Conciseness

The body is ~20 lines with zero padding: a one-line purpose statement ("Extract a single frame from a video, or create quick thumbnails for inspection"), two commands, and two terse notes that each earn their place. It matches anchor 5 ('Lean and efficient; assumes Claude's competence; every token earns its place') — nothing explains concepts Claude already knows, so it is not 4.

Actionability

Both quick-start commands are fully executable, copy-paste-ready invocations of the bundled script, and the flags shown (--time, --out) match the actual frame.sh argument parser. The two examples cover the common cases (first frame, frame at a timestamp), matching anchor 5; it is not 4 because there are no gaps in the provided examples.

Workflow Clarity

This is a simple, single-task skill with an unambiguous action: run frame.sh with the right flag, per the rubric's simple-skill exception ('workflow clarity can score 5 if the single action is unambiguous'). The operation writes a new output file and is neither destructive nor batch, so the validation cap does not apply; it is not 4 because no checkpoint is missing for an operation of this scope.

Progressive Disclosure

The body is under 50 lines with well-organized sections (Quick start, Notes) and no need for external references, satisfying the rubric's simple-skill allowance. Scored against the actual bundle: the single referenced path {baseDir}/scripts/frame.sh is a real file used with correct flags, so navigation is trivial and one level deep — anchor 5, not 4, since there are no organization gaps.

Specificity

"Extract frames or short clips from videos using ffmpeg" names the domain (videos) and two concrete actions with the tool specified, matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. It is not 4 because it does not list several specific actions (no mention of timestamps, frame indexes, thumbnails, or output formats), and not 2 because the actions are concrete rather than generic like 'Processes PDF files'.

Completeness

The 'what' is clear (extract frames or clips from videos via ffmpeg), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3 ('Has a clear what but when is missing or only weakly implied'). It is not 2 because the 'what' is concrete rather than vague, and not 4 because no explicit 'when' guidance exists at all.

Trigger Term Quality

The terms "frames", "short clips", "videos", and "ffmpeg" are relevant and natural, but common variations users would say — "screenshot", "thumbnail", "still" — and file extensions (.mp4, .mov) are missing, matching anchor 3 ('Some relevant keywords but missing common variations or synonyms'). It is not 4 because keyword coverage is thinner than the anchor-4 example ('PDF files, forms, document extraction') and not 2 because the keywords present are domain-specific rather than generic.

Distinctiveness Conflict Risk

"Extract frames or short clips from videos using ffmpeg" carves out a clear niche (video frame/clip extraction with a named tool) that is unlikely to trigger for unrelated skills, matching anchor 5 ('Clear niche with distinct triggers; minimal conflict risk'). It is not 4 because the domain and action are specific enough that even overlap with closely related video skills is minimal — no broad phrasing like 'Works with PDF and Word document files' is present.