CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 strong, highly actionable body: executable commands, verified reference routing, and explicit ordering checkpoints. The main improvement areas are trimming the repetition in the Preflight and credential-switch sections and consolidating the multi-step flow into a single sequenced overview with error-recovery guidance.

Suggestions

Consolidate the Preflight section: the sign-in recommendation and the STOP-and-wait instruction are each stated across multiple bullets — state them once to cut redundant tokens (conciseness).

The credential-fallback switch appears twice — in the engine's capability table and again in Provider chains — merge or cross-reference one of them (conciseness).

Add a brief ordered end-to-end flow (preflight → audio_request.json → audio.mjs → wait-bgm → assemble → captions) plus what to do when an engine run fails, so the sequence doesn't have to be synthesized from scattered sections (workflow_clarity).

DimensionReasoningScore

Conciseness

The body is dense, table-driven, and entirely project-specific — no generic-concept padding. However, the Preflight section repeats its sign-in recommendation and STOP instruction across multiple bullets, and the credential-fallback switch is stated twice (engine table and Provider chains section). Not 5 because these redundancies could be trimmed; not 3 because virtually every other token earns its place.

4 / 5

Actionability

Copy-paste ready commands cover the main paths: 'node <MEDIA_DIR>/scripts/audio.mjs --request ./audio_request.json --hyperframes . --out ./audio_meta.json', 'npx hyperframes auth status --json', plus exact request/output JSON shapes and a routing table pointing to real files. Specific examples cover the common cases with no meaningful gaps.

5 / 5

Workflow Clarity

Ordering is explicit ('Always run this before generating voice or BGM', 'run scripts/wait-bgm.mjs before assembling') with real checkpoints ('exit 1 is expected here', 'bgm_pending: true', --json branching). Not 5: the end-to-end flow is distributed across sections rather than given as one sequenced overview, and there is no error-recovery guidance for a failed engine run.

4 / 5

Progressive Disclosure

A routing table maps each task to a verified, one-level-deep reference file (all referenced paths exist in the bundle), while bulk detail — full flags, the audio_meta.json schema, provider specifics — is correctly deferred to the scripts/audio.mjs header and references/*. The overview/split is essentially ideal.

5 / 5

Total

18

/

20

Passed

Description

96%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 excellent description: comprehensive concrete capabilities, natural synonym-rich trigger coverage, and explicit what/when structure in third person. The only weakness is that 'background removal' and 'transcription' are generic enough to create minor conflict risk with adjacent skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities with named specifics — 'multi-provider TTS (HeyGen / ElevenLabs / Kokoro local)', 'Whisper transcription, background removal, and caption authoring', plus the exact fallback chain ('local Lyria / MusicGen BGM generation and a bundled SFX library'). Coverage is comprehensive rather than leaving minor gaps.

5 / 5

Completeness

The first sentence explicitly states what the skill does, and the explicit 'Use for voiceover / TTS, BGM, SFX / sound effects, transcription, captions / subtitles...' clause answers when to invoke it with concrete trigger phrases. Both halves are explicit, not implied.

5 / 5

Trigger Term Quality

It pairs natural synonyms users would actually say: 'voiceover / TTS', 'SFX / sound effects', 'captions / subtitles / lyrics / karaoke / per-word styling', 'voice + provider selection', and 'music-mood prompting'. Common variations are comprehensively covered.

5 / 5

Distinctiveness Conflict Risk

'Audio and media assets for HyperFrames compositions' carves a clear niche, but the generic trigger terms 'background removal' and 'transcription' overlap with image-editing and dedicated transcription skills. Mostly distinct with minor overlap risk, not minimal.

4 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.