image-generate

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

Quality

71%

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 ./.trae/openclaw-skills/image-generate/SKILL.md

Quality

Content

92%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 a tight, well-structured instruction sheet: a clear three-step usage flow, authentication fallback chain, output format, and a runnable example. Its only weaknesses are small actionability gaps — an under-specified working-directory instruction and a missing dependency-install note.

Suggestions

Replace '运行之前cd到对应的目录' with the concrete directory (e.g., the skill root containing scripts/) so the command is copy-paste runnable from anywhere.

Add one line noting the required dependency (pip install volcenginesdkarkruntime) or that the script will fail without it.

Briefly state required arguments/limits of the prompt (e.g., supported language, length) so users prepare a valid prompt the first time.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding or explanations of concepts Claude already knows — every section (适用场景, 使用步骤, 认证与凭据来源, 输出格式, 示例) carries operational information. It matches the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	The guidance is mostly executable: a concrete command ('python scripts/image_generate.py "<prompt>"'), a runnable example ('一只可爱的猫'), and specific env var names. Minor gaps keep it below 5: '运行之前cd到对应的目录' does not state which directory, and there is no note that the script's dependency (volcenginesdkarkruntime) must be installed.	4 / 5
Workflow Clarity	This is a simple single-purpose skill with a numbered sequence (prepare prompt → run script → receive URL), so the single action is unambiguous; the simple-skill exception applies. No validation steps are required since the operation is neither destructive nor batch, and error behavior ('若调用失败，将打印错误信息') is stated.	5 / 5
Progressive Disclosure	The body is under 50 lines with no need for external references, and content is well organized into clearly headed sections; the one bundle file referenced (scripts/image_generate.py) exists and is referenced at exactly one level of depth, matching the actual bundle structure.	5 / 5
	Total	19 / 20 Passed

Description

50%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 communicates a single concrete capability but is minimal: it lacks any 'Use when...' trigger guidance, natural keyword variations, and supporting context (e.g., which API/model, output type). It is functional but would benefit from a fuller trigger-oriented rewrite.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user wants to generate/create an image from a text description, mentions 文生图/text-to-image, or asks for AI-generated pictures.'

Include natural keyword variations and synonyms such as '画图', '生成一张...的图片', 'AI 绘图', 'image generation' so users' phrasing matches the description.

State what the skill returns (a URL to the generated image) and mention the backing service (Volcengine Ark / Doubao Seedream) to distinguish it from other image-related skills.

Dimension	Reasoning	Score
Specificity	The description names the domain (image generation) and one concrete action ('使用内置 image_generate.py 脚本生成图片') plus a prep directive ('准备清晰具体的 prompt'), but coverage is not comprehensive. It fits the 'names domain and 1-2 concrete actions' anchor rather than score 4, which requires several specific actions.	3 / 5
Completeness	It has a clear 'what' (generate images using the built-in script) but no 'when' clause — there is no 'Use when...' or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not score 4 because the 'when' is entirely missing rather than merely under-specified.	3 / 5
Trigger Term Quality	'生成图片' (generate image) and 'prompt' are relevant keywords a user might say, but common variations and synonyms (e.g., '画图', 'AI 生图', 'image', '文生图', text-to-image) are absent. Not score 2 because it is not purely generic, but not score 4 because keyword coverage is thin.	3 / 5
Distinctiveness Conflict Risk	Image generation is a fairly distinct niche and the named script (image_generate.py) adds specificity, but the one-line description could still overlap with related skills (image editing, image analysis, other generation tools). It sits between anchor 3 ('somewhat specific but could still overlap with similar skills') and anchor 4.	3 / 5
	Total	12 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: huangruiteng/CS-Notes
Path: .trae/openclaw-skills/image-generate/SKILL.md
Commit: 77c775d

Reviewed: 1 day 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.