media-provenance-rights
Provider-independent provenance, rights, consent, disclosure, and release governance for AI-generated media. Use when producing or reviewing generated images, video, audio, ads, avatars, product content, social clips, documentaries, localization, music, sound, or campaign assets that need source-rights checks, model/provider term checks, likeness or voice consent, trademark/logo review, copyrighted-character/style risk triage, music licensing, C2PA/content credentials, provenance ledgers, release notes, platform disclosures, jurisdiction/client caveats, or rights QA.
Profile →npx skills add calesthio/generative-media-skills --skill media-provenance-rights --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Provides a governance workflow to identify rights evidence, missing permissions, disclosure duties, and escalation points for AI-generated media before client or platform release.
How it works
Treats evidence as three classes: Documented facts, Empirical observations, and Production heuristics. Emphasizes separating these evidence types and citing sources and verification dates for volatile facts. Requires creation of a rights map listing input, generated outputs, and final deliverables with fields such as asset_id, file_path, hash, role, source, license_or_permission, allowed_use, restrictions, AI_process, likeness_voice_identity, marks_logos_trade_dress, provenance_metadata, and review_status, along with reviewer and notes. For input/reference items, checks rights, licenses, and terms, differentiating CC licenses by BY/SA/NC/ND, and avoiding NC material in commercial contexts. Also covers provider/model terms checks, likeness/voice consent, and trademark/style considerations.
When to use it
Use when producing or reviewing assets across media (images, video, audio, ads, avatars, product content, social clips, etc.) that require source-rights checks, model/provider term checks, consent, disclosure, or rights QA. Rules emphasize not claiming clearance without documented basis and recording unknowns as blockers when information is missing.
What it can touch
Rights governance touches inputs, licenses, and release details, including C2PA/content credentials, provenance metadata, and platform disclosures as part of the release process. It requires documenting provenance and consent information within the rights map and release notes.
Caveats
Not legal advice; production governance workflow and evidence categories are provided for risk reduction. The skill notes that claims of clearance must be based on documented assumptions with dated caveats and highlights the need to distinguish provider terms from third-party rights in inputs, trademarks, likenesses, music, or outputs.
# Media provenance and rights governance Use this skill to make generated media releasable, auditable, and explainable. It is not legal advice. It is a production governance workflow that helps an agent identify rights evidence, missing permissions, disclosure duties, and escalation points before a client or platform receives the asset. Default posture: do not claim an asset is "cleared," "copyrig
What does the media-provenance-rights skill do?
Provider-independent provenance, rights, consent, disclosure, and release governance for AI-generated media. Use when producing or reviewing generated images, video, audio, ads, avatars, product content, social clips, documentaries, localization, music, sound, or campaign assets that need source-rights checks, model/provider term checks, likeness or voice consent, trademark/logo review, copyrighted-character/style risk triage, music licensing, C2PA/content credentials, provenance ledgers, release notes, platform disclosures, jurisdiction/client caveats, or rights QA.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill media-provenance-rights --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.