network-mapper
Skill1 starsChanged 3 months agoMITView on GitHub
Find warm-intro paths into a target company from the user's own LinkedIn connections export. First-degree from the CSV; second-degree via enrichment + human-in-the-loop. No scraping. Scheduled weekly or on demand.
In this repository19 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- company-researchSkill
- cover-letterSkill
- cv-tailorSkill
- interview-coachSkill
- job-scoutSkill
- learnSkill
- negotiatorSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-exploreSkill
- openspec-proposeSkill
- openspec-sync-specsSkill
- openspec-update-changeSkill
- outreach-drafterSkill
- setupSkill
- submitSkill
- trackerSkill
- upskillSkill
The file
Files
network-mapper — the gap nobody else builds
Legal stance
LinkedIn blocks automation and litigates scraping. This skill uses only the user's own
data: LinkedIn Settings → Data Export → Connections → CSV in data/connections/. No
scraping, no ToS violation.
First-degree (fully automatable today)
- Parse the connections CSV.
- Given a target company, find who in the network works (or worked) there.
- Rank by relationship strength signals available in the export (connection date, shared context if present).
Second-degree (the genuinely hard part — optimise the human step, don't fake it)
The export is first-degree only. Options, in order of preference:
- Enrich first-degree connections' current employers (Harmonic
enrich_person, or Apollo/Hunter via API) and reason about who is likely to know someone relevant. - Ask — draft a message for the user to send a first-degree contact requesting an intro. Often the export can't prove the second-degree link, so make the human ask efficient rather than eliminating it.
Output
For each target role: warm-intro paths found, ranked, each with a suggested next action.
Hands off to outreach-drafter. Scheduled weekly (network changes slowly) or on demand.
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.

