agentleFS
Starlight-IntelligenceStarlight-Intelligence/starlight-agent-skills/skills/media/caption-and-hashtag/SKILL.md

caption-and-hashtag

Skill1 starsChanged 4 months agoMITView on GitHub

Write a platform-tuned caption plus a researched, non-spammy hashtag set for a post. Use when finishing a social post, asked for 'caption and hashtags', or optimizing reach for Instagram/TikTok/X/LinkedIn.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Caption & Hashtag

A post's subject → a platform-tuned caption + a tiered hashtag set.

Purpose

Captions and hashtags are where reach is won or wasted. This skill writes a caption that fits the platform's voice and produces a tiered hashtag set (broad / niche / branded) that's relevant rather than spammy — calibrated to the platform's norms.

When it fires

  • Keyword triggers: caption, hashtags, caption and hashtags, tags for post
  • File triggers: posts/**
  • Command triggers: /caption-and-hashtag

Inputs

InputRequiredNotes
subjectyesWhat the post is about (+ any link/credit).
platformyesinstagram, tiktok, x, linkedin.
voicenostarlight (default), arcanea, frankx.

Workflow

  1. Caption — hook line + value + optional CTA, sized to the platform (IG/TikTok short; LinkedIn longer; X terse). ✅ Check: fits platform length norms.
  2. Hashtag tiers — broad (reach), niche (relevance), branded (identity). Count per platform norm (IG ~8–12; TikTok ~3–5; X ~1–3; LinkedIn ~3–5).
  3. Relevance + safety pass — drop spammy/banned/irrelevant tags; keep facts true.
  4. Carry credit — include any required image credit.

Output contract

{
  "caption": "string",
  "hashtags": { "broad": ["string"], "niche": ["string"], "branded": ["string"] },
  "platform": "string"
}

Tools & MCP

  • Tools: Read, optional WebSearch for trending tags. MCP: none required.

Quality bar

  • Hashtag count matches the platform norm; no spam/banned tags.
  • Caption length and tone fit the platform.
  • Claims true; credit carried if needed.

Example

Input: "Webb image of the Carina Nebula", platform instagram → a caption + ~10 tiered hashtags, credit line included.


Built on SIP — Starlight Intelligence Protocol Substrate: starlightintelligence.org/protocol v1.1.0 Layers used: [file-contract, attestation, sovereignty] Vertical: starlight-agent-skills · portable capability layer

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.