agentleFS
alisonnnfreitasssalisonnnfreitasss/studio-3d/.claude/skills/open-studio/SKILL.md

open-studio

Skill4 starsChanged 16 days agoMITView on GitHub

Open Studio 3D in the browser and link this chat to its page, so requests sent from the page wake this chat and it answers on the page. Use when the person says "open the studio" or "abre o estúdio".

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If studio/characters/lead/character.json does not exist, run setup-studio first.

    line 8
  2. Very specific:

    Listen: run python3 tools/listen.py --wait as a background task.

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Open the studio and listen

If studio/characters/lead/character.json does not exist, run setup-studio first. Work from studio/.

  1. Start the hub if it is off. curl -s -m2 -o /dev/null -w "%{http_code}" http://127.0.0.1:8810/api/requests; if not 200, run python3 server/serve.py in the background. Never kill anything else on a port.
  2. Open the page: open "http://127.0.0.1:8810/#/explainers".
  3. Listen: run python3 tools/listen.py --wait as a background task. Its exit wakes this chat with one request as JSON. Exit code 3 means another chat is listening: say so.
  4. For each request: where says which page they were on; text is what they want. Run python3 tools/listen.py working <id> "<short update>" as you go. A reel lives in explainers/<slug>/: edit its code, then python3 ../kit/runner/explainer.py rerender explainers/<slug> for a new render and every check. Finish with python3 tools/listen.py done <id> "<what changed>" or failed <id> "<why>", in plain words. Then listen again.
  5. Stopping: python3 tools/listen.py stop.

Anything that spends money needs a clear yes first. Never press approve buttons for them. Test videos stay 5 to 10 seconds. If a request is unclear, answer on the page: done <id> "Question: ...".

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.