sort order |39|-----------|------------|40| Decision role | **Champion → Economic Buyer → User → Influencer** |41| Company size | Enterprise → Mid-market → SMB → Startup |42| Frequency | Very high → High → Medium → Low |43| Confidence | High → Medium → Low |44| Customer concentration | High → Medium → Low |45| Priority | 1 → 2 → 3 → 4 |46| Industry presence | Strong → Moderate → Emerging |4748---4950## Workflow5152The research runs in 3 phases. Read the premium reference for the full step-by-step.5354Phase summary:55561. **Data extraction** — discover key pages (customers, case studies, solutions, pricing, integrations, G2, LinkedIn) → extract raw data with URL+date per source → normalize attributes (geography, industry, company size, team size, tech stack)572. **Analysis and synthesis** — identify patterns per segment → build Champion + Economic Buyer deep-dives → identify negative ICP + intent signals → collect proof points → document technographics → calculate TAM with targeting strategy → identify ICP as highest-priority segment below SOM583. **Structured output** — generate the 12 numbered sections, apply sorting rules, include rich descriptions with URLs and dates5960---6162## Input requirements6364### Required65- **Website URL** — primary company website6667### Optional (improves quality)6869| Input | Purpose |70|-------|---------|71| Case studies URL | Direct link to case studies page |72| Testimonials URL | Direct link to testimonials |73| Market context | Category, competitors, GTM approach |74| Sales call notes | Win/loss context, objections |75| Existing ICP docs | Validate or expand current understanding |7677---7879## Anti-hallucination guardrails80811. **Never invent customer names.** Only cite publicly referenced customers.822. **Quote verbatim.** Use exact customer language in quotes.833. **Mark confidence levels.** Tag data as High/Medium/Low confidence.844. **Cite sources with URLs and dates.** Include URL and access date for every claim.855. **Acknowledge gaps.** Explicit "Not available" for missing data.8687| Confidence | Definition |88|------------|------------|89| High | Direct from official source, verifiable |90| Medium | Third-party source, multiple signals |91| Low | Single indirect source, inferred |9293---9495## Quality9697Pre-delivery checklist (coverage / personas / segments / evidence): the premium reference.9899---100101## Related context102103**Built from:**104- `MMYY-company-context.md` (company profile)105- `MMYY-competitor-*.md` (competitor profiles for market context)106- Win/loss analysis if available107108**Feeds into:**109- `/icp-behavioural` (synthetic personas built on ICP foundation)110- `/positioning` (positioning targets ICP pain points)111- `/product-messaging` (messaging speaks to ICP personas)112- `/content-strategy` (content targets ICP channels and topics)
matteotitta