agentleFS
Sign inStart free
olivMertensolivMertens/copilot-skills/skills/linkedin-post/SKILL.md

linkedin-post

Skill1 starsChanged 51 days agoMITView on GitHub

Draft a punchy, ready-to-paste LinkedIn post around a video, demo, repo or launch — in the user's own voice. Runs a short intake (language EN or EN+FR, target audience, complexity/register, main messages, mandatory links, assets, CTA, hashtags, disclaimers), researches the author's tone from their profile/ articles (or asks for a sample when LinkedIn blocks fetching), applies LinkedIn reach best-practices (hook, white space, native video, captions, link placement, length, hashtags), and outputs the final copy plus a media checklist (poster/cover + FR & EN subtitle files). Use for "write a LinkedIn post", "LinkedIn caption for this video", "post this demo on LinkedIn", "rédige un post LinkedIn", "poste ma vidéo sur LinkedIn". Not for other social networks or long-form articles.

41 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use youtube-upload, proposal-writer and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • BlackLotus1974Skill

    youtube-upload

    Upload videos to Atchalta's YouTube channel (office@atchalta.com). Use when the user asks to upload a video to YouTube, list YouTube videos, manage playlists, or update video metadata. Trigger phrases: 'upload to youtube', 'youtube video', 'publish video', 'post to youtube', 'list my videos', 'youtube playlists'.

    Also in 3 projects that use this

  • ncklrsSkill

    proposal-writer

    Expert sales proposal and pricing presentation strategist. Use when writing proposals, executive summaries, ROI business cases, pricing presentations, SOWs (Statement of Work), RFP responses, or competitive positioning documents. Covers proposal structure, terms positioning, design formatting, follow-up strategy, and win-rate optimization.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    lint

    Run all linting and spell checking for TypeScript and Rust code. Run this before committing to catch style issues, clippy warnings, and misspellings.

    Also in 3 projects that use this

  • OpenAISkill

    brainstorming

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 3 projects that use this

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 36 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. Very specific:

    Run references/questionnaire.md: language (EN, or EN+FR two-part post),

    line 29
  2. Distinctive:

    disclaimers: Never invent a link or a disclaimer — ask.

    line 32
  3. Very specific:

    Follow references/tone-and-voice.md.

    line 35
  4. Distinctive:

    Links: default to placing mandatory links in the first comment (and say "link in comments") to protect reach.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 36 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

LinkedIn post writer

Produce a copy-paste-ready LinkedIn post in the author's voice, tuned for reach, around a piece of media (usually a video/demo) with the right links, captions and cover.

Bundled references

  • references/questionnaire.md — the intake to run before writing.
  • references/linkedin-playbook.md — structure, media, links, hashtags, length.
  • references/tone-and-voice.md — how to capture and mirror the author's voice.

1. Intake (ask before writing)

Run references/questionnaire.md: language (EN, or EN+FR two-part post), target audience, complexity/register, main messages (2–4), mandatory links, assets (video, poster, FR/EN subtitles), CTA, hashtags, disclaimers. Never invent a link or a disclaimer — ask.

2. Capture the author's voice

Follow references/tone-and-voice.md. Try to fetch the author's LinkedIn profile/ articles; LinkedIn usually blocks server-side fetches (HTTP 999 / login wall). If blocked, ask the user to paste 1–3 recent posts or pick a tone from the menu — do not fabricate their style. State which sample you matched.

3. Write the post

Apply references/linkedin-playbook.md:

  • A hook line that earns the "…more" click (no "I'm excited to announce").
  • Short paragraphs with white space; 3–5 beats (problem → what → how → proof).
  • Name concrete tech where the register calls for it; show, don't boast.
  • One clear CTA. 3–5 specific hashtags at the end.
  • Target ~1,300–1,900 characters; front-load meaning in the first ~210 chars.
  • For EN+FR: EN block, a — — — divider, then the FR block (not a literal translation — localize idioms).
  • Links: default to placing mandatory links in the first comment (and say "link in comments") to protect reach; if the user requires them in-body, honor that and note the trade-off. Provide the first-comment text separately.

4. Media checklist (deliver alongside the copy)

  • Native video (upload the MP4 directly, not as a URL).
  • Captions: FR and EN. LinkedIn takes one SRT per upload (viewer toggle); for both languages, deliver two SRT files (user picks per post) or a burned-in variant per language. Most feed views are muted — captions are mandatory.
  • Poster/cover: a strong, muted-legible first frame or a custom cover (headline + product name). Offer a 1:1 or 4:5 re-crop for more mobile height.
  • Alt text for any still image.

5. Deliver

Output, clearly separated:

  1. The post body (per language) ready to paste.
  2. The first-comment text (links) if links were moved out of body.
  3. The media checklist with exact file paths for video, poster and SRTs.
  4. A one-line note on which voice sample you matched and any assumption to confirm.

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