generated-media-qa
Provider-independent quality assurance for AI-generated and AI-assisted media. Use when reviewing, accepting, revising, or reporting on images, video, audio, avatars, ads, product content, social clips, explainers, localization, mixed-source edits, captions, accessibility, provenance, model metadata, safety/policy, and delivery readiness.
Profile →npx skills add calesthio/generative-media-skills --skill generated-media-qa --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
Judges the deliverable against the approved brief, platform specifications, legal/safety constraints, and audience context. Requires recording enough evidence so another agent can reproduce the decision.
How it works
- Creates three evidence lanes: Documented facts (brief/platform/legal), Empirical observations (measured asset properties and defects), and Production heuristics (professional judgments).
- Requires an intake phase to collect briefs, delivery specs, source inventory, generation metadata, and risk context before review.
- Establishes an acceptance matrix across: Brief conformance, Technical delivery, Generated-media realism, Audio and speech, Accessibility, Rights and provenance, and Safety/policy.
- Performs sequential inspection starting from the acceptance frame; do not allow a single attractive frame to override a failed criterion.
- Includes language-alignment QA for textual content tied to metadata or descriptions, and distinguishes it from pixel/audio quality.
- Applies Technical file QA checks for file integrity, streams, visual/audio defects, and versioning; references broadcast models as guidance but notes not universal requirements for all deliveries.
- Provides specialized QA domains for Visual/motion, Audio/loudness/intelligibility, Captions/accessibility/viewer safety, and Rights/provenance/disclosure checks.
- Documents facts: provenance, licenses, model/provider metadata, synthetic disclosures, and source rights; ensures metadata handling and disclosures per platform/policy guidance.
When to use it
Use when reviewing, accepting, revising, or reporting on AI-generated or AI-assisted media across formats (images, video, audio, avatars, captions, localization, etc.).
What it can touch
Contains guidance on sources, metadata, and disclosures; specifies intake data and provenance metadata requirements (C2PA, IPTC Digital Source Type, Google/YouTube guidance, FTC disclosures). Tools listed in frontmatter (claude-code, codex, copilot, cursor) are the intended agent interfaces for execution.
Caveats
Depends on platform-specific guidance and licensing; emphasizes that platform requirements can be volatile and must be consulted (e.g., IPTC, C2PA, YouTube disclosures, Netflix guidance). It does not guarantee delivery outcomes beyond documented verification and evidence collection.
# Generated Media QA Treat QA as a release decision, not a vibe check. Judge the deliverable against the approved brief, platform specifications, legal/safety constraints, and the audience context. Record enough evidence that another agent or producer can reproduce the decision. ## Keep three evidence lanes separate Documented facts are requirements from the brief, platform specs, legal/policy gui
What does the generated-media-qa skill do?
Provider-independent quality assurance for AI-generated and AI-assisted media. Use when reviewing, accepting, revising, or reporting on images, video, audio, avatars, ads, product content, social clips, explainers, localization, mixed-source edits, captions, accessibility, provenance, model metadata, safety/policy, and delivery readiness.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill generated-media-qa --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.