agentleFS
Starlight-IntelligenceStarlight-Intelligence/starlight-agent-skills/skills/cosmos/space-social-repurposer/SKILL.md

space-social-repurposer

Skill1 starsChanged 4 months agoMITView on GitHub

Repurpose a space asset (APOD short, mission brief, launch reel, atlas page) into a coordinated multi-platform pack, preserving image/footage credits across every variant. Use when distributing space content across X/LinkedIn/Instagram/YouTube while keeping NASA/ESA attribution intact.

2 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Space Social Repurposer

One space asset → a coordinated social pack, with credits carried everywhere.

Purpose

The space-tuned sibling of ../../media/social-repurposer. Same multi-platform distribution, with one critical addition: NASA/ESA/observatory image and footage credits are propagated to every variant that shows the media, so attribution never gets dropped in the repurposing.

When it fires

  • Keyword triggers: repurpose space, space social pack, distribute space content, cross-post nasa
  • File triggers: content/space/**
  • Command triggers: /space-social-repurposer

Inputs

InputRequiredNotes
sourceyesSpace asset + its credit/rights line.
platformsnoSubset of x, linkedin, instagram, youtube-short, newsletter. Default: all.
voicenostarlight (default), arcanea, frankx.

Workflow

  1. Lock facts + credit — capture the science and the verbatim credit; route rights questions through rights-check-nasa-esa. ✅ Check: credit string captured.
  2. Generate variants — X thread, LinkedIn, IG caption + hashtags, YouTube-short script, newsletter blurb — platform-native, facts consistent.
  3. Credit propagation — every variant that shows the media carries the credit.
  4. Consistency pass — facts agree across variants and with the source.

Output contract

{
  "core_message": "string",
  "x_thread": ["string"],
  "linkedin": "string",
  "instagram": { "caption": "string", "hashtags": ["string"] },
  "youtube_short": "string",
  "newsletter": "string",
  "rights_line": "string — propagated to all media variants"
}

Tools & MCP

  • Tools: Read, WebFetch. MCP: none required.

Quality bar

  • Credit line appears on every variant that shows the image/footage.
  • Facts identical across variants and true to source.
  • Each variant fits platform norms.

Example

Input: the APOD "Pillars of Creation" short (credit: NASA, ESA, CSA, STScI) → a full pack where the credit rides along on the X, LinkedIn, and Instagram variants.


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.