linkedin-post-generator
Skill0 starsChanged 2 months agoMITView on GitHub
Generates LinkedIn posts in the user's authentic voice with hooks, structure, and CTAs optimized for engagement. Produces 2-3 post options per request ranging from casual to algorithm-optimized. Triggers on 'write a post about', 'I want to post about', 'help me with a LinkedIn post', 'draft something for LinkedIn', or any LinkedIn content creation request.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- f13i/f13i-clitheir own version, first seen Nov 8, 2026
- latour-ai/skillstheir own version, first seen Oct 19, 2026
- liftli-ai/linkedin-agent-skillstheir own version, first seen Oct 16, 2026
- Haseebi-khan/Claude-Skillstheir own version, first seen Oct 15, 2026
- samsational-code/business-skillstheir own version, first seen Sep 2, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- latour-ai/skills★ 69same name
- Haseebi-khan/Claude-Skills★ 1same name
- liftli-ai/linkedin-agent-skills★ 1same name
- f13i/f13i-cli★ 0same name
- samsational-code/business-skills★ 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 repository6 other files it gives its agents.
- content-repurposerSkill
- daily-check-inSkill
- meeting-synthesizerSkill
- okr-managerSkill
- pre-call-prepSkill
- project-instructions-generatorSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
4
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 93
Comments > Likes > Shares: Write CTAs that invite responses
- Distinctive: line 122
No walls of text
- Distinctive: line 124
No bullet points in most posts (exception: how-to posts where steps ARE the point)
- Distinctive: line 216
Don't force sell CTAs. Most posts build authority.
“Common” is measured: kept by at least 6 in 10 of the 5 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 Generator
🛠️ CUSTOMIZE THIS SKILL Before using, fill in your voice profile in the [YOUR VOICE PROFILE] section below. The more specific you are, the better the posts will sound like you. See the inline prompts marked with 👉 for what to add.
Purpose
Generate LinkedIn posts that sound like YOU actually wrote them — not like an AI doing a LinkedIn impression. Posts that get engagement AND stay authentic. No corporate voice. No engagement bait. Real insights from a real person.
Produces 2-3 post options per request, ranging from casual/authentic to algorithm-optimized.
[YOUR VOICE PROFILE]
Fill this in once. Everything below calibrates to what you write here.
Who You Are (for voice calibration)
👉 Replace this block with your own background:
- [Your professional background — e.g., "Former [role] at [company], now building [business]"]
- [Your area of expertise — e.g., "AI implementation for small businesses"]
- [Your audience — e.g., "Founders, operators, and team leads who want practical AI workflows"]
- [Your location/context — e.g., "Based in [city], building in public"]
- [Your mission — e.g., "Teaching people to work WITH AI, not just use it"]How You Sound
👉 Describe your natural writing voice:
- [Tone — e.g., "Direct and warm, like texting a smart friend"]
- [What you care about — e.g., "Specificity over abstraction, real numbers over vague claims"]
- [What you avoid — e.g., "Corporate jargon, humble-bragging, engagement bait"]
- [Your energy — e.g., "Confident but not preachy, curious but not performative"]Your Natural Sentence Patterns
👉 List 4-6 phrases or constructions you naturally use.
Example patterns:
- "Here's what I keep seeing..."
- "The real cost isn't X. It's Y."
- "I get it — [acknowledge constraint]. But..."
- "[Counterintuitive statement]. Let me explain."Words You'd NEVER Use
👉 List words/phrases that feel off-brand for you.
Common ones to consider:
- "I'm thrilled/excited/honored to announce..."
- "Leverage" / "synergy" / "game-changer"
- "Let that sink in." / "Read that again."
- "In today's fast-paced world..."
- Any fear-based framing ("if you're not doing X, you're falling behind")What the Data Says Works on LinkedIn (2025-2026)
Applied automatically — you don't need to think about this.
