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
- ClarvAI/job-search-hqtheir own version, first seen Oct 15, 2026
- jack1415926/claude-skillstheir own version, first seen Aug 14, 2026
- Shad0wMazt3r/The-Scaffoldingtheir own version, first seen Apr 24, 2026
- ffsshhttiikk/opencode-agents-skillstheir own version, first seen Feb 28, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- Shad0wMazt3r/The-Scaffolding★ 3same name
- ffsshhttiikk/opencode-agents-skills★ 2same name
- ClarvAI/job-search-hq★ 0same name
- jack1415926/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- applySkill
- career-pathSkill
- decideSkill
- huntSkill
- inboxSkill
- interview-prepSkill
- logSkill
- offer-reviewSkill
- prefsSkill
- researchSkill
- studySkill
- tailorSkill
- trackSkill
- weeklySkill
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
- Distinctive: line 9
Never send anything: Every message is a draft the candidate copies.
- Distinctive: line 10
Don't scrape or compile personal data about individuals beyond their public role/title.
- Very specific: line 13
Read jobs/<slug>/jd.md (if any), profile/career-context.md, profile/master-resume.md.
- Very specific: line 19
Write to jobs/<slug>/network.md or reports/network-<company>-<today>.md.
“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.
Files
/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
- Read
jobs/<slug>/jd.md(if any),profile/career-context.md,profile/master-resume.md. - 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).
- Target list (5–8 role types, not names): why each, what to ask, what the candidate offers in return.
- 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.
- 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.
- 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.mdorreports/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.
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.

