Conciseness

The body is dense and purpose-built: every step carries commands, gates, or constraints, and it never explains concepts Claude already knows. Minor trimmable redundancy keeps it off anchor 5 — the bpm/beats_sec trust caveat is restated in 'Two ideas that shape everything', again in Step 1, and again via Step 2's pacing, and Step 0's auth-status paragraph is a long digression. Not anchor 3: there is no padding or gratuitous explanation, only deliberate (if repeated) reinforcement.

Actionability

Fully executable throughout: copy-paste-ready commands for every step (`npx hyperframes init ... --non-interactive --example=blank`, the `pip install librosa numpy soundfile` fallback, `python3 <SKILL_DIR>/scripts/analyze-beatgrid.py ... -o ... --print`, `validate-plan.mjs`, `assemble-index.mjs`, the lint/validate/inspect chain, and the final `render ... -o renders/video.mp4 --fps 30`), plus a fully specified sub-agent dispatch context template with concrete placeholder semantics. This matches anchor 5's copy-paste-ready coverage of the common cases.

Workflow Clarity

Steps 0–6 are clearly sequenced with an explicit **Gate** checkpoint after each, user-approval gates at Steps 3 and 6, and machine validation with error-recovery feedback loops: 'Fix every `✗` (hard errors...)', 'a missing or blank frame file means that worker wrote a partial file; re-dispatch it (Step 4) and re-assemble', and install-on-import-failure at Step 1. The batch operation (one sub-agent per frame) is validated at Steps 4–6, and a Resume table handles mid-pipeline restarts — a full match to anchor 5.

Progressive Disclosure

Good structure overall: the body is an orchestrating overview, detailed material is split one level deep into `references/` and read exactly when needed ('Read [`references/frame-skeleton.md`](references/frame-skeleton.md)' at Step 2; the planning/template/montage references at Step 3), and a Quick Reference table maps each read to its step. It falls short of anchor 5 because `sub-agents/frame-worker.md` — referenced in Step 4, the Quick Reference, and the Directory layout — does not exist in the bundle, a broken in-bundle reference, and several cross-skill paths (`../hyperframes-core/...`, `../hyperframes-creative/...`) are unverifiable here. Not anchor 3: references are clearly signaled, one level deep, and the split is otherwise appropriate.

Specificity

The description lists several concrete pipeline 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 user media "cut into the frames on the same beat grid (beat-cut / ken-burns)" — which is well past the 1–2 actions of anchor 3. It stops short of anchor 5's comprehensive coverage because the downstream capabilities (assembly, verification, rendering to an MP4) are never mentioned, so the action list has minor gaps.

Completeness

It explicitly answers both questions with concrete trigger phrases: "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" (when) and the pipeline description of what the skill does with that track (what). This matches anchor 5; anchor 4 would require the 'when' to be less explicit, which it is not.

Trigger Term Quality

Good natural keyword coverage: "music track", "audio file", "video to pull audio from", "beat-synced", "lyric video, slideshow, kinetic promo", and "images or videos" — phrases a user would plausibly say. Missing common synonyms and extensions ("song", "music video" itself, ".mp3"), so it does not reach anchor 5's comprehensive synonym/extension coverage, but it is well above anchor 3's partial coverage.

Distinctiveness Conflict Risk

The niche is clear and the triggers are distinct: triggering is tied to possessing a music track and wanting a beat-synced video, with explicit boundary notes ("a complete video needs zero assets"; "the pipeline never branches on it" for genre). Minimal conflict risk with non-music video skills; not anchor 4, since the trigger conditions are sharply discriminating rather than merely 'mostly distinct'.