CtrlK
BlogDocsLog inGet started
Tessl Logo

image-generate

使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。

59

Quality

67%

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/image-generate/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is concise, well-structured, and clearly references a real script, but its output documentation is inaccurate and it omits dependency and credential-setup details needed for the command to actually run.

Suggestions

Correct the output description: the script downloads each image to a file (e.g. `generated_image_<ts>_<i>.png`) and prints the filepath, rather than returning a URL.

Add a prerequisites note covering `pip install volcenginesdkarkruntime` and the required environment variables (`MODEL_IMAGE_API_KEY` / `ARK_API_KEY`).

Clarify the vague 'cd到对应的目录' instruction by stating the exact working directory (the skill root containing `scripts/`).

DimensionReasoningScore

Conciseness

The body is lean with short, focused sections and no padding explaining concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.

3 / 3

Actionability

It gives a concrete command and a copy-paste example, but claims the script returns a URL while the script actually downloads the image to a file and prints the filepath, and it omits the `volcenginesdkarkruntime` dependency and credential-setup requirements, matching the 'concrete guidance but incomplete; missing key details' anchor.

2 / 3

Workflow Clarity

For this simple single-purpose skill the three steps (prepare prompt, run script, observe output) are clearly sequenced and unambiguous; no validation checkpoint is required for non-destructive image generation.

3 / 3

Progressive Disclosure

The skill is under 50 lines with well-organized sections and a single one-level-deep reference to the real bundle file `scripts/image_generate.py`, matching the guideline that such skills can score 3 with just well-organized sections.

3 / 3

Total

11

/

12

Passed

Description

50%

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 names a concrete capability, but it omits an explicit 'Use when' trigger clause and only partially covers natural trigger terms. It is adequate but not exemplary.

Suggestions

Add an explicit trigger clause, e.g. '当用户要求根据文本描述生成图片、画图或 AI 图片时使用' to raise completeness and trigger-term coverage.

Broaden natural keywords to include common variations like 画图、AI配图、text-to-image alongside 生成图片.

State the capability in third person (e.g. '生成基于文本描述的图片') instead of the imperative '使用...' to match the recommended voice.

DimensionReasoningScore

Specificity

Names a concrete action ("生成图片") and a precondition ("准备清晰具体的 `prompt`"), but does not enumerate multiple specific actions, matching the 'names domain and some actions, but not comprehensive' anchor.

2 / 3

Completeness

It states what the skill does (generate images via the built-in script) but provides no explicit 'Use when...' trigger guidance, so per the judging guidelines completeness is capped at 2.

2 / 3

Trigger Term Quality

"生成图片" and "prompt" are natural terms a user might say, but the description lacks common variations (e.g. 画图, AI 图片, text-to-image), matching the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

Image generation is a recognizable niche, but the single trigger "生成图片" could overlap with other image-related skills, matching the 'somewhat specific but could still overlap' anchor.

2 / 3

Total

8

/

12

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.

Validation16 / 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.