agentsclimarketplace

Caption writer

Skill lumizone/social-content-os-claude-skill/skills/caption-writer

Claude Code skill pack that plans and produces social media content that performs: a tagged content calendar, scroll stopping hooks, rendered carousels, captions, and repurposing. Interest Graph playbook, zero AI artifacts.

Install
npx -y skills add lumizone/social-content-os-claude-skill --skill caption-writer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

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.

SKILL.md

2.6 KB, as published. Nobody here has run it

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".

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.