agentleFS
Sign inStart free
lumizonelumizone/social-content-os-claude-skill/skills/caption-writer/SKILL.md

caption-writer

Skill0 starsChanged 5 months agoMITView on GitHub

Write captions, standalone Instagram/LinkedIn/X posts, and CTAs. Use when the user wants a caption, a post body, a LinkedIn post, a tweet/thread, or a call-to-action, or says "napisz caption", "opis pod reels", "post na linkedin", "napisz posta", "write a caption", "linkedin post", "write the CTA", "thread on X". Uses the 6 caption types (relatable story, tool list, surprising fact, before/after, simple question, educational body) and PAS / BAB skeletons for text posts, one-idea-one-post, scannable, with an ABC close and a low-friction ManyChat comment-trigger CTA. Produces multiple variants.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. stevenflanagan1/social-ai-team★ 216same name
    2. duncan-buildroom/freeskills★ 65same 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 repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Distinctive:

    No AI tells: no em-dashes, no en-dashes, no smart quotes, no "unlock/unleash/elevate/dive in/in today's fast-paced world".

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

caption-writer

Turn an idea (or a carousel/hook you already have) into finished caption and post copy. Default output: English. Match the recipient's language if the target audience is non-English. Reference: caption types + PAS/BAB + ABC close + ManyChat in ../social-content-os/reference/frameworks.md §3, §8, §11. Load ../social-content-os/brand.json for voice and the comment-trigger WORD.

Inputs

  • The idea or the asset it accompanies (carousel topic, Reel, hook).
  • Platform: Instagram caption, LinkedIn post, X post/thread.
  • Funnel job: ToF (reach), MoF (trust), or BoF (offer) — sets the CTA aggressiveness.

Method

  • Open with the hook. First line = the scroll-stopper (pull from hook-lab if available). On LinkedIn the first two lines must clarify the topic and trigger a personal concern, because the rest is hidden behind "see more".
  • Pick the structure:
    • Instagram caption → one of the 6 caption types that fits the idea.
    • LinkedIn / text post → PAS (Problem, Agitate, Solution) or BAB (Before, After, Bridge). One idea only.
    • X → either a single sharp post or a thread (hook post + 3–6 beats + CTA post).
  • Write for scanning: short sentences, line breaks, no jargon, no walls of text.
  • Close with ABC: one clear, low-friction CTA. For ToF/MoF default to the comment-trigger ("Comment WORD and I'll DM you ...") so ManyChat can do the handshake. For BoF, a direct offer/link CTA.
  • Hashtags: 3–6 relevant, specific (niche + topic), never 30 generic ones.

Output

Produce 3 variants using different angles (e.g. story vs fact vs question) so the user can A/B test:

  1. Variant A, B, C — each labeled with its caption type / framework.
  2. For each: the body copy, the CTA line, and a short hashtag set.
  3. A one-line note on which variant to lead with for the stated funnel job and why.

No AI tells: no em-dashes, no en-dashes, no smart quotes, no "unlock/unleash/elevate/dive in/in today's fast-paced world".

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.

Check your setup, free