asset-provenance-audit
Skill4 starsChanged 3 months agoMITView on GitHub
Audit website images, videos, models, textures, audio, generated media, and VFX for source records, commercial rights, attribution, manifests, and secret-safe public documentation.
In this repository26 other files it gives its agents.
- aigentSkill
- aigent-3d-scroll-systemSkill
- aigent-asset-gallery-systemSkill
- aigent-business-sitesSkill
- aigent-designSkill
- aigent-landing-page-polishSkill
- cinematic-asset-gallerySkill
- cinematic-site-qaSkill
- cinematic-studioSkill
- cinematic-web-directorSkill
- creative-asset-directorSkill
- design-forensicsSkill
- design-resolverSkill
- gsap-scroll-choreographySkill
- hyperframes-videoSkill
- inspiration-originality-auditSkill
- modular-scroll-pageSkill
- publish-siteSkill
- reference-synthesisSkill
- remotion-web-assetsSkill
- spline-web-sceneSkill
- threejs-web-sceneSkill
- video-asset-pipelineSkill
- video-scrub-deckSkill
- visual-design-criticSkill
- web-3d-asset-pipelineSkill
The file
Files
Asset Provenance Audit
Read:
creative-production/standards/provenance.mdassets/manifests/asset-manifest.schema.jsoncreative-production/catalog.json
For every asset
Verify:
- source type
- provider or creator
- exact source URL
- exact license or active plan class
- commercial-use status
- attribution requirement
- verification date
- safe receipt or generation reference
- production edits
- public outputs
- mobile and reduced-motion variants
- budget overrides
Block release when
- commercial use is unresolved
- required attribution is absent
- a free-plan generation is assumed to inherit later paid rights
- a marketplace summary replaces the item license
- a source asset is redistributed as a competing standalone asset
- the repository contains API keys, signed URLs, personal billing data, or confidential paths
Run
npm run assets
npm run catalogsThe script checks structure and public-file safety. It cannot make a legal judgment. Escalate restricted, geographic, enterprise, trademark, likeness, or editorial-use questions.
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.