linkedin-post-writer
Skill1 starsChanged 39 days agoMITView on GitHub
Write LinkedIn posts built for the feed - a hook that survives the two-line truncation, scannable one-idea-per-line structure, a comment-bait close, and first-hour engagement moves. Use when someone asks "write a LinkedIn post about this", "punch up my LinkedIn hook", "why did my post get no reach", or "turn this win into a LinkedIn post". Do NOT use for Twitter/X threads - use tweet-thread-builder instead. Do NOT use for scheduling across a monthly calendar - use social-content-calendar instead.
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 10 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
sergebulaevSkilllinkedin-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
az9713Skilllinkedin-profile-optimizer
Optimize LinkedIn profile sections for maximum impact and conversions. Use when the user wants to improve their LinkedIn headline, about section, experience descriptions, or overall profile strategy.
Also in 10 projects that use this
- +9 more from sergebulaev
Other versions22 projects use a version of this.
Word for word · 2
- SkillMedev/social-media-studio★ 1100% same
- SkillMedev/job-search-kit★ 0100% same
Edited · 0
None found.
Wrote their own version · 20
- 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
10 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 repository7 other files it gives its agents.
- brand-guidelinesSkill
- case-study-builderSkill
- content-briefSkill
- email-newsletter-proSkill
- landing-page-copySkill
- testimonial-capture-interviewSkill
- tweet-thread-builderSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 19 edited versions we read keep these.
10
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 27
No throat-clearing ("I've been thinking lately...").
- Distinctive: line 28
No hashtags in the hook - they read as spam up top.
- Distinctive: line 60
Do not edit the post in the first hour, and do not put an external link in the post body.
- Distinctive: line 62
If the user cannot be online for the first hour, avoid the "comment X and I'll DM you" close - unanswered comment-bait reads as a broken …
- Distinctive: line 117
Do not open with throat-clearing or "thrilled to announce" - the hook budget is two lines.
- Distinctive: line 118
Do not put external links in the post body.
- Distinctive: line 119
Do not use markdown bullets or heavy formatting - LinkedIn renders it literally.
- Distinctive: line 120
Do not stack five hashtag-buzzwords where one number would do.
- Distinctive: line 121
Do not post and ghost; an unattended first hour wastes the post.
- Distinctive: line 122
Do not write a thread-shaped piece here - for Twitter/X format, use tweet-thread-builder.
“Common” is measured: kept by at least 6 in 10 of the 19 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 posts for how people actually read LinkedIn: on a phone, fast, in a crowded feed. The feed truncates after roughly two lines, so the costly mistake is spending effort on the body while line one fails to earn the "see more" click - and then abandoning the post at publish, when the first hour of engagement decides whether the algorithm shows it to anyone at all.
Operating procedure
Step 1: Gather inputs
- The story or idea - one concrete moment, result, or claim. If the user offers a vague topic ("leadership"), push for a specific incident or number; specificity is the post.
- The single takeaway a reader should leave with (one, not five).
- Proof details: numbers, timeframes, names of situations (anonymized as needed). Label estimates as estimates.
- The engagement goal: comments (default - comments drive reach hardest), profile visits, or a lead-magnet offer.
- Whether the user can be online for 60 minutes after posting (this changes the close - see Step 5).
Step 2: Write the hook (first 2 lines)
The opening must earn the "see more" click before truncation.
- Lead with tension, a number, a contrarian claim, or a concrete moment.
- No throat-clearing ("I've been thinking lately...").
- No hashtags in the hook - they read as spam up top.
Hook patterns that work:
- "I [did X]. It [unexpected result]. Here's what I learned."
- "Most people get [topic] wrong. Here's the part they miss."
- "[Number] [thing] in [time]. The breakdown:"
Step 3: Structure the body
- One idea per line. Short lines. Generous line breaks - the white space is the format.
- 5-12 short paragraphs, most only 1-2 lines.
- Build toward one takeaway, not five.
- Lists use line-break bullets, not markdown bullets (LinkedIn renders markdown as literal characters).
- Voice: conversational, first person, specific. Concrete details beat adjectives - "cut onboarding from 9 days to 2" beats "improved onboarding dramatically". No buzzword stacking; no "thrilled to announce" unless it is truly an announcement.
Step 4: Close for comments
End with a single clear call to engage:
- A question that is easy to answer from experience.
- "Agree? What would you add?"
- An offer ("Comment 'guide' and I'll send the template") - only if the user can actually fulfill every comment within a day.
Hashtags: 3-5 max, at the very bottom, specific to the topic.
Step 5: Run the first-hour engagement play
The first 60-90 minutes of engagement heavily determine total reach. Build this into the plan, not as an afterthought:
- Post when the audience is awake - for a professional audience, weekday mornings in their timezone (roughly 7-10am) are the safe default.
- Reply to every comment in the first hour, with a substantive reply (a sentence that adds something, not "Thanks!") - replies count as comments and double the comment volume.
- Do not edit the post in the first hour, and do not put an external link in the post body; if a link is needed, add it in a comment after initial traction. Both suppress distribution.
- Spend 10-15 minutes before and after posting leaving thoughtful comments on others' posts in the same niche; reciprocal early engagement is the most reliable cold-start lever.
- If the user cannot be online for the first hour, avoid the "comment X and I'll DM you" close - unanswered comment-bait reads as a broken promise.
Worked example: bad vs good
Bad:
Thrilled to share some exciting news! 🎉
Over the past few months, our team has been working incredibly hard on
improving our customer onboarding experience, and I'm proud to say the
results have been amazing. It just goes to show that with dedication,
teamwork, and a customer-first mindset, anything is possible. Huge
shoutout to everyone involved - couldn't have done it without you!
#onboarding #teamwork #customerfirst #growth #saas #startup #proudWhy it fails: the hook says nothing before truncation, one wall-of-text paragraph, zero numbers, five buzzwords, no takeaway, no reason to comment, hashtag soup.
Good:
Our onboarding took 9 days. New customers were churning before day 10.
We got it to 2 days. Here's the change that did 80% of the work:
We stopped asking customers to configure anything.
Instead, we shipped every account pre-configured from their signup answers.
Wrong guesses? They fix in minutes. Blank screens? They abandon.
The counterintuitive part: our "flexible setup" was the churn driver.
Flexibility felt like homework.
Result after 60 days:
→ Onboarding: 9 days → 2
→ Week-2 retention: up 23%
→ Support tickets during setup: down half
The takeaway: defaults beat options for first-run experiences.
What's the "homework" you're accidentally assigning your customers?
#onboarding #productmanagement #saasWhy it works: line one is a concrete failure with numbers, the "see more" click is earned before truncation, one idea per line, a real before/after, exactly one takeaway, and a closing question anyone in the niche can answer from experience.
Deliverable
Produce a publish-ready post containing: a two-line hook that survives truncation, a 5-12 paragraph body with one takeaway, a single engagement CTA, 3-5 bottom hashtags - plus a first-hour plan (post time, reply commitment, link-in-comment if any).
Do NOT
- Do not open with throat-clearing or "thrilled to announce" - the hook budget is two lines.
- Do not put external links in the post body; drop them in a comment after traction.
- Do not use markdown bullets or heavy formatting - LinkedIn renders it literally.
- Do not stack five hashtag-buzzwords where one number would do.
- Do not post and ghost; an unattended first hour wastes the post.
- Do not write a thread-shaped piece here - for Twitter/X format, use tweet-thread-builder.
Quality bar
Before publishing, verify:
- Does line 1 make you want to read line 3?
- Could this be 30% shorter? Cut it.
- Is there exactly one takeaway?
- Does the ending invite a comment, not a sale?
- Is every claim backed by a specific - a number, timeframe, or named situation?
- Is the first-hour plan set (time slot, reply availability, link handling)?
For the Twitter/X version of the same story, route to tweet-thread-builder; for slotting posts into a publishing rhythm, use social-content-calendar.
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.

