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

89%

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, action-dense body that uses progressive disclosure effectively via a verified navigation table and concrete commands. The main gaps are minor: a few verbose passages, placeholder flags without a full worked example, and no explicit validate→fix→retry loop for treatment workflows.

Dimension	Reasoning	Score
Conciseness	Dense and assumes Claude's competence (no explaining what a LUT/BGM is), but the inline "Rules that keep this a help, not nagware" parenthetical definitions and editorial lines like "The human usually can't tell which media would lift the piece. You can." could be trimmed. Not 5 because of these minor over-explanation spots; not 3 because almost every token is actionable instruction.	4 / 5
Actionability	Concrete executable commands throughout — `node <SKILL_DIR>/scripts/resolve.mjs --type <type> --intent "<description>" --project <dir>`, `--doctor`, `--candidates`, `hyperframes media-treatment --capabilities --json`, `--selector '#hero' --analyze --json` — plus a stated return format. Not 5 because some flags use placeholders (`--for ...`) and there is no complete end-to-end worked input→output example.	4 / 5
Workflow Clarity	Clear escalating workflow with inspection checkpoints ("inspect one after-sheet", escalate "only when the result is ambiguous, temporal, stylized...") and "deterministic persistence and verification", so the destructive/batch cap does not apply. Not 5 because there is no explicit validate→fix→retry error-recovery loop or checklist.	4 / 5
Progressive Disclosure	Clear overview with a well-signaled one-level-deep navigation table ("read only the file your task needs") mapping tasks to references; all 8 referenced files and resolve.mjs verified to exist, content appropriately split. Not 4 because the structure is exemplary with easy navigation, not merely 'good with minor gaps'.	5 / 5
	Total	17 / 20 Passed

Description

100%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.

An exemplary description: comprehensive concrete actions, vivid natural-language triggers, an explicit when-clause, and a distinctive niche with minimal conflict risk. It assumes no generic overlap and tells the model exactly when to fire.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with comprehensive coverage: "Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT", "generate via TTS / music / image models", "produce voiceover, transcription, captions, and background removal", "operate on media (cut / reframe / transform)", "reuse assets".	5 / 5
Completeness	Explicitly answers both: what (resolve / generate / produce / operate / reuse) and when ("Also use for vague feedback that real footage looks dark, flat, boring...") with concrete trigger phrases. Not 4 because the 'when' is fully explicit, not just implied or improvable.	5 / 5
Trigger Term Quality	Rich natural trigger phrases a user would actually say — "looks dark, flat, boring", "should feel retro/camcorder/print/ASCII", "needs privacy", "needs a media reveal" — with synonym coverage for aesthetic intent. Hits the top anchor; not 4 because keyword coverage is comprehensive, not merely good.	5 / 5
Distinctiveness Conflict Risk	Clear niche — "every media need in a HyperFrames project" anchored on one verb `resolve` — with distinctive triggers (retro/camcorder/print/ASCII looks, media reveal) and minimal overlap risk. Not 4 because it is a distinct niche, not merely 'mostly distinct'.	5 / 5
	Total	20 / 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: a562946

Reviewed: about 9 hours 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.