agentleFS
eunomia-bpfeunomia-bpf/eunomia.dev/.agents/skills/linkedin-publisher/SKILL.md

linkedin-publisher

Skill244 starsChanged 5 days agoMITView on GitHub

Prepare or publish eunomia.dev content for LinkedIn posts, articles, carousels, and professional updates. Use when asked to draft, adapt, paste, publish, QA, or record LinkedIn content for blog, tutorial, project, paper, release, consulting, research, or GitHub updates. Covers professional positioning, reader targeting, publication authorization, browser QA, comment/DM follow-up, and media ledger updates.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    If the source path is missing, inspect .github/publisher/posts_queue.txt, .github/publisher/media/not-published.md, recent …

    line 18
  2. Distinctive:

    Use a browser surface with the logged-in session when UI work is required.

    line 29
  3. Distinctive:

    Never bypass authentication with search results or alternate sources.

    line 30
  4. Distinctive:

    Do not directly access LinkedIn APIs, internal endpoints, or background HTTP interfaces.

    line 41
  5. Distinctive:

    document/carousel only when the user explicitly asks for one

    line 52
  6. Distinctive:

    Do not add a separate interpretation, summary, or professional story arc to a long-form share.

    line 58
  7. Distinctive:

    Use a project, GitHub, or paper link instead only when that is the actual long-form or primary artifact being shared.

    line 60
  8. Very specific:

    Before opening the LinkedIn composer, write or update the LinkedIn draft under draft/media/YYYY-MM-DD/<source-slug>/linkedin.md using the …

    line 65
  9. Distinctive:

    no confidential customer, partner, or roadmap information appears

    line 79
  10. Distinctive:

    After a confirmed publish, capture the URL and monitor comments, reactions, and messages only when the user asks or follow-up was part of …

    line 84
  11. Very specific:

    After confirmed publish, update .github/publisher/media/published.md with source path, LinkedIn URL, date, format, media, link target, and …

    line 92

≈ “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 Publisher

Prepare professional LinkedIn posts that build technical credibility. Publication authorization follows CLAUDE.md's Precedence Rule and Publishing section.

Inputs

  • Source Markdown path, project, repo URL, paper, or topic.
  • Intended audience, format, and posting account when specified.
  • Optional media, canonical link, GitHub link, hashtags, or follow-up plan.

If the source path is missing, inspect .github/publisher/posts_queue.txt, .github/publisher/media/not-published.md, recent docs/blog/posts/, and relevant GitHub repos before asking the user.

Platform Entry Points

Use a browser surface with the logged-in session when UI work is required. Never bypass authentication with search results or alternate sources.

References

Load references/platform-preferences.md when choosing LinkedIn-native framing, professional positioning, first-lines hook, media/link treatment, promotion balance, or follow-up. Do not load broad strategy drafts for routine posting unless the user asks for campaign or content-platform planning.

Browser-Only Platform Boundary

Do not directly access LinkedIn APIs, internal endpoints, or background HTTP interfaces. All drafting, QA, screenshots, and ledger evidence must come from normal browser interactions.

Draft Preparation

  1. For a long-form share, read the source and identify only its core problem, tension, or result and the published link.
  2. Choose the format:
    • feed post for the default long-form share case: the published link plus one or two hook sentences
    • document/carousel only when the user explicitly asks for one
    • article only when the user explicitly asks for long-form on LinkedIn
  3. For a LinkedIn article that syndicates an existing long-form source, preserve the source title exactly and keep the body substantively unchanged. Only make mechanical rendering fixes and set platform metadata. A rewrite requires an explicit request for that article.
  4. Do not add a separate interpretation, summary, or professional story arc to a long-form share. Use one or two sentences for the hook, then the link.
  5. Use a project, GitHub, or paper link instead only when that is the actual long-form or primary artifact being shared.

Draft Archive

Before opening the LinkedIn composer, write or update the LinkedIn draft under draft/media/YYYY-MM-DD/<source-slug>/linkedin.md using the local date. Include the full paste-ready post or exact long-form source reference, first-visible-lines check, primary link, optional first-comment links, media/alt text, visibility target when known, and QA state.

Browser QA

  • first visible lines make the value clear before "see more"
  • link card, media, or document preview renders correctly
  • audience/visibility setting is intentional
  • mentions and hashtags are relevant and minimal
  • no confidential customer, partner, or roadmap information appears
  • the final action matches the task: published when authorized, untouched for a draft-only task

Follow-Up

After a confirmed publish, capture the URL and monitor comments, reactions, and messages only when the user asks or follow-up was part of the task. Draft substantive replies to technical questions and move implementation work to GitHub when appropriate. Do not send connection requests, DMs, likes, reposts, or comments without explicit instruction.

Ledger Update

After confirmed publish, update .github/publisher/media/published.md with source path, LinkedIn URL, date, format, media, link target, and follow-up notes.

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.