image-generate

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

Quality

66%

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

80%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, actionable, and well-structured for a simple single-purpose skill, with a real executable example and a verified script path. Its main weakness is the absence of a validation/verification step for the image-download output, which caps workflow clarity.

Suggestions

Add a verification step after generation, e.g. confirm the file exists at the printed 'Downloaded to:' path and report it back to the user.

Note where images are saved (the IMAGE_DOWNLOAD_DIR env var / default ./) and the default model, so output handling is predictable without reading the script.

Add brief error-recovery guidance for the documented failure cases (empty prompt, missing API key) rather than only stating errors will be printed.

Dimension	Reasoning	Score
Conciseness	The body is short and assumes Claude's competence, using brief sections and a single executable example; the only minor padding is restating that the prompt should be clear, which already appears in the steps.	4 / 5
Actionability	It provides a fully executable command with a concrete example (`python scripts/image_generate.py "一只可爱的猫"`) and the referenced script exists and matches the documented behavior, making the guidance copy-paste ready.	5 / 5
Workflow Clarity	Steps are listed in sequence, but the operation writes generated images to disk (a batch/download operation) with no explicit validation or verification checkpoint confirming the file was saved successfully; the rubric caps such cases at 3.	3 / 5
Progressive Disclosure	This is a simple skill under 50 lines with a single bundled script referenced by a real path (scripts/image_generate.py, confirmed present); content is well-organized into short sections with no nested references, matching the simple-skill exception for a 5.	5 / 5
	Total	17 / 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 conveys a clear single purpose (image generation via a built-in script) but omits explicit 'Use when...' trigger guidance and natural synonym coverage, capping completeness and trigger-term quality at 3. It is reasonably distinct because it names a specific script.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to generate, draw, or create an image from a text prompt.'

Expand trigger terms with natural synonyms users say, such as '画图', '创建图像', '生成插画', and 'text-to-image'.

List 1-2 more concrete capabilities (e.g., downloads the generated image to a local directory, uses the doubao-seedream model by default) to lift specificity.

Dimension	Reasoning	Score
Specificity	It names the domain (image generation) and one concrete action (running image_generate.py via a clear prompt), but coverage is thin — it does not list multiple specific actions like model selection, downloading, or output handling.	3 / 5
Completeness	The 'what' is clear (generate images via the built-in script), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	It mentions '生成图片' and 'prompt' which are relevant natural terms, but it lacks common variations/synonyms a user might say (e.g., '画图', '创建图像', '生成插画') and offers no file-extension or trigger phrasing.	3 / 5
Distinctiveness Conflict Risk	The reference to the specific image_generate.py script gives it a clear niche and low overlap risk with other skills, though the phrasing is generic enough to leave minor ambiguity versus other image-related skills.	4 / 5
	Total	13 / 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: 43eb317

Reviewed: 3 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.