CtrlK
BlogDocsLog inGet started
Tessl Logo

video-generate

使用 video_generate.py 脚本生成视频,需要提供文件名和 prompt,可选提供首帧图片(URL或本地路径)。

63

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.trae/openclaw-skills/video-generate/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 body is a tight, highly actionable guide: exact command signature, three complete examples, explicit credential sources, and clean section structure. Its only weaknesses are minor output-information duplication and the absence of post-run verification/error-handling steps.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: no concept explanations, tight sections (适用场景, 使用步骤, 认证与凭据来源, 输出格式, 示例). A minor instance could be trimmed — the 输出格式 section restates step 4's URL/download info — matching 'efficient; minor instances that could be trimmed' rather than the every-token-earns-its-place anchor.

4 / 5

Actionability

Fully executable guidance: exact CLI signature ('python scripts/video_generate.py <filename> "<prompt>" [first_frame]') plus three copy-paste-ready bash examples covering text-only, URL first-frame, and local first-frame cases, and concrete env-var names (MODEL_VIDEO_API_KEY, ARK_API_KEY, VOLCENGINE_ACCESS_KEY/SECRET_KEY).

5 / 5

Workflow Clarity

A clear 4-step sequence (prepare filename/prompt → optional first frame → run script → receive URL/download) with a documented credential fallback chain. There are minor validation gaps — no post-run verification that the video downloaded or guidance on error recovery — which holds it at 4 rather than 5; the operation is non-destructive so the destructive-skill cap does not apply.

4 / 5

Progressive Disclosure

Under 50 lines, well-organized into clearly headed sections, with a single appropriately referenced script (scripts/video_generate.py, which exists in the bundle) and no external reference files needed. This matches the simple-skill exception where well-organized sections alone warrant a 5.

5 / 5

Total

18

/

20

Passed

Description

61%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 and specific about the tool and its inputs, but omits any explicit 'when to use' trigger guidance and uses imperative rather than third-person voice, which caps both completeness and specificity. Trigger keywords are good but lack common synonyms.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user asks to generate a video from a text prompt or to animate/animate-from a first-frame image (URL or local path).' This lifts completeness from 3 to 4-5.

Rewrite in third person: 'Generates videos via the video_generate.py script from a filename, prompt, and optional first-frame image (URL or local path).' instead of '使用...生成视频' imperative voice.

Include a couple of natural synonyms such as 'create video', 'text-to-video', and 'animate image' to broaden trigger term coverage.

DimensionReasoningScore

Specificity

The description names the concrete tool ('video_generate.py 脚本生成视频') and all inputs (文件名, prompt, 可选提供首帧图片(URL或本地路径)), placing it between the 1-2-action anchor and the several-actions anchor. A 1-point voice penalty applies because '使用...生成视频' is imperative/second-person instruction ('Use the script to...') rather than third person ('Generates videos...'), lowering it from 4 to 3.

3 / 5

Completeness

The 'what' is clear — generate video via the script with filename, prompt, and optional first-frame image — but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guideline. It fits the 'clear what but when missing or only weakly implied' anchor exactly.

3 / 5

Trigger Term Quality

Natural terms users would say are present: '生成视频' (generate video), 'video_generate.py', 'prompt', '首帧图片' (first frame image), 'URL或本地路径'. A few natural variations are missing (e.g., 'create video', 'animate an image', 'text-to-video'), matching the 'good keyword coverage; a few natural terms missing' anchor rather than the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

Video generation with first-frame (URL/local path) control is a clear niche unlikely to collide with unrelated skills. Minor overlap risk remains with adjacent video skills (editing, downloading, animation) since no explicit triggers delimit the boundary, so it sits at 'mostly distinct' rather than 'clear niche with distinct triggers'.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
huangruiteng/CS-Notes
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.