linkedin-content-writer
Skill4 starsChanged 2 months agoMITView on GitHub
Turn one complete source or draft into one source-faithful LinkedIn post through mandatory Halbert headline and Hormozi Hook-Retain-Reward steps.
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 11 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
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 12
Follow every step in order.
- Distinctive: line 16
Read the complete input and both references:
- Distinctive: line 56
Add source-backed specificity: numbers, timeframes, mechanisms, events, or visible results.
- Distinctive: line 74
Use one or more real components.
- Distinctive: line 78
Follow the headline with source-backed context, proof, tension, a question, a story already in motion, or a concrete picture.
- Distinctive: line 88
Keep one clear theme.
- Distinctive: line 95
Use steps only when order matters.
- Distinctive: line 102
Start inside a real source event or establish the situation quickly.
- Distinctive: line 117
Keep the material relevant and usable for the people the hook addresses.
- Distinctive: line 121
If the source cannot fit under 3,000 characters, write one complete content unit around the source's main topic.
- Distinctive: line 127
Use plain words, concrete nouns, active verbs, and natural paragraph rhythm.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
LinkedIn content writer
Input: one complete source or draft.
Output: one paste-ready LinkedIn post under 3,000 characters.
Follow every step in order. Move forward only when the gate passes.
1. Read
Read the complete input and both references:
- Halbert headlines
- LinkedIn winners
Gate: the input and both references have been read in full.
2. Lock the source
Identify the source's exact topic, main claim or result, evidence, examples, sequence, uncertainty, and attribution. The source owns all of them.
The user is always the author, owner, and narrator of the finished post. Name no other person, source creator, or author unless the user explicitly requests it.
Gate: every planned factual claim maps to the input.
3. Choose the post structure
Choose the structure already present in the source:
- list for themed items in flexible order;
- steps for actions that require an order to produce a result;
- story for events that lead to a resolution or lesson;
- argument for a claim supported by evidence and reasoning;
- case breakdown for a result explained by its situation and evidence;
- comparison for differences that affect a decision;
- news explanation for a change, its evidence, and its consequence.
Argument, case, comparison, and news are LinkedIn editorial forms. Carry their attention through Hormozi's lists, steps, stories, or a useful combination.
Gate: the structure preserves the source's real order and can fit below 3,000 characters without breaking its promise.
4. Hook attention
Hormozi defines the hook as topic + headline + format. The input supplies the topic. LinkedIn supplies the format. Build the headline from the source.
Halbert headline pass
- Review the worked headline constructions in the Halbert reference.
- Name the exact event, result, problem, mechanism, or claim in the source.
- Find the strongest truthful news, benefit, or news-plus-benefit already in the source.
- Add source-backed specificity: numbers, timeframes, mechanisms, events, or visible results. Add a person's name only when the user explicitly requests it.
- Draft genuinely different directions. Use the Halbert constructions only when the source supports them.
- Return to what is true and relevant. Reject playful practice lines that distort the source.
- Compare the strongest alternatives phrase by phrase. Keep only phrases that add attention, clarity, credibility, benefit, specificity, consequence, or curiosity.
- Select the headline that gives the clearest truthful reason to consume and that the body can fulfil.
Hormozi headline pass
Strengthen the headline with news components already present in the source:
- recency;
- relevance to the reader;
- a person or authority the user explicitly requested to name;
- proximity to the reader's place or situation;
- conflict;
- unusualness;
- an ongoing development.
Use one or more real components. Try two when they fit naturally. The components are ingredients, not a template.
Opening bridge
Follow the headline with source-backed context, proof, tension, a question, a story already in motion, or a concrete picture. The bridge must make the expected reward clear and lead directly into the body.
Gate: the opening states the exact subject, gives a truthful reason to continue, and creates a promise the body can fulfil.
5. Retain attention
Hormozi's retention mechanism is curiosity through an unresolved question, explicit or implicit. Carry that question with the structure that fits the source.
Lists
- Keep one clear theme.
- State the exact count in the headline or opening when the count is part of the hook.
- Let the remaining items create the unresolved question.
- Deliver every promised item.
Steps
- Use steps only when order matters.
- State the result the sequence produces.
- Make each early step clear and useful so the reader wants the remaining steps.
- Preserve every dependency needed to reach the result.
Stories
- Start inside a real source event or establish the situation quickly.
- Preserve what happened, what changed, and what remained unresolved.
- Move through events toward the answer.
- End with the supported resolution or lesson.
Lists, steps, and stories can interweave when each part adds clarity or curiosity. Longer posts can link smaller Hook-Retain-Reward units inside sections.
Gate: every paragraph advances an unresolved question with a fact, step, example, reason, event, consequence, or useful distinction from the source.
6. Reward attention
Reward means satisfying the reason the reader started.
- Answer every unresolved question.
- Deliver the promised quantity and quality.
- Keep the material relevant and usable for the people the hook addresses.
- Increase value per second: each section must provide a useful fact, example, explanation, distinction, or action.
- Match or exceed the expectation created by the opening.
If the source cannot fit under 3,000 characters, write one complete content unit around the source's main topic. Make a promise that fits that unit. Do not claim to cover the entire source.
Gate: removing any remaining paragraph would remove needed proof, meaning, progression, or reward.
7. Unslop the draft
Use plain words, concrete nouns, active verbs, and natural paragraph rhythm. Remove filler, inflated claims, generic transitions, repeated conclusions, forced symmetry, empty suspense, and abstract labels that add no meaning.
The unslop pass changes wording only. It preserves the source facts, hook promise, structure, and meaning.
Gate: every sentence adds information, movement, proof, or payoff.
8. Verify
Give the source and draft to an independent factual verifier when available. It checks:
- topic fidelity;
- unsupported or changed claims;
- changed scope, conditions, uncertainty, sequence, causation, or metric meaning;
- the selected retention structure;
- unfulfilled opening questions or promises.
Correct every failure and recheck. If no verifier is available, perform the same check line by line.
Gate: zero source-fidelity failures and zero unfulfilled promises remain.
9. Format and return
- Opening block first.
- Short readable paragraphs.
- Numbers for ordered actions.
- Bullets for unordered items.
- CTA after the reward when requested.
- P.S. only for an additional link, resource, or action.
Return only the finished post.
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- microsoft/cat-agent-skills★ 95same name
- syeda-hoorain-ali/personal-ai-employee-hackathon★ 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 repository12 other files it gives its agents.
- audience-content-osSkill
- buyer-signal-list-researchSkill
- cold-offer-reviewSkill
- google-maps-list-builderSkill
- google-maps-owner-email-finderSkill
- icp-prompt-builderSkill
- list-builderSkill
- list-expanderSkill
- offer-creationSkill
- outbound-funnel-economicsSkill
- tiktok-slideshow-machineSkill
- x-content-writerSkill
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.

