video-frames

Extract frames or short clips from videos using ffmpeg.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/video-frames/SKILL.md

The canonical home for this skill is video-frames in Hung-Reo/hungreo-openclaw

Quality

Content

93%Weight 40%Scale 1-5

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

The content is lean, executable, and well-structured for a simple single-purpose skill, with a real referenced script backing the inline examples. The only gap is the absence of an explicit validation/verification step in the body, which keeps workflow clarity just below perfect.

Suggestions

Add a brief verification step to the Quick start, e.g. 'Confirm the output: open /tmp/frame.jpg' or note that frame.sh prints the output path on success.

Optionally mention the additional frame.sh flags (--index, --time) inline so the full capability surface is discoverable without reading the script.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: a short intro, two copy-paste bash commands, and a brief Notes list, with every token earning its place, matching the score-5 anchor.	5 / 5
Actionability	Both examples are fully executable, copy-paste-ready commands covering the common cases (first frame and timestamped frame), with the underlying frame.sh handling additional flags, matching the score-5 anchor.	5 / 5
Workflow Clarity	This is a simple single-purpose skill whose one action is unambiguous, but the body does not show an explicit validation checkpoint (e.g. confirming the output file exists or ffmpeg succeeded), so it sits just below a perfect workflow score.	4 / 5
Progressive Disclosure	For a sub-50-line simple skill, the well-organized Quick start and Notes sections plus a real one-level-deep referenced script (scripts/frame.sh) satisfy the score-5 simple-skill exception.	5 / 5
	Total	19 / 20 Passed

Description

53%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 concise and clearly states a niche capability, but it omits an explicit 'Use when...' trigger clause and lacks synonyms and file extensions that would strengthen trigger-term coverage. Adding trigger guidance would lift completeness and trigger-term quality.

Suggestions

Append a 'Use when...' clause naming concrete triggers, e.g. 'Use when the user wants to grab a frame, thumbnail, or short clip from a video (.mp4, .mov).'

Add natural synonyms and file extensions such as 'thumbnails', 'timestamps', and '.mp4' to broaden trigger-term coverage.

Optionally add one more concrete action (e.g. 'create thumbnails') to push specificity toward the score-5 anchor.

Dimension	Reasoning	Score
Specificity	The description names the domain and concrete actions ('Extract frames or short clips from videos using ffmpeg'), listing two distinct actions but not a comprehensive set, matching the score-3 anchor.	3 / 5
Completeness	It clearly states what the skill does ('Extract frames or short clips from videos using ffmpeg') but has no 'Use when...' or equivalent explicit trigger clause, capping completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Natural terms like 'frames', 'short clips', and 'videos' are present, but common variations such as 'thumbnails', 'timestamps', or file extensions like '.mp4' are missing, matching the score-3 anchor.	3 / 5
Distinctiveness Conflict Risk	The ffmpeg-based video frame/clip niche is mostly distinct with only minor overlap risk against broader video skills, fitting just above the score-3 anchor.	4 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: Bitterbot-AI/bitterbot-desktop
Path: skills/video-frames/SKILL.md
Commit: 017761f

Reviewed: 2 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.