CtrlK
BlogDocsLog inGet started
Tessl Logo

image-generation

AI 图片生成:原生 tool call(Codex/Antigravity)或浏览器自动化(Gemini/ChatGPT)。 Use when: 需要 AI 生成概念图、UI 参考、像素画素材、完整 PPT 页面、复杂架构图、信息图或视觉 mock。 Not for: 已有图片的展示(用 media_gallery rich block)、硬要求可编辑/native text 的 PPT/图表(用 PPT/HTML 管线)。 Output: 生成图片自动发布,或作为完整视觉 mock / 图像素材进入后续交付。

69

Quality

84%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

Highly actionable content with concrete tools, paths, selectors, and well-sequenced workflows that include explicit feedback loops. The main weakness is conciseness: the core imagegen-first guidance is repeated across several sections and could be consolidated, and some reference-style tables could live in separate files.

Suggestions

Consolidate the repeated 'imagegen-first, don't write SVG' messaging from the 原生能力校准, SVG