linkedin-signal-posts
Skill0 starsChanged 4 months agoMITView on GitHub
Turns messy project notes into high-signal LinkedIn posts for AI, research, startup, hackathon, education, or technical audiences. Use when the user asks for a LinkedIn post, launch post, achievement post, founder update, research announcement, or polished social post.
In this repository5 other files it gives its agents.
- agent-task-compilerSkill
- skill-authorSkill
- skill-repair-loopSkill
- video-prompt-directorSkill
- voice-capsuleSkill
The file
We split this skill 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
- Very specific: line 11
Read examples.md in this skill's folder before writing — the voice lives there, not in adjectives.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
LinkedIn Signal Posts
Mission
Turn messy project notes into a sharp LinkedIn post that builds credibility and gives the reader one useful idea. The post must sound like a real builder, not a corporate announcement.
Read examples.md in this skill's folder before writing — the voice lives there, not in adjectives.
Inputs
Work with what you're given. If BOTH proof and audience are missing, ask one batched question for them — never more than one round. Never invent metrics, users, or traction the notes don't contain.
Workflow
- Extract the signal: what was built, why it matters, who should care, what proof exists.
- Choose ONE angle: builder story / research progress / product launch / technical workflow / education impact / hackathon story. If the notes contain several projects, pick the strongest single story — never merge them into mush. Note the dropped ones in the risk check.
- Strip weak language: no "thrilled to announce", no "leveraging cutting-edge AI", no fake humility, no unsupported traction claims, no "AI is changing the world" framing.
- Write: strong first line (the problem or the concrete thing — never the announcement), short paragraphs, concrete details, one useful takeaway, clean ending. No engagement bait.
- Risk check: anything overclaimed? audience clear? proof specific? sounds human? would a smart reader respect it?
Rule precedence
Explicit user requests beat style rules. If the user asks for something the rules forbid (e.g. "start with Thrilled to announce"), do it their way, offer one alternative hook, and don't lecture.
Output format
Final LinkedIn post
[The post]
Alternate hooks
1–3 different first lines.
Risk check
Unsupported, vague, or overhyped parts — or "clean".
Shorter version
Compressed to under 80 words.
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.

