Linkedin Post Writer

LinkedIn Post Writer

Most weak posts are decided before the first word is written. The author starts from a topic ("something about onboarding") instead of from material (a number, a date, a thing a customer said), so the draft has to be built from generalities, and generalities all sound alike. The opening is then chosen for how it sounds, a format is borrowed from a post that did well for someone else, and the result is a confident paragraph about nothing in particular with a question bolted to the end.

This skill reverses the order. It starts with an inventory of what the author really has, lets that inventory decide which of fourteen opening patterns are available, builds the body from beats that each need a fact, and runs a mechanical gate before the text leaves the editor. Patterns the author lacks the material for are not offered; instead the skill says which single question would unlock them.

Scope boundary. This skill drafts a single feed post and checks it. It does not run the full machine-tell audit, score emoji, or build a voice fingerprint; hand the draft to linkedin-humanizer for that. It does not study other people's posts to extract their openings; that is linkedin-hook-analyzer. Drawing a story out of an author who "has nothing to say" is linkedin-story-interviewer; turning an article, talk or thread into posts is linkedin-content-repurposer; deciding what to post this month is linkedin-content-planner. Comments and replies (linkedin-comment-writer, linkedin-reply-manager, linkedin-thread-tracker), profile copy (linkedin-profile-optimizer), team programmes (linkedin-employee-advocacy) and performance review (linkedin-engagement-analytics) are separate skills. Everything here is offline: the skill produces text for the user to paste into LinkedIn themselves. It does not post, schedule, fetch, or call any service.

When to use this skill

• Someone asks for a LinkedIn post and has a topic but no angle
• A draft exists and the opening is not working
• An author has one good fact (a result, a mistake, a quote) and wants the post built around it
• A ghostwriter needs a repeatable way to brief, draft and check posts for several authors
• A draft is finished and needs a last mechanical check before it is pasted
• The same author keeps producing the same shape of post and wants a different one

Inputs the skill expects

• A brief: topic, one goal, the audience in a sentence (assets/post_brief_template.md)
• The author's material: any of a figure, a dated event, a scene, a changed belief, an opposing view, a before-and-after, a quote, a rule, a sample count, a question they were asked, a person to credit, a term to explain, a prediction, a list of steps
• Constraints: what must be included, what must not be named, preferred length
• Optional: a voice profile or two past posts, so the draft is in the author's register

Clarify First

Before drafting, confirm these inputs. If any is unknown or vague, ASK — do not assume:

• The one goal (conversation, saves, reshares, or inbound interest) — it changes which pattern ranks first and what the last line asks for; a post that tries for all four gets none
• What the author actually has — at least one concrete item of material; without it every pattern is locked and the only honest output is a question back to the author
• Who it is for — the same fact is written differently for peers, buyers and candidates; "everyone" produces a post for no one
• What cannot be said — client names, unreleased figures, people who have not agreed to be named; these decide whether a quote or a number can be used at all

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," use the material in the request as given, pick the top-ranked pattern, and list the assumed goal and audience at the top of the reply. If there is no material at all, ask the single unlock question for the pattern that best fits the topic; do not invent a figure to get started.

Workflows

Quick start: fill in the brief, run the picker, draft from the first option, run the gate.

Workflow 1 — From brief to angle

1. Fill in assets/post_brief_template.md with the author, or convert their notes into the JSON shape in assets/sample_brief.json. Leave a material field empty if the author does not have it.
2. Run the picker. It ranks only the patterns the material supports and lists the rest as locked, each with the question that would unlock it.
3. Read any caution lines. A counter-position or a prediction with no evidence behind it is an opinion; get the evidence or choose another pattern.
4. Offer the author the top two or three options in one line each. Let them choose; they know which one they are comfortable publishing.

python3 tools/linkedin/linkedin-post-writer/scripts/angle_picker.py \
  --input tools/linkedin/linkedin-post-writer/assets/sample_brief.json --top 3

Workflow 2 — Draft the post

1. Write the opening from the chosen pattern in references/opening-patterns.md. The agent writes it from the author's material and nothing else; the point of the line must land inside the first clause.
2. Write the second line so it works if the first is all the reader sees before expanding: add the stake, do not restate.
3. Build the body from the pattern's beats (references/post-structures.md). One beat per paragraph, each anchored to a fact. Cut any beat the author has no fact for.
4. Include the part that did not work. A post with no cost, exception or open question reads as an advertisement.
5. Close according to the goal: a question only a practitioner could answer, the last fact, or nothing. Never a stock ask.
6. Draft two alternative openings from the second-ranked pattern so the author has a real choice.

python3 tools/linkedin/linkedin-post-writer/scripts/angle_picker.py \
  --input tools/linkedin/linkedin-post-writer/assets/sample_brief.json \
  --top 5 --format json

Workflow 3 — Gate the draft before it is pasted

1. Save the draft as plain text with the line breaks it will have in the feed.
2. Run the gate. Blockers fail it outright; more than three warnings fail it.
3. Fix blockers first: a leftover placeholder or a stock closing line is never acceptable. Then work the warnings in the order shown.
4. Verify that every figure, name and quote in the draft appears in the brief, using the manual checklist in references/pre-publish-gate.md §4. The tool cannot do this part.
5. Re-run until the exit code is 0, then hand over the text with its character count. For a full style audit, pass the result to linkedin-humanizer.

python3 tools/linkedin/linkedin-post-writer/scripts/post_gate.py \
  --input tools/linkedin/linkedin-post-writer/assets/sample_draft.txt

python3 tools/linkedin/linkedin-post-writer/scripts/post_gate.py \
  --input tools/linkedin/linkedin-post-writer/assets/sample_draft_revised.txt

The first sample fails with two blockers and three warnings. The revised version of the same post passes clean.

Decision frameworks

Pattern by material

The pattern is chosen by what the author has, then ranked by goal. Goal-fit scores are editorial heuristics, not measurements.