media-use

Agent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + ledger record (one verb, `resolve`); generate via TTS / music / image models when the catalog misses; produce voiceover, transcription, captions, and background removal through one shared audio engine; operate on media (cut / reframe / transform); and reuse assets across projects. Also use for vague feedback that real footage looks dark, flat, boring, should feel retro/camcorder/print/ASCII, needs privacy, or needs a media reveal.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured operational overview: executable commands, an escalating treatment workflow with real checkpoints, and an exemplary task→reference navigation table. It leans slightly instructional in the treatments section and delegates some workflow detail to references rather than spelling out full end-to-end sequences.

Suggestions

Tighten the 'Treat broad visual feedback' paragraph into a short checklist or table so it reads as executable guidance rather than a prose block (improves conciseness and actionability).

Add a one-line end-to-end resolve→operate→reuse sequence (e.g. resolve → verify the returned path → optionally operate → ledger records it) so the multi-step path is explicit in SKILL.md rather than implied across references.

Reference the two currently-unlinked bundle files (media-treatment-recipes.md, telemetry-dashboard.md) in the 'Where to look' table, or note they are reached via other references, so every bundle file is discoverable from the overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational (tables, command blocks, terse rules) and assumes Claude's competence, but the Treat broad visual feedback section is a dense paragraph block that could be tightened, so it sits at 'efficient with minor instances to trim' rather than the fully-lean anchor at 5.	4 / 5
Actionability	Provides concrete executable commands ('node <SKILL_DIR>/scripts/resolve.mjs --type <type> --intent …', 'hyperframes media-treatment --capabilities --json', '--selector '#hero' --analyze --json') covering common cases, but the treatments section mixes in instructional prose ('choose one primary intent', 'compose correction, a preset, finishing…') that is not purely copy-paste, keeping it just below the fully-executable anchor at 5.	4 / 5
Workflow Clarity	A clear escalating workflow with checkpoints (inspect one contact sheet, apply one candidate, inspect one after-sheet, 'escalate … only when the result is ambiguous') plus a --doctor verify step and 'surface, never silently mutate'; the end-to-end resolve→operate flow and the cut/reframe/transform path are delegated to references, leaving minor gaps versus the explicit-validation-checklist anchor at 5.	4 / 5
Progressive Disclosure	The body is an overview with a 'Where to look' task→file table pointing one level deep to references/resolve.md, grading.md, audio.md, operations.md, media-treatments.md, setup-providers.md, memory.md, and meta.md — all verified to exist — matching the clear-overview, well-signaled, easy-navigation anchor; two unreferenced bundle files (media-treatment-recipes.md, telemetry-dashboard.md) are a negligible gap.	5 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A dense, capability-rich description that pairs a comprehensive 'what' with an explicit, naturally-worded 'use for' trigger clause. It is slightly jargon-heavy (BGM/SFX/LUT) but otherwise highly specific and clearly scoped.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions across all media types — 'Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + ledger record', 'produce voiceover, transcription, captions, and background removal', 'operate on media (cut / reframe / transform)' — which matches the comprehensive-coverage anchor, not the minor-gaps anchor at 4.	5 / 5
Completeness	Explicitly answers what (resolve/generate/produce/operate/reuse) and when via 'Also use for vague feedback that real footage looks dark, flat, boring… or needs a media reveal', matching the anchor that requires both with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger phrasing for the feedback case ('looks dark, flat, boring', 'should feel retro/camcorder/print/ASCII', 'needs a media reveal') plus 'voiceover, transcription, captions', but several core terms are jargon (BGM, SFX, LUT) rather than the plain synonyms users say, so it sits just below the comprehensive anchor at 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to 'every media need in a HyperFrames project' with distinctive vague-feedback triggers (retro/camcorder/print/ASCII, privacy, media reveal), giving a clear niche and minimal conflict risk; not the minor-overlap anchor at 4.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: heygen-com/hyperframes
Path: skills/media-use/SKILL.md
Commit: 0f8eb89

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.