map-investors
Skill4 starsChanged 8 months agoMITView on GitHub
Find the right individual people at each candidate VC firm — partners, principals, and associates relevant to the startup's sector and stage. Uses Exa people search and LinkedIn Profile Search Scraper (harvestapi) for accurate, no-cookie profile lookup. Triggers on: "map investors", "find people at funds", "who to contact", "step 3", "next step", "continue to map investors", "find partners at".
In this repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- clarify-thesisSkill
- draft-investor-outreachSkill
- enrich-vc-contactsSkill
- export-csvSkill
- find-vcsSkill
- resetSkill
- score-vc-fitSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 5 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
Read data/raw/fund_candidates.json.
- Very specific: line 35
Use the Exa MCP people_search_exa tool to find investment professionals at the firm.
- Distinctive: line 53
Run 1–2 queries per firm. If Exa returns strong results, proceed to Step 2.
- Distinctive: line 86
Use this to confirm the person is currently at the firm (not a past role) and to extract their sector focus from experience history.
- Distinctive: line 90
If Exa returns nothing and Apify returns nothing for a firm:
- Distinctive: line 96
Use this approach sparingly — it is less reliable than Exa + Apify.
- Distinctive: line 109
Only include operating partners, platform team, or talent team if they are clearly sector-relevant.
- Very specific: line 127
Write an array to data/raw/investor_list.json conforming to schemas/investor_list.schema.json.
- Very specific: line 129
Use the same fund_id slugs from fund_candidates.json as the foreign key.
- Very specific: line 133
After writing data/raw/investor_list.json, present a summary to the founder:
- Very specific: line 156
Do not proceed to enrich-vc-contacts until the founder confirms or adjusts the list.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Map Investors
Pipeline: clarify-thesis → find-vcs → map-investors → enrich-vc-contacts → score-vc-fit → draft-investor-outreach
You are step 3 of 6. Your job is to identify the best 1–3 people to contact at each firm from fund_candidates.json.
Tools
- Exa MCP (
people_search_exa) — primary: semantic people search by name, company, and role - Apify MCP (
harvestapi/linkedin-profile-search) — structured LinkedIn profile data once names are known - WebSearch / WebFetch — fallback for firms with no Exa results
Input
Read data/raw/fund_candidates.json. If the file does not exist, stop and ask the founder to complete find-vcs first.
Also read data/normalized/company_profile.json for sector/stage context — this determines which partners are most relevant.
What to do
For each fund in fund_candidates.json, run the following steps in order.
Step 1: Find people using Exa
Use the Exa MCP people_search_exa tool to find investment professionals at the firm.
Query pattern:
"[fund_name] venture capital" partners principals investorsOr more targeted:
"[fund_name]" "[sector]" partner OR principal OR investorExa returns people with names, titles, LinkedIn URLs, and sometimes bios. Extract:
- Full name
- Title
- LinkedIn URL (if returned)
- Any sector or thesis signals from the bio
Run 1–2 queries per firm. If Exa returns strong results, proceed to Step 2. If Exa returns nothing useful, fall back to Step 3.
Step 2: Pull structured profile data using Apify
Once you have names (and optionally LinkedIn URLs) from Exa, use the Apify actor harvestapi/linkedin-profile-search to get structured profile data.
Actor: harvestapi/linkedin-profile-search
Input pattern (search by name + company):
{
"queries": [
{
"keywords": "[name] [fund_name]",
"filters": {
"currentCompany": "[fund_name]"
}
}
],
"maxResults": 3
}Or if you already have a LinkedIn URL from Exa, pass it directly to get richer profile data (experience history, education, location).
This actor requires no cookies and no LinkedIn account. It returns:
- Full name
- Current title and company
- Location
- Work experience history
- Education
- LinkedIn profile URL
Use this to confirm the person is currently at the firm (not a past role) and to extract their sector focus from experience history.
Step 3: Fallback — WebSearch + WebFetch
If Exa returns nothing and Apify returns nothing for a firm:
- WebSearch:
"[fund_name]" team OR partners site:[fund_website] - WebFetch the team page directly
- Extract names and titles from the page text
Use this approach sparingly — it is less reliable than Exa + Apify.
Person selection priority
Pick people in this order:
- Partner / General Partner
- Principal
- Investor / Investment Team Member
- Associate
Include up to 3 people per firm. If only 1 strong fit exists, include just that person.
Only include operating partners, platform team, or talent team if they are clearly sector-relevant.
Relevance signals
Prefer people who:
- Have invested in the startup's sector before (visible in experience history or bio)
- Focus on the relevant stage
- Are based in the startup's target geography
- Have written or spoken publicly about the relevant thesis area (check Exa bio snippets)
Deprioritize people who:
- Are listed as "advisor" or "venture partner" with no recent deal activity
- Joined the firm very recently with no visible investment history
- Are clearly focused on an unrelated sector
Output
Write an array to data/raw/investor_list.json conforming to schemas/investor_list.schema.json.
Use the same fund_id slugs from fund_candidates.json as the foreign key.
Review checkpoint
After writing data/raw/investor_list.json, present a summary to the founder:
Mapped [N] investors across [M] firms for [company_name]:
| Fund | Name | Title | LinkedIn | Source |
|------|------|-------|---------|--------|
| ... | ... | ... | yes/no | exa / linkedin-search / web |
...
[If some firms had no relevant contacts found]:
⚠ No contacts found for: [list of fund names] — these firms may still be worth targeting via their general contact page.
[If LinkedIn was not found for some]:
Note: LinkedIn missing for [N] contacts — enrich-vc-contacts will attempt to find them.
Does this look right? You can:
- Confirm to proceed to step 4 (enriching contact details)
- Remove a person: "remove [name] from [fund]"
- Add a person manually: "add [name], [title] at [fund]"
- Ask to find more people at a specific firm: "find more people at [fund]"Do not proceed to enrich-vc-contacts until the founder confirms or adjusts the list.
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.

