prospecting-lists
Skill8 starsChanged 3 months agoMITView on GitHub
Build qualified prospect lists from directories, databases, and community research. Use when the user wants to build a target list of potential clients beyond real-time keyword search. Also use when the user mentions "prospect list," "lead list," "ICP," "ideal client profile," "target accounts," "who should I reach out to," or "build a list." This is systematic list-building — different from the real-time keyword-search skill. For writing outreach after building the list, see cold-dm.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- cold-dmSkill
- content-sellingSkill
- discovery-callsSkill
- follow-up-sequencesSkill
- keyword-searchSkill
- profile-optimizationSkill
- context-engineeringSkill
- design-docSkill
- discussSkill
- grillingSkill
- llm-wikiSkill
- opencode-sessionsSkill
- playwright-cliSkill
- pr-descriptionSkill
- demand-first-validationSkill
- founder-market-fitSkill
- idea-scoringSkill
- market-entry-strategiesSkill
- ship-v1Skill
- trend-researchSkill
- tiger-style-codingSkill
- voicenotesSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Don't skip this. A vague ICP produces a vague list.
- Distinctive: line 29
Referrals from current/past clients: Ask "who else should I talk to?"
- Distinctive: line 70
Weekly: Add 10-20 new prospects from Tier 1-2 sources
- Distinctive: line 71
Monthly: Run Tier 3 database searches for new matches
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Prospecting Lists
Your goal is to help the user define their ideal client precisely, then systematically find matching prospects across multiple sources.
Before Starting
Define the ICP (Ideal Client Profile)
Don't skip this. A vague ICP produces a vague list. Nail down industry/vertical, company stage, size, budget signal (can they actually pay?), pain point, decision-maker, and geography.
Example ICP (not "startups"): "Seed-to-Series-A startups in the AI/ML space with 5-20 employees, based in UK/US/EU, that have raised funding in the last 6 months and are hiring engineers (signal they're building). Decision-maker is the CTO or technical co-founder. They need help shipping their API/developer experience layer but can't justify a full-time hire for it."
Disqualifiers (equally important)
Define what makes a prospect a clear skip: pre-idea founders with no funding, companies with in-house teams that already cover your skill, industries you don't want to work in, budget below your floor.
Source Hierarchy
Tier 1: Warm Sources (Highest Conversion)
- Your existing network: Past colleagues, conference contacts, community members
- Referrals from current/past clients: Ask "who else should I talk to?"
- Communities you're in: Ramen Club, P1, Slack groups, Discord servers, Telegram groups
- Event attendees: Meetup/conference attendee lists
Tier 2: Public Intelligence
- Funding trackers: Crunchbase, PitchBook, TechCrunch Startups — recently funded = recently spending
- Job boards: Companies hiring for your skill = companies that need your skill NOW
- Product Hunt / Hacker News: Recently launched products that might need help scaling
- GitHub: Active repos in your niche, check the org/company behind them
Tier 3: Database Tools
- Apollo.io — firmographic + contact data, free tier available
- LinkedIn Sales Navigator — advanced search by role, company, industry
- Hunter.io — find email addresses from domains
- Clay — enrichment and multi-source prospecting
- BuiltWith — find companies using specific technologies
- Twitter/X lists — curate lists of ideal clients, monitor their activity
Building the List
Target: Start with 50-100 qualified prospects
For each prospect, capture:
| Field | Example |
| Name | Sarah Chen |
| Role | CTO |
| Company | Acme AI |
| Company stage | Series A, $5M raised |
| Platform (best channel) | Twitter + Telegram |
| Qualification signal | Hiring 3 engineers, launched API last month |
| Personalisation hook | Posted about struggling with API documentation |
| Status | Not contacted |
Quality > Quantity
25 verified, well-researched leads beats 250 mostly-junk ones. Each prospect should pass your ICP checklist before going on the list.
Refresh Cadence
- Weekly: Add 10-20 new prospects from Tier 1-2 sources
- Monthly: Run Tier 3 database searches for new matches
- Quarterly: Review and update ICP based on what's actually converting
Related Skills
- keyword-search — find real-time opportunities (complements list-building)
- cold-dm — write outreach for your list
- follow-up-sequences — systematic follow-up for non-responders
- discovery-calls — handle the call when prospects respond
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.