CtrlK
BlogDocsLog inGet started
Tessl Logo

video-frame-extractor

视频反推工具,支持视频抽帧、视觉模型分析、提示词生成,适用于视频创作参考、内容提取、场景分析

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/video-frame-extractor/video-frame-extractor/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The content is highly actionable with executable commands and a clean progressive-disclosure structure pointing to real bundle files, but it is held back by repetitive sections that restate known concepts and a batch workflow that lacks explicit validation checkpoints or error-recovery loops.

Suggestions

Add validation/verification checkpoints to the workflow (e.g. verify extracted frames count before analysis, check API response status and retry on failure) to lift workflow clarity.

Collapse the redundant '可选参数', '使用示例', and '技术说明' sections and remove explanations of concepts Claude already knows (OpenCV internals, batch/caching benefits) to tighten conciseness.

Remove or externalize the hardcoded plaintext COZE_API_KEY and BOT_ID from the skill body — credential secrets should not be embedded in documentation.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands and parameters, but restates the same scripts/params across '操作步骤', '可选参数', '使用示例', and '技术说明', and the '技术说明'/'Coze Bot优势' sections explain concepts Claude already knows (OpenCV VideoCapture, batch efficiency, caching), so it could be tightened.

2 / 3

Actionability

Provides fully executable bash invocations with real script paths, concrete flags, and a copy-paste-ready JSON output schema — matching the anchor for fully executable, specific examples.

3 / 3

Workflow Clarity

The 抽帧→视觉分析→结果整合 sequence is clearly laid out with two alternative paths, but this batch operation (batch frame extraction and batch image API analysis) has no validation/verification checkpoints or error-recovery feedback loops, which caps workflow clarity at 2 per the rubric guideline.

2 / 3

Progressive Disclosure

The body is a concise overview with a '资源索引' section of well-signaled, one-level-deep markdown links to verified existing bundle files (three scripts + references/analysis-guide.md), matching the anchor for clear overview with appropriately split references.

3 / 3

Total

10

/

12

Passed

Description

67%

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 specific and action-oriented with a clear distinctive niche, but it lacks an explicit 'Use when...' trigger clause and only partially covers the natural terms a user would say, leaving completeness and trigger quality at the mid level.

Suggestions

Add an explicit 'Use when...' (例如: 当用户需要分析视频内容、提取分镜参考、生成AI创作提示词时使用) trigger clause to lift completeness to 3.

Include more natural user phrasings as triggers (e.g. '分析视频', '视频分镜', '视频转文字/提示词') alongside the technical terms to improve trigger-term coverage.

Trim the generic trailing terms '内容提取、场景分析' to sharpen distinctiveness and reduce overlap with general analysis skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '视频抽帧'(frame extraction), '视觉模型分析'(visual model analysis), '提示词生成'(prompt generation) — matching the anchor that names several specific actions rather than just a domain.

3 / 3

Completeness

Clearly states what the skill does, but the 'when' is only implied via '适用于视频创作参考、内容提取、场景分析' with no explicit 'Use when...' trigger clause, capping completeness at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

Contains relevant keywords ('视频抽帧', '视觉模型分析', '视频创作参考') but leans on technical phrasing and misses common natural variations a user would say (e.g. '分析这个视频', '视频分镜', '视频转提示词'), so coverage is partial rather than full.

2 / 3

Distinctiveness Conflict Risk

The video reverse-prompting + frame extraction + visual analysis niche is distinctive and unlikely to trigger for unrelated skills, though the appended '内容提取/场景分析' terms are somewhat generic.

3 / 3

Total

10

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
anbeime/skill
Reviewed

Table of Contents

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.