hyperframes-media

Audio and media assets for HyperFrames compositions, produced by one shared audio engine (`scripts/audio.mjs`) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound effects (HeyGen audio-library retrieval by default, with local Lyria / MusicGen BGM generation and a bundled SFX library as the no-credential fallback), Whisper transcription, background removal, and caption authoring. Use for voiceover / TTS, BGM, SFX / sound effects, transcription, captions / subtitles / lyrics / karaoke / per-word styling, voice + provider selection, and music-mood prompting.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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-architected skill body: executable entry point, an explicit preflight validation gate with recovery branches, and clean one-level-deep progressive disclosure to real reference files. The only weak spot is minor redundancy between the engine switch table and the Provider chains section, plus repeated emphasis in the Preflight.

Suggestions

Collapse the overlap between the 'audio engine' switch table and the 'Provider chains' tables — the TTS/BGM/SFX credential behavior is stated twice; keep one canonical table and cross-reference it.

Tighten the Preflight section: the 'STOP and wait for the user's choice / don't proceed past it on your own' guidance and 'relay output verbatim' instruction each recur; state each once.

The description already enumerates capabilities; consider whether the body's opening paragraph partially restates it and could be shortened to jump straight to the engine.

Dimension	Reasoning	Score
Conciseness	Dense with non-obvious operational gotchas (the Kokoro-only CLI bug, credential resolution order) rather than concepts Claude already knows, but the switch table is partly repeated in the Provider chains section and the Preflight section restates the 'STOP and wait' emphasis several times, so a little could be trimmed.	4 / 5
Actionability	Fully executable: a copy-paste `node <MEDIA_DIR>/scripts/audio.mjs --request ... --out ...` command, concrete `audio_request.json`/`audio_meta.json` schemas, `npx hyperframes auth status`, the `--only` merge flag, and `wait-bgm.mjs` for the detached-BGM case.	5 / 5
Workflow Clarity	Clear preflight gate sequenced before any generation, with explicit validation (`auth status` exit codes, `--json` for deterministic branching), an error-recovery branch when the CLI can't run, and the Non-negotiable rules acting as a checklist.	5 / 5
Progressive Disclosure	SKILL.md is a lean overview with a Routing table pointing to one-level-deep references (tts.md, bgm.md, sfx.md, transcribe.md, remove-background.md, tts-to-captions.md, captions/*.md, requirements.md) — all of which exist — with bulk schema/provider detail correctly deferred to the audio.mjs header and references.	5 / 5
	Total	19 / 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.

A strong, comprehensive description that names concrete capabilities, supplies rich natural trigger synonyms covering both 'what' and 'when', and stakes out a clearly distinct niche. It uses the conventional third-person/'Use for' trigger pattern matching the rubric's good examples.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound effects... Whisper transcription, background removal, and caption authoring' — with comprehensive coverage and no vague filler.	5 / 5
Completeness	Explicitly answers both 'what' (the enumerated capabilities) and 'when' via the 'Use for voiceover / TTS, BGM, SFX / sound effects, transcription, captions / subtitles / lyrics / karaoke...' trigger clause.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage with synonyms: 'voiceover / TTS, BGM, SFX / sound effects, transcription, captions / subtitles / lyrics / karaoke / per-word styling' — the phrases a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Scoped to 'Audio and media assets for HyperFrames compositions' with distinct, specific triggers (TTS/BGM/SFX/captions), giving it a clear niche and minimal overlap with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing, 4 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: calesthio/OpenMontage
Path: .agents/skills/hyperframes-media/SKILL.md
Commit: 08e2151

Reviewed: 2 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.