agentleFS
leoleolroleoleolro/career-os/.claude/skills/network/SKILL.md

network

Skill0 starsChanged 55 days agoMITView on GitHub

Build a networking plan for a target role or company — who to reach, drafted LinkedIn/email messages (the candidate sends), events, communities, and a LinkedIn profile rewrite. Use when the candidate says "network", "who should I talk to", "reach out", "referral", "LinkedIn message", "fix my LinkedIn", "/network".

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    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. Distinctive:

    Never send anything: Every message is a draft the candidate copies.

    line 9
  2. Distinctive:

    Don't scrape or compile personal data about individuals beyond their public role/title.

    line 10
  3. Very specific:

    Read jobs/<slug>/jd.md (if any), profile/career-context.md, profile/master-resume.md.

    line 13
  4. Very specific:

    Write to jobs/<slug>/network.md or reports/network-<company>-<today>.md.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

/network [company | jobs/<slug> | linkedin-about]

Rules

  • Never send anything. Every message is a draft the candidate copies. Never log into LinkedIn or act on their account; use the Browser pane / WebSearch only to read public pages.
  • Don't scrape or compile personal data about individuals beyond their public role/title. Name roles ("BCG X Perth recruiter", "alumni of your current employer now at BCG") and let the candidate find the person.

For a company / role

  1. Read jobs/<slug>/jd.md (if any), profile/career-context.md, profile/master-resume.md.
  2. Warm paths first: your university's alumni at the company, alumni of your current employer, society/volunteering contacts, people who engaged with their LinkedIn posts, the recruiter named in the JD (BCG ANZ: recruitmentinANZ@bcg.com).
  3. Target list (5–8 role types, not names): why each, what to ask, what the candidate offers in return.
  4. Drafts (each ≤ 300 characters for LinkedIn connection notes, ≤ 120 words for InMail/email): connection request, follow-up after accept, referral ask (only after a conversation), thank-you. Specific, no flattery, one clear ask (a 15-minute chat about X). Include a "why me" line grounded in master.
  5. Events/communities: Perth and online (BCG X info sessions late Feb — check careers.bcg.com/events; Oracle user groups; AI meetups; Anthropic community/Discord; your university's alumni events). Verify dates with WebSearch; say "verify" if you can't.
  6. Cadence: a 2-week plan (3 outreach/day max, follow-up after 5 business days, stop after 2 follow-ups). Write to jobs/<slug>/network.md or reports/network-<company>-<today>.md.

linkedin-about

Using profile/linkedin-audit.md and master: write the new headline (≤ 220 chars), About (≤ 2,000 chars, 4 short paragraphs: what they does now / what they builds / credentials / what they's looking for + open to relocation), the your current employer experience description (5 bullets, clients anonymised), the 40-skill list in priority order, 3 Featured items, and Open-to-Work settings. Australian English, first person for About only. Output as profile/linkedin-rewrite.md for the candidate to paste.

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.