The body is a model of a lean, single-purpose skill: concrete copy-paste commands for each mode, helpful usage notes, and an explicit non-overwrite safety behavior. No improvements needed for its scope.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding; it assumes Claude's competence and never explains what a video, frame, or FFmpeg is, so every token earns its place.	5 / 5
Actionability	Three fully executable, copy-paste bash commands cover the common cases (first frame, timestamp, frame index) with concrete flags and output paths.	5 / 5
Workflow Clarity	Single-purpose skill with an unambiguous action; the script is protective (refuses to overwrite) rather than destructive or batch, so the validation cap does not apply and the simple-skill exception holds.	5 / 5
Progressive Disclosure	Under 50 lines with well-organized Quick start and Notes sections; the only bundle reference (scripts/frame.sh) is real and clearly signaled as the command to run, satisfying the under-50-line exception.	5 / 5
	Total	20 / 20 Passed

Description

70%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.

The description is concrete, specific, and third-person, clearly stating what the skill does across three modes. Its main weakness is the absence of an explicit 'when to use' trigger clause, which limits the completeness score.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants a still frame, thumbnail, or screenshot from a local video.'

Include natural synonyms like 'thumbnail' or 'screenshot' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (video) and a concrete action (extract a single frame) with three explicit variants (first frame, timestamp, zero-based frame index) and the tool (FFmpeg); not a full 5 because it is effectively one action with variants rather than multiple distinct actions.	4 / 5
Completeness	Has a clear 'what' but no explicit 'Use when…' trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('video', 'frame', 'timestamp', 'FFmpeg') but omits common synonyms like 'thumbnail' or 'screenshot from video' that the body itself alludes to.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (single-frame extraction from local video via FFmpeg) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: iflytek/skillhub
Path: builtin-skills/skills/video-frames/SKILL.md
Commit: 7352597

Reviewed: 4 days 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.