linkedin-post-writer
Skill1 starsChanged 46 days agoMITView on GitHub
Write LinkedIn posts for a personal profile or company page that people read, react to and comment on. Use when the user asks to write, rewrite, improve or turn something (an update, article, video, idea or notes) into a LinkedIn post, before publishing it with the PostOnce LinkedIn MCP.
22 other projects use a version of this.
Adopted by
Most recently taken up by
- uplika/uplika-plugintheir own version, first seen Nov 8, 2026
- alunadev/ald-skillstheir own version, first seen Nov 8, 2026
- 07001ec010shnk-svg/linkedin-agent-skillstheir own version, first seen Oct 25, 2026
- jaredhhawk/claude-skillstheir own version, first seen Oct 25, 2026
- Rajveerx11/skillstheir own version, first seen Oct 25, 2026
- prosyo-ai/gtm-skilltheir own version, first seen Oct 25, 2026
Used with
Projects with it also use linkedin-comment-drafter, linkedin-content-planner and 9 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.
sergebulaevSkilllinkedin-comment-drafter
Draft a LinkedIn comment on someone else's post from its URL, or reshare (repost) it to your feed with optional commentary. Use when the user pastes a post URL and asks to comment, engage, be first commenter, or repost with their thoughts. Produces 1-3 variants in the user's voice, picks a reaction, and publishes via Publora on approval. Not for replying to existing comments (use linkedin-reply-handler).
Also in 7 projects that use this
- sergebulaevSkill
linkedin-content-planner
Generate a 7-day LinkedIn content plan from a theme, audience, and pillars. Produces per-day post pillar, format, hook type, CTA, posting time, daily comment targets, and a weekly inbound-readiness check. Use when the user wants to plan a week or month of content, not draft a single post (use linkedin-post-writer).
Also in 7 projects that use this
- +9 more from sergebulaev
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- sergebulaev/linkedin-skills★ 5.4ksame name
- aakashg/pm-claude-skills★ 106same name
- prosyo-ai/gtm-skill★ 13same name
- styfinity/linkedin-engine★ 9same name
- TaplioOfficial/taplio-linkedin-claude-skills★ 7same name
- alunadev/ald-skills★ 4same name
- TaplioOfficial/taplio-linkedin-plugin★ 3same name
- uplika/uplika-plugin★ 3same name
- sohaib25225-gif/claude-linkedin-post-writer★ 2same name
- AIProUK/linkedin-claude-skills★ 1same name
12 more not listed
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 repository6 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
0
Distinctive
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
Write one LinkedIn post that earns attention in the feed, then hand it to the postonce skill if the user wants it published or scheduled.
“Common” is measured: kept by at least 6 in 10 of the 21 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
LinkedIn post writer
Write one LinkedIn post that earns attention in the feed, then hand it to the postonce skill if the user wants it published or scheduled.
Before writing
Get or infer: who is posting (a person or a company page), who they want to reach, the one idea the post carries, and any fact, number or story that proves it. If the user gives a long source (article, transcript, notes), pick the single most interesting idea; one post, one idea. Never invent numbers, results, customers or quotes.
The first two lines decide everything
LinkedIn shows roughly the first two lines before "…see more". Write those lines to make someone tap. Pick one pattern:
| Pattern | Template |
| Name the moment | Open on a specific situation the reader lives. "You posted it on Tuesday. It's Friday and it's still not on Instagram." |
| Worst advice | "WORST ADVICE EVER" then the quoted bad advice, then your stance. |
| Contrarian | "[Topic] advice that doesn't work:" · "Doing [common effort] won't [expected result]." |
| Numbered list | "[N] signs it's time to [big decision]." · "[N] harsh truths nobody told you about [topic]:" |
| Mistake | "One of the biggest mistakes I made in my first year of [skill] was [choice]." |
| Comparison | "The difference between [A] and [B]." |
| Proof | "I analyzed my [N]+ [posts / data points]. Here's what actually worked." · "These [N] [templates] helped me get [result]." |
What to avoid, from studying top company and creator posts:
- Opening with a question. Question openers performed worst (about half the reactions of the same account's normal post).
- Opening with the product or "We're excited to announce". Announcements do well only when line 1 is about the reader's problem.
- Generic tips with no stance. Tip posts underperform unless they take a side.
The body
- Short lines, one thought per line, blank line between ideas. No walls of text.
- Make the stance clear by line 4.
- Specifics beat adjectives: a number, a name, a before/after, a moment.
- Plain words. No "game-changer", "unlock", "in today's fast-paced world", "let's dive in", emoji bullet lists or hashtag walls.
- Length: 600–1,300 characters works for most posts. The hard limit is 3,000.
- A company page can sound human. Named people and real moments beat brand voice.
The ending
End on one of: a specific question that's easy to answer from experience ("What's the one thing you always change before a video goes somewhere else?"), a clear takeaway line, or a soft next step. One ending only.
Links, hashtags and media
- Links in the post body tend to reduce reach. Put the link in the first comment, or say "link in the comments", unless the user wants it in the post.
- 0–3 hashtags, at the end, only if they're specific.
- Native media beats text-only and links: a real photo, a simple chart, a two-frame before/after image, or a short video. Suggest one. For several images, use the
linkedin-image-carouselskill. LinkedIn document (PDF) posts can't be published through this server.
Output
Give the user the post exactly as it will appear, then one line on the hook pattern used and any suggested visual. Offer to publish or schedule it with the postonce skill; confirm the account (profile or which page) and the time before calling create_post.
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.