agentleFS
Sign inStart free
HemanthMChakravarthyHemanthMChakravarthy/linkedin-agent-skills/AGENTS.md

linkedin-agent-skills

AGENTS.md2 starsChanged 43 days agoMITView on GitHub

Repo context for AI coding agents (Claude Code, Copilot, Codex, Gemini CLI, Cursor). This file is read by all of them. linkedin-agent-skills is a pack of 12 Agent Skills (open SKILL.md standard) that run a LinkedIn content workflow: posts, comments, replies, profile audits, weekly planning, DMs, inbox triage, carousels, repurposing, performance audits, a voice profiler, and a humanizer that strips the AI fingerprint from every draft. 1. Frontmatter stays portable. name + description only. No platform-specific keys (user-invocable, disable-model-invocation, argument-hint,…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository12 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    No fabrication: Never invent metrics, clients, or outcomes.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md

AGENTS.md

Repo context for AI coding agents (Claude Code, Copilot, Codex, Gemini CLI, Cursor). This file is read by all of them.

What this is

linkedin-agent-skills is a pack of 12 Agent Skills (open SKILL.md standard) that run a LinkedIn content workflow: posts, comments, replies, profile audits, weekly planning, DMs, inbox triage, carousels, repurposing, performance audits, a voice profiler, and a humanizer that strips the AI fingerprint from every draft.

Non-negotiable rules

  1. Frontmatter stays portable. name + description only. No platform-specific keys (user-invocable, disable-model-invocation, argument-hint, allowed-tools, context). scripts/validate.py enforces this in CI.
  2. Skills are draft-only. Nothing posts, publishes, sends, connects, or logs into LinkedIn. Ever. See docs/SAFETY.md.
  3. No fabrication. Never invent metrics, clients, or outcomes. Use {{your number}} placeholders and flag them.
  4. Voice profile first. Any new writing skill must load ~/.agents/linkedin/voice.md (with the Claude/Copilot fallbacks) or invoke li-voice before drafting.
  5. Humanizer in the loop. Any new outward-facing skill must route drafts through li-human before showing them.

Layout

  • skills/li-*/SKILL.md — the skills; name matches the directory name
  • skills/li-human/ — humanize.py, detect.py, slop.json (zero-dep tools)
  • skills/li-post/hooks.json, skills/li-profile/rubric.json — skill data
  • templates/voice.md — blank voice profile
  • scripts/install.sh — multi-agent installer; scripts/validate.py — CI contract

Checks

python3 scripts/validate.py   # frontmatter + contract for all 12 skills
bash -n scripts/install.sh    # installer syntax

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