agentleFS
Sign inStart free
Starlight-IntelligenceStarlight-Intelligence/starlight-agent-skills/skills/media/rocket-launch-to-youtube/SKILL.md

rocket-launch-to-youtube

Skill1 starsChanged 4 months agoMITView on GitHub

Turn a rocket launch (mission details + footage notes) into a full YouTube package — title options, description, chapters, tags, and a long-form script. Use when producing a launch recap/explainer video, or asked to 'make a YouTube video about this launch'.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Create a free account to mount
Files
SKILL.md

Rocket Launch → YouTube

A launch + its facts → a complete long-form YouTube package.

Purpose

Launches are high-interest events that reward fast, accurate long-form coverage. This skill assembles the full YouTube package — clickable-but-honest titles, a structured description with timestamps, tags, and a narrated script — grounded in verified mission facts.

When it fires

  • Keyword triggers: rocket launch, youtube video, launch recap, mission video, long-form script
  • File triggers: videos/**, *.script.md
  • Command triggers: /rocket-launch-to-youtube

Inputs

InputRequiredNotes
missionyesVehicle, payload, provider, date, outcome (+ source).
footagenoNotes on available clips/segments for chapters.
lengthnoTarget minutes, default 8.

Workflow

  1. Verify mission facts — vehicle, payload, provider, date, outcome from a cited source. ✅ Check: outcome confirmed, not assumed.
  2. Title options — 3–5, accurate and compelling (no false drama).
  3. Script — intro hook → context → the launch beat-by-beat → significance → outro/CTA, timed to length.
  4. Chapters — timestamped sections matching the script/footage.
  5. Description — 2–3 paragraphs + chapter list + sources.
  6. Tags — relevant, non-spammy.
  7. Rights — credit any agency/provider footage used.

Output contract

{
  "titles": ["string"],
  "script": "string",
  "chapters": [{ "time": "string", "title": "string" }],
  "description": "string",
  "tags": ["string"],
  "rights_line": "string | null"
}

Tools & MCP

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

Quality bar

  • Mission outcome and facts are verified and cited.
  • Titles are honest — no fabricated stakes.
  • Chapters align with script timing.
  • Footage credit included where required.

Example

Input: "Falcon 9, Starlink batch, [date], nominal" + footage notes → titles, 8-min script, timestamped chapters, description with sources, tags.

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.

Check your setup, free