apod-to-short
Skill10 starsChanged 7 months agoApache-2.0View on GitHub
Turn a NASA Astronomy Picture of the Day (APOD) into a 30–60s vertical short — script, shot list, captions, and a rights line. Use when the user mentions APOD, 'astronomy picture of the day', or wants a daily space short/reel/TikTok from a NASA image.
Files
APOD → Short
NASA Astronomy Picture of the Day → a ready-to-shoot 30–60s vertical short.
Purpose
NASA publishes a stunning image with an expert explanation every day. This skill converts one APOD entry into a complete vertical short package: a hook, a tight narration script, an on-screen caption track, a shot/animation list, and a rights line — so a creator can film/edit in one sitting without misstating the science or the licensing.
When it fires
- Keyword triggers:
apod,astronomy picture of the day,daily space short,nasa image short,space reel - File triggers:
apod.json,apod-*.md - Command triggers:
/apod-to-short
Inputs
| Input | Required | Notes |
apod | yes | APOD URL/date, or the title + explanation text + image credit. |
length | no | Target seconds, default 45 (range 30–60). |
voice | no | starlight (default), arcanea, or frankx — see brand skills. |
Workflow
- Resolve the APOD — get title, date, explanation, media URL, and the exact image credit. If credit names a non-NASA party (ESA, an observatory, an individual), flag it for the rights step. ✅ Check: you have a verbatim credit string.
- Extract the one idea — reduce the explanation to a single, true, surprising fact a non-expert can grasp. ✅ Check: it survives "what does that mean specifically?"
- Write the hook (0–3s) — a question or claim that earns the first three seconds without clickbaiting the science.
- Script the body — narration timed to
lengthat ~2.5 words/sec. Keep every claim traceable to the explanation; never invent figures. - Build the caption track — short on-screen lines synced to beats (≤7 words each).
- Write the shot list — Ken Burns push/pan on the still, plus any overlay labels (object name, distance, instrument). No fabricated footage.
- Emit the rights line — exact attribution; route through
rights-check-nasa-esaif credit is non-NASA.
Output contract
{
"title": "string — APOD title",
"hook": "string — 0–3s opener",
"script": "string — full narration, timed",
"captions": ["string — ≤7 words each"],
"shot_list": ["string — shot/animation directions"],
"rights_line": "string — exact attribution",
"duration_sec": "number"
}Tools & MCP
- Tools:
WebFetch(resolve APOD),Read. - MCP dependencies: none required. (Optional: a NASA-media MCP from
starlight-mcpto fetch APOD JSON directly.)
Quality bar
- Every stated fact is traceable to the APOD explanation — no invented numbers.
- Rights line is verbatim and correct; non-NASA credit is flagged.
- Narration fits
lengthat ~2.5 words/sec. - Hook respects the audience's intelligence (no "scientists HATE this").
Example
See examples/example-01.md.
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
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- frankxai/starlight-agent-skills★ 299% same
Wrote their own version · 0
None found.
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 repository131 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/commands/monitoring/agents.mdAGENTS.md
- .claude/skills/gstack/AGENTS.mdAGENTS.md
- .claude/agents/CLAUDE.mdCLAUDE.md
- .claude/commands/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- .claude/skills/agentic-orchestration/CLAUDE.mdCLAUDE.md
- .claude/skills/cacos/CLAUDE.mdCLAUDE.md
- .claude/skills/CLAUDE.mdCLAUDE.md
- .claude/skills/frankx-daily-execution/CLAUDE.mdCLAUDE.md
- .claude/skills/gstack/CLAUDE.mdCLAUDE.md
- .claude/skills/memory-guardian/CLAUDE.mdCLAUDE.md
- .claude/skills/newsletter/CLAUDE.mdCLAUDE.md
- .claude/skills/oci-services-expert/CLAUDE.mdCLAUDE.md
- .claude/skills/oracle-ai-architect/CLAUDE.mdCLAUDE.md
- .claude/skills/oracle-diagram-generator/CLAUDE.mdCLAUDE.md
- .claude/skills/research/CLAUDE.mdCLAUDE.md
- .claude/skills/swarm-advanced/CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- drafts/CLAUDE.mdCLAUDE.md
- hub-generator/CLAUDE.mdCLAUDE.md
- instances/CLAUDE.mdCLAUDE.md
- mcp-servers/CLAUDE.mdCLAUDE.md
- outputs/CLAUDE.mdCLAUDE.md
- scripts/CLAUDE.mdCLAUDE.md
- skills/CLAUDE.mdCLAUDE.md
- templates/CLAUDE.mdCLAUDE.md
- workflows/CLAUDE.mdCLAUDE.md
- acos-metaSkill
- agentic-jujutsuSkill
- agentic-orchestrationSkill
- AI Architect NewsletterSkill
- ai-architectureSkill
- algorithmic-artSkill
- arxiv-space-paper-to-briefSkill
- book-publishingSkill
- brand-guidelinesSkill
- brand-voiceSkill
- cacosSkill
- canvas-designSkill
- Claude SDK ExpertSkill
- cosmic-mythic-overlaySkill
- creator-productivitySkill
- descript-operatorSkill
- doc-coauthoringSkill
- docxSkill
- excellence-book-writingSkill
- Framer ExpertSkill
- frankx-brandSkill
- FrankX Daily Execution SystemSkill
- frontend-designSkill
- game-developmentSkill
- github-code-reviewSkill
- github-multi-repoSkill
- github-project-managementSkill
- github-release-managementSkill
- github-workflow-automationSkill
- Greek PhilosopherSkill
- grok-harnessSkill
- gstackSkill
- The first 60 shown.
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
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.

