| name | linkedin-signal-posts |
| description | 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. |
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.
