music-to-video

Use when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting. The music drives everything: one analyzer reads it once, the orchestrator lays out the frames and fills a per-frame plan, and one sub-agent builds each frame. Typography and templates are the floor — a complete video needs zero assets — but any images or videos the user supplies are cut into the frames on the same beat grid (beat-cut / ken-burns). The genre (lyric video, slideshow, kinetic promo) falls out of the per-frame choices; the pipeline never branches on it.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

77%

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

A well-engineered workflow body: sequenced steps with gates, executable commands, and clear reference navigation. The main gaps are a missing core bundle file that Step 4 depends on, and some restated guidance that could be tightened.

Suggestions

Add the missing `sub-agents/frame-worker.md` and `references/bgm.md` to the bundle — Step 4 fully delegates to frame-worker.md and the Directory layout section lists it, but neither file exists, so the skill's own referenced navigation is broken.

Tighten the 'trust the analyzer' rule, which is restated in Step 0, Step 1, and the 'Two ideas' section, and condense the Step 0 `npx hyperframes auth status` relay prose to reduce redundancy.

Verify the cross-skill paths (`../hyperframes-core/references/subagent-dispatch.md`, `../hyperframes-creative/references/design-spec.md`, `../hyperframes-creative/frame-presets/`) resolve in the deployed plugin, or call out that dependency explicitly so the references aren't dead links in isolation.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept-explanation fluff, but the 'trust the analyzer' rule is restated across Step 0, Step 1, and 'Two ideas', and Step 0's auth-relay prose is dense — fitting 'mostly efficient but could be tightened' rather than the lean level-3 anchor.	2 / 3
Actionability	Provides fully executable, copy-paste commands throughout — `npx hyperframes init`, `python3 .../analyze-beatgrid.py`, `node .../validate-plan.mjs`, `node .../assemble-index.mjs`, and the lint/validate/inspect/render chain — matching the level-3 anchor.	3 / 3
Workflow Clarity	Steps 0–6 are explicitly sequenced with a Gate checkpoint after each, feedback loops ('Fix every ✗', 're-dispatch it ... and re-assemble'), and a resume table, satisfying the clear-sequence-with-validation level-3 anchor.	3 / 3
Progressive Disclosure	Structure is well-signaled with one-level-deep references and a Read/When navigation table, but the core referenced file `sub-agents/frame-worker.md` (and `references/bgm.md`) do not exist in the bundle despite being listed in the directory layout — broken navigation caps this below the level-3 'easy navigation' bar.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 description with an explicit 'Use when' trigger, several concrete capabilities, and a distinctive niche. Its only weakness is density — the internal pipeline mechanics (orchestrator, per-frame plan, sub-agent) are implementation detail that pads the description without adding user-facing trigger value.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "one analyzer reads it once, the orchestrator lays out the frames and fills a per-frame plan, and one sub-agent builds each frame" and media "cut into the frames on the same beat grid (beat-cut / ken-burns)" — matching the level-3 anchor rather than the domain-only level-2 example.	3 / 3
Completeness	Explicitly answers both: the trigger clause "Use when the user has a music track ... and wants a beat-synced HyperFrames video" (when) plus the analyzer/orchestrator/sub-agent pipeline (what), clearing the level-3 bar that level-2 misses by omitting the trigger.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — "music track", "audio file", "beat-synced", "lyric video", "slideshow", "kinetic promo" — giving good coverage rather than the partial level-2 set.	3 / 3
Distinctiveness Conflict Risk	The niche is tight — a beat-synced HyperFrames video driven by one music track with a fixed non-branching pipeline — making it unlikely to fire for unrelated video skills; this is the clear-niche level-3 case, not the overlapping level-2 one.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	14 / 16 Passed

Repository: calesthio/OpenMontage
Path: .agents/skills/music-to-video/SKILL.md
Commit: 0af32ce

Reviewed: 1 day 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.