virtual-crew
Skill1 starsChanged 36 days agoLicence not identifiedView on GitHub
Orchestrator for an AI film production crew. Stage A: extract the asset layer from the script and storyboard (character identities and variants, four directional views per location, props) into an asset document in the project folder. Stage B: per shot, route through continuity (world-state), art department (style + assets), QC (failure catalogue) and the ethics gate, then hold the two human gates (approve the prompt; judge the clip) and run the loop — look up shot → draft → approve → the director generates → watch-list → structured comparison → v(n+1) → approve/reject → write state back → log → triage the feedback into the owning skill. Use when starting an AI-generated film, when asked for asset prompts or a shot's prompt, or when a reported problem has to be classified and written into the skills. AIGC 短片制作的资产+镜头总调度，含两处人工确认与反馈归档。
In this repository6 other files it gives its agents.
- art-departmentSkill
- asset-forgeSkill
- continuity-supervisorSkill
- ethics-gateSkill
- line-producerSkill
- qc-reviewerSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
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.