post-writer
Skill21 starsChanged 4 months agoMITView on GitHub
Writes LinkedIn and X posts that read human — a hook line drawn from proven patterns, whitespace rhythm, story or insight structure, a soft CTA — and delivers three full variants per ask (story, contrarian, list). Applies the project's voice profile when one exists and enforces platform length rules. Use when the user says "write a LinkedIn post about...", "turn this into an X post", "draft the launch announcement", or "this sounds corporate — make it human".
4 other projects use a version of this.
Adopted by
Most recently taken up by
- claudiocebpaz/blotato-opencodetheir own version, first seen Oct 13, 2026
- charlie947/social-media-skillstheir own version, first seen Sep 15, 2026
- wltn7810-dotcom/claude-skilltheir own version, first seen Jul 13, 2026
- mahiunfiltered/claude-code-skillstheir own version, first seen Jul 8, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- charlie947/social-media-skills★ 4.4ksame name
- claudiocebpaz/blotato-opencode★ 2same name
- mahiunfiltered/claude-code-skills★ 1same name
- wltn7810-dotcom/claude-skill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository63 other files it gives its agents.
- account-intelligenceSkill
- account-researchSkill
- ad-creativeSkill
- agent-evaluationSkill
- agent-reliabilitySkill
- ai-adoption-leadSkill
- ai-data-stewardSkill
- ai-seoSkill
- ai-workflow-architectSkill
- appsec-reviewSkill
- audit-supportSkill
- brand-guidelinesSkill
- call-prepSkill
- cash-flow-snapshotSkill
- chief-of-staffSkill
- claude-memSkill
- close-managementSkill
- compliance-checkSkill
- context7Skill
- copywritingSkill
- croSkill
- cto-advisorSkill
- customer-researchSkill
- draft-outreachSkill
- financial-statementsSkill
- frontend-designSkill
- growth-engineeringSkill
- growth-experimentsSkill
- growth-strategySkill
- hook-generatorSkill
- invoice-chaseSkill
- journal-entrySkill
- lead-magnetsSkill
- legal-risk-assessmentSkill
- lifecycle-growthSkill
- margin-analyzerSkill
- mcp-builderSkill
- objection-handlerSkill
- pipeline-reviewSkill
- plan-payrollSkill
- profile-optimizerSkill
- proposal-builderSkill
- reconciliationSkill
- reels-scriptingSkill
- revenue-operationsSkill
- review-contractSkill
- run-campaignSkill
- signature-requestSkill
- skill-creatorSkill
- skill-vettingSkill
- superpowersSkill
- tasteSkill
- tax-prepSkill
- token-accountantSkill
- transitionsSkill
- triage-ndaSkill
- ui-ux-pro-maxSkill
- variance-analysisSkill
- vendor-checkSkill
- voice-builderSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
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
- Distinctive: line 29
Write the hook first. Draft 5–10 candidates across proven patterns — specific number, contrarian, mistake, transformation, curiosity gap — …
- Distinctive: line 35
Keep paragraphs to 1–2 lines.
“Common” is measured: kept by at least 6 in 10 of the 4 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.
Files
Post Writer — Ghostwriter
"Write LinkedIn posts"
When to use
- Turning a win, launch, lesson, or opinion into a LinkedIn or X post.
- "Write a LinkedIn post about our migration off Kubernetes."
- "Turn this blog post into an X post that isn't just a summary."
- "Draft my new-role announcement" / "announce our funding round".
- Rescuing a stiff draft: "make this sound like a person wrote it."
Workflow
- Extract the one idea. Decide what the reader should think, feel, or do after reading. One post carries one idea — park the extras as future posts and say so.
- Load
voice-profile.mdif it exists. Its signature phrases, sentence lengths, punctuation quirks, and vocabulary do/don't override generic style everywhere. - Apply platform physics:
- LinkedIn: only the first 2–3 lines show before "...see more", so the hook must survive the fold; 900–1,300 characters is the sweet spot; breaks are free.
- X: 280 characters and the hook is the whole post; thread only if every tweet stands alone.
- Write the hook first. Draft 5–10 candidates across proven patterns — specific number, contrarian, mistake, transformation, curiosity gap — and promote the strongest to line one.
- Build the body on one spine:
- Story: context → tension → resolution → lesson.
- Insight: claim → evidence → implication. Keep paragraphs to 1–2 lines. Whitespace is the pacing; never a wall of text.
- Close soft: a question worth answering, an invitation, or a plain "follow for
more on
<topic>" — never "thoughts?" or "agree?". - Produce three full variants of the same idea: story-led, contrarian-led, list-led.
- Self-edit: delete the first sentence if the post works without it (it usually does), cut adverbs, read aloud for cadence, then run the quality bar.
Output format
## Post: <topic> — <platform>
### Variant A — Story
<full post text, formatted exactly as it should be pasted>
### Variant B — Contrarian
<full post text>
### Variant C — List
<full post text>
---
Recommended: <A | B | C> — <one-line reason>
Character counts: A <n> | B <n> | C <n> (limit: <platform rule>)
Voice profile: applied | not found — generic voice usedQuality bar
- Line one stops the scroll with zero context — no throat-clearing, no "So,".
- One idea per post; every line earns the next.
- No paragraph over two lines; the post breathes.
- Zero corporate tells: no "thrilled to announce", "game-changer", "in today's fast-paced world".
- Hashtags 0–3, end of post only, each one a real discovery channel.
- Inside platform limits; the LinkedIn hook survives the "...see more" fold.
Example
Invocation: "Write a LinkedIn post: we cut our AWS bill 60% by deleting three services nobody used."
Produces: three paste-ready variants — story ("We were paying $14k a month for software nobody had opened since March."), contrarian ("Your cloud bill isn't an engineering problem. It's an archaeology problem."), list (the three services, what each cost, what replaced them) — with the contrarian flagged as recommended for a CTO audience, character counts per variant, and a soft closing question asking readers what's hiding in their own billing console.
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.

