prospect-researcher
Skill9 starsChanged 3 months agoMITView on GitHub
Use when evaluating a specific company's fit for your ICP, when needing to score an account against ICP criteria, or when preparing for outreach to a new target
1 other project uses a version of this.
Adopted by
Most recently taken up by
- unrealandychan/AgentFoundrytheir own version, first seen Apr 22, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- unrealandychan/AgentFoundry★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- champion-trackerSkill
- compliance-managerSkill
- contact-finderSkill
- deliverability-managerSkill
- email-writerSkill
- linkedin-contentSkill
- meeting-followupSkill
- multi-channel-writerSkill
- pipeline-trackerSkill
- resource-offerSkill
- setupSkill
- signal-scannerSkill
- validateSkill
The file
Files
Prospect Researcher
Input
Company name or domain. Optionally: known signal type (GitHub, ArXiv, hiring, funding).
Steps
1. Firmographics — web search for: headcount, funding stage, HQ, founding year, investors.
2. Technographics (Firecrawl) — use scripts/firecrawl_client.py to scrape the company website (/scrape endpoint on homepage + /about, /careers, /product). Extract tech stack, product description, hiring language, and domain-specific keywords from config/gtm-context.md. The Firecrawl scanner (scripts/scanners/firecrawl_scanner.py) automates this — run python -m scripts.scanners.firecrawl_scanner --domains company.com for a structured website_enrichment signal. For G2 review intelligence, use scripts/scanners/g2_firecrawl_scanner.py to extract frustration signals and vendor replacement intent without session cookies.
3. Domain Maturity — classify using evidence based on maturity stages defined in config/gtm-context.md:
- PRODUCTIONIZING: domain technology in production + papers or 3+ domain engineers
- SCALING: multiple active repos or hiring ≥2 domain-specific roles
- BUILDING: one active repo (commits <90 days) or recent preprint
- EXPLORING: domain technology mentioned in blog/talk/JD but no active code
- NONE: no detectable domain activity
4. Team Mapping — find decision makers matching priority titles from config/gtm-context.md.
5. Competitive Landscape — note any competitor signals: in-house build indicators, known vendor mentions.
6. Score using templates/scoring-rubrics/icp-scoring-model.md:
weighted_score = (signal_strength * 0.30) + (domain_maturity * 0.25) +
(company_fit * 0.20) + (budget * 0.15) + (accessibility * 0.10)Apply disqualification overrides before scoring.
Output
## [Company Name] — Grade [A/B/C/D]
**Weighted Score:** X.X / 5.0
**ICP Tier:** [1-4 or None]
**Domain Maturity:** [stage]
**Funding:** [stage, amount, date]
**Headcount:** ~N
### Dimension Scores
| Dimension | Points | Weight | Contribution |
|------------------|--------|--------|-------------|
| Signal Strength | | 0.30 | |
| Domain Maturity | | 0.25 | |
| Company Fit | | 0.20 | |
| Budget | | 0.15 | |
| Accessibility | | 0.10 | |
### Key Contacts
- [Name], [Title] — [LinkedIn URL if found]
### Messaging Angles
- [Specific technical hook tied to their work]
### Recommended Next Step
[Run contact-finder / skip / nurture]Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

