agentleFS
Sign inStart free
velasco810velasco810/claude-code-linkedin/skills/vcs/SKILL.md

vcs

Skill1 starsChanged 7 months agoMITView on GitHub

End-to-end LinkedIn investor search — scrape a person's network and rank the best VC matches for your raise

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Ask the user for everything you need.

    line 17
  2. Distinctive:

    Look for existing scraped data:

    line 33
  3. Distinctive:

    If data exists, tell the user:

    line 39
  4. Distinctive:

    If no data exists, proceed to scraping.

    line 42
  5. Distinctive:

    Before invoking the scraper, set expectations:

    line 46
  6. Distinctive:

    Wait for it to complete.

    line 59
  7. Very specific:

    After scraping completes, read ${CLAUDE_SKILL_DIR}/../../output/<person>/progress.json and display:

    line 63
  8. Distinctive:

    After analysis completes, provide a final wrap-up:

    line 78

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

LinkedIn Leads — Investor Search

Find and rank potential VC investors from a LinkedIn network based on your raise details and ideal investor profile.

Instructions

Step 1: Gather information

Ask the user for everything you need. If they provided details in $ARGUMENTS, use those and only ask for what's missing:

  1. Target person's name — A short label used as the output folder (e.g. "eduardo", "aum")
  2. LinkedIn URL — The connections page or search results URL to scrape
  3. Scrape type — "connections" (their connections list) or "search" (a search results page)
  4. What are you raising? — Stage, target amount, and sector. Examples:
    • "Seed round, $3M, AI security for enterprise"
    • "Series A, $15M, developer tools for platform engineering"
    • "Pre-seed, $1.5M, vertical SaaS for construction"
  5. What kind of investor do you want? — What matters beyond the check? Examples:
    • "Hands-on operator VCs who've built enterprise sales motions"
    • "Sector-specific funds with deep cybersecurity portfolios"
    • "Solo GPs or small funds where we'd be a top-3 bet"

Step 2: Check for existing data

Look for existing scraped data:

${CLAUDE_SKILL_DIR}/../../output/<person>/meta.json

If data exists, tell the user:

"I found existing data for [person] — [count] profiles scraped on [date] from [url]. Want to use this data or re-scrape?"

If no data exists, proceed to scraping.

Step 3: Scrape (if needed)

Before invoking the scraper, set expectations:

Starting scrape of [person]'s [connections/search results]

  • A Chromium browser window will open (this is expected)
  • Typical scrape time: 10-15 minutes depending on connection count (one-time — you won't need to re-scrape to run different analyses)
  • You'll see real-time progress in the terminal

Invoke the scrape skill:

/linkedin:scrape <person> <type> <url>

Wait for it to complete.

Step 3.5: Post-scrape report

After scraping completes, read ${CLAUDE_SKILL_DIR}/../../output/<person>/progress.json and display:

Scrape complete: [count] profiles in [duration] ([rate] profiles/min) Starting investor analysis...

Step 4: Analyze

Build the criteria string from the user's raise details and investor preferences, then invoke the analyze skill in vcs mode:

/linkedin:analyze <person> <raise + investor preferences as criteria> vcs

Step 5: Summary

After analysis completes, provide a final wrap-up:

Investor search complete

  • Scrape: [count] profiles in [duration]
  • Analysis: [agent_count] agents, ~[tokens]K tokens, [duration]
  • Total wall time: ~[total]
  • Results: [tier1_count] Tier 1 / [tier2_count] Tier 2 / [tier3_count] Tier 3

Then:

  • Top 5 investor matches and why each one fits your raise
  • File locations for the full ranked list
  • Offer to format results for WhatsApp, email, or CSV if the user wants to share them

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free