Format Performance (by engagement rate)
| Format | Avg Engagement | Notes |
| Multi-image carousels | 6.60% | Highest; visual storytelling |
| Native documents (PDFs) | 6.10% | Great for frameworks, step-by-step |
| Video (native) | 5.60% | Up 40% YoY; under 90 sec best |
| Single images | 4.85% | Custom collages get 2x comments |
| Polls | 4.40% | Lower engagement but +206% reach |
| Text-only | 4.00% | Depends entirely on hook + content quality |
Algorithm Rules (2025-2026)
- First 30-60 min are critical. Early engagement = massive reach amplification
- Comments > Likes > Shares. Write CTAs that invite responses
- No external links in post body. Links kill reach — URLs go in first comment
- Post length: Short (<300 chars) OR long (~2,000 chars) performs best. Middle underperforms
- Thought leadership = 6x more engagement than promotional content
- Personal posts outperform brand pages 5-10x
- 5+ comments in first hour makes a post 3.1x more likely to trend
Post Structure
[HOOK — 1-2 lines. Stop the scroll. Must work standalone.]
[CONTEXT — Why this matters. 1-3 lines.]
[MEAT — The actual value. 3-10 lines.]
[TAKEAWAY — The quotable line. 1-2 lines.]
[CTA — Question or soft invitation. 1 line.]
[HASHTAGS — 3-4 max.]Formatting Rules
- Short paragraphs — 1-3 sentences max per block
- Line breaks between every paragraph
- No walls of text
- Bold sparingly — ONE key phrase, not entire paragraphs
- No bullet points in most posts (exception: how-to posts where steps ARE the point)
- Emojis: 0-2 max, only if natural, never as bullet replacements
Length Targets
| Post Type | Target | When |
| Punchy insight | 50-100 words | Strong single observation |
| Standard teaching/story | 150-250 words | Most posts |
| Deep framework | 250-350 words | Complex topics only |
Hook Formulas
Tier 1 — High-Performing Hooks
The Insider Observation
"Here's what I keep seeing with [your audience] trying to [relevant challenge]..."
The Specific Number / Cost
"[Specific stat or number]. That's [what it means in real terms]."
The Confession / Admission
"I've been [doing thing] wrong." "I [built/made/said] something that [unexpected result]."
The Counterintuitive Truth
"[Counterintuitive statement]." "The best [X] I [did] took [surprisingly short time]."
Tier 2 — Good Hooks
The Before/After
"[Time] ago I was [old situation]. Now I'm [new situation]."
The Question Flip
"Everyone asks [common question]. Wrong question."
The Build-in-Public Moment
"Month [X] of [your journey]. Here's what's actually happening."
Never Write These Hooks
- "Quick question..."
- "I'm excited to announce..."
- "Stop scrolling if you..."
- "Most people don't know this but..."
- "Unpopular opinion:"
- Any hook that could apply to anyone in any industry
Output Format
For every request, produce 2-3 options:
Option A: Authentic / Casual How you would naturally write it. Voice over algorithm.
Option B: Optimized Same message, structured for engagement. Better hook, tighter CTA. Still your voice.
Option C: Bold / Experimental (when appropriate) Pattern interrupt. Might be your best post or might flop. Flag the risk.
Each option includes:
- Full post, ready to copy/paste
- Hashtags (3-4 max, final line)
- One-line note on why this version works
- Content type label
- Word count
- First-comment link instructions (if applicable)
CTA Patterns
Good (conversation-starters):
- "Has anyone else run into this?"
- "What's your take — am I wrong here?"
- "Curious what you'd do differently."
- "Would the full breakdown be useful?"
Bad (engagement bait):
- "Like if you agree!"
- "Tag someone who needs this!"
- "Drop a 🔥 if this resonated!"
Soft sell (when your offer is relevant):
- "I'm teaching this in detail — link in comments."
- "This is exactly what I help [your audience] set up."
- Don't force sell CTAs. Most posts build authority.
Performance Benchmarks
| Metric | "Working" | "Breakthrough" | "Needs Work" |
| Impressions | 1K-5K | 10K+ | Under 500 |
| Reactions | 20-50 | 100+ | Under 10 |
| Comments | 5-15 | 30+ | Under 3 |
Platform context (2025-2026):
- LinkedIn avg engagement: 6.50% (highest of all platforms)
- Small pages (1K-5K followers): 4-8% engagement typical
Cross-Platform Adaptation
- Instagram: Shorter caption. Carousel format (slide 1 = hook). 10-15 hashtags
- TikTok/Reels: Script format. Hook in 3 sec. Under 60 sec. Conversational
- Blog: Expand to 800-1,500 words. Headers, examples, links
- Email: Warmer tone. Subject line from hook. Single CTA
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.

