Conciseness

The body is largely lean and tool-specific — command blocks with inline comments, a compact flags table, and no explanation of concepts Claude already knows. It sits at the 4 anchor ('efficient; minor instances of over-explanation that could be trimmed') because a few passages repeat themselves slightly (e.g., the Studio-URL guidance across lines 76-88 restates the index.html-is-not-the-project point), rather than the 5 anchor where every token earns its place.

Actionability

Every section is copy-paste-ready executable commands with real flags, defaults, and concrete variants ('npx hyperframes inspect --at 1.5,4,7.25', 'transcribe subtitles.srt', 'tts "Text here" --voice af_nova'), plus a complete flags table for render. This matches the 5 anchor (fully executable, common cases covered) and exceeds 4 ('minor gaps') — the common cases for each subcommand are all shown.

Workflow Clarity

The workflow is an explicit numbered sequence (Scaffold → Write → Lint → Inspect → Preview → Render) with the ordering rule 'Lint and inspect before preview', and validation is built in: 'Errors should be fixed before rendering', '--strict'/'--strict-all' to fail on errors/warnings, and 'Run doctor first if rendering fails' for error recovery. This matches the 5 anchor (clear sequence, explicit validation, error-recovery guidance); the 4 anchor's 'minor validation gaps' does not apply since validation checkpoints are stated at each stage.

Progressive Disclosure

The single file is well-sectioned per command with no nested or buried references, and the one pointer out ('see the hyperframes skill') is clearly signaled, matching the 4 anchor ('good structure; most content appropriately placed; minor organization gaps'). It does not reach 5 because there is no reference file layer at all — content such as the full render flag table and template/command catalog is inlined, which is acceptable at this size but leaves the overview carrying everything.

Specificity

The description enumerates the full concrete command surface — 'hyperframes init, lint, inspect, preview, render, transcribe, tts, doctor, browser, info, upgrade, compositions, docs, benchmark' — giving comprehensive, specific coverage of the tool's actions rather than vague domain language. This matches the 'lists multiple specific concrete actions; comprehensive coverage' anchor and exceeds the 'several specific actions; minor gaps' (4) anchor because no listed subcommand is missing.

Completeness

It explicitly answers both questions: 'what' via the enumerated command list and 'when' via the explicit 'Use when scaffolding a project, linting, validating, inspecting visual layout in compositions, previewing in the studio, rendering to video, transcribing audio, generating TTS, or troubleshooting the HyperFrames environment' clause with concrete triggers. This matches the 5 anchor; the 4 anchor ('when' could be more explicit) does not apply since the 'Use when' phrasing is explicit and specific.

Trigger Term Quality

Trigger phrases are natural and well-matched — 'scaffolding a project', 'linting', 'rendering to video', 'transcribing audio', 'generating TTS', 'troubleshooting the HyperFrames environment' — which a user would plausibly say. It falls short of the 5 anchor because common synonyms and file extensions ('video', 'MP4', 'subtitles', 'captions', 'narration') are absent, leaving a few natural terms missing.

Distinctiveness Conflict Risk

The 'HyperFrames CLI tool' framing carves out a clear niche (CLI operation, not composition authoring) with distinct, product-specific trigger terms, so it is unlikely to fire for unrelated skills. It fits the 'clear niche with distinct triggers; minimal conflict risk' anchor; score 4 ('minor overlap risk with closely related skills') is not warranted since the description scopes itself to CLI commands only.