agentleFS
tang-vutang-vu/social-posting-skills/.agents/skills/post-linkedin/SKILL.md

post-linkedin

Skill9 starsChanged 2 months agoMITView on GitHub

Adapt and publish campaign items on LinkedIn — professional narrative posts

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Document carousels and native media over external links.

    line 16
  2. Distinctive:

    Never mass-tag people for reach.

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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 Adapter

Facts live in platforms/linkedin.json (3000-char body, media bounds, publish modes). Do not duplicate numbers here.

What LinkedIn rewards (culture)

  • First-person, specific, professional narrative. "I built X and learned Y."
  • The first line decides the "see more" click — lead with the outcome.
  • Short paragraphs and line breaks; mobile readability matters.
  • Document carousels and native media over external links.
  • Genuine expertise signaled through specifics, not adjectives.

Drafting from the content graph

  • core-claim → opening line (the scroll-stopper).
  • context → 1–2 lines of why/who.
  • proof/technical → arrow-point bullets with the strongest specifics.
  • cta → closing ask + engagement question.
  • Link → first comment (community practice; flagged as heuristic in data).
  • Disclosures read natively: "I built this", "Open source project".

AI-content caution

LinkedIn's feed visibly deprioritizes generic AI-template text. Write in a real voice: concrete details, an actual opinion, a small imperfection. Human review before publishing is mandatory anyway — use it.

Publishing

  • manual → draft package; user pastes. LinkedIn ToS restricts automation — this adapter deliberately offers no browser mode.
  • api → official Posts API exists (OAuth app required); adapter not implemented. Env contract documented in platforms/linkedin.json.

Genuine engagement

  • Comment on others' posts with real substance (LinkedIn surfaces long, substantive comments).
  • Reply to every comment on your post with actual answers.
  • Never mass-tag people for reach; never DM-blast.

Pitfalls

  • Hashtags: a few relevant ones at the bottom; more looks spammy.
  • "Link in comments" is strategy folklore, not a documented penalty — the data labels it honestly.

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.