agentleFS
timscheueraitimscheuerai/gtm-architecture-template/.agents/skills/linkedin-copywriter/SKILL.md

linkedin-copywriter

Skill2 starsChanged 2 months agoMITView on GitHub

Draft or edit one LinkedIn post using the author's context, writing samples, factual sources and intended funnel job.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read AGENTS.md, index.md, relevant identity and audience pages, identity/proof.md, voice/linkedin-voice.md, voice/formats.md and the …

    line 11
  2. Distinctive:

    Write an opening that the body can substantiate.

    line 19
  3. Distinctive:

    Check that each paragraph adds information.

    line 25
  4. Distinctive:

    Check every factual claim, quote, date and number against its source and public-use status.

    line 27
  5. Very specific:

    When saving to Notion is requested, follow strategy/notion-schema.md, fetch the configured destination and use templates/notion-content.md.

    line 35
  6. Distinctive:

    If Notion is unconfigured, deliver in chat and state it was not saved.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Workspace: all context paths below (identity, audience, strategy, voice, brand, raw, output, index, log, workspace preferences and context scripts) resolve from context/ in the kit root. Read both the root AGENTS.md and context/AGENTS.md. Skill-local references/ and flowchart scripts/ resolve from this skill directory.

Write a LinkedIn post

Read AGENTS.md, index.md, relevant identity and audience pages, identity/proof.md, voice/linkedin-voice.md, voice/formats.md and the selected pillar/funnel context. Read the full source behind the central claim.

Find the post

Identify one useful point, its source, the intended reader and the post's job. Work from the supplied brief and existing context; ask for missing information only when it would change the substance. Do not invent a milestone, anecdote or customer quote to make an idea interesting.

Choose a structure that suits the material: a sequence for a process, a story for a real change, evidence for a claim, or a comparison for a decision. Do not force every post into one house format.

Write an opening that the body can substantiate. Prefer a specific observation over manufactured suspense. Use the author's actual rhythm and vocabulary. Do not add slang, self-deprecation, deliberate mistakes, dramatic reversals or numeric claims just to sound human.

A stub voice page does not block useful editing of a supplied draft. Preserve the user's wording and use plain language, while being clear that the voice has not yet been calibrated.

Edit for substance

Check that each paragraph adds information. Cut generic praise, unsupported superlatives, repeated morals, empty transitions and slogan-like conclusions. Keep necessary explanations and qualifications. Read the opening, paragraph starts and ending together: the argument should remain understandable.

Check every factual claim, quote, date and number against its source and public-use status. Keep reported results, targets and illustrative examples distinct. Use a CTA only when it fits the chosen funnel job and a real available offer.

For repurposing, select one argument from the source rather than compressing the entire source into a post. For revisions, address the user's requested changes first and preserve their facts and meaningful phrasing.

Deliver or save

Return one paste-ready draft, brief source notes and any material uncertainty. Offer alternate hooks only when useful or requested. Do not put process commentary inside the copy.

When saving to Notion is requested, follow strategy/notion-schema.md, fetch the configured destination and use templates/notion-content.md. Set Status to Creating, one Pillar and the selected Platform. Add a Publish date only if a date is agreed. Check for the existing card before creating another.

If Notion is unconfigured, deliver in chat and state it was not saved. Never silently use another board. Saving a draft does not schedule or publish it.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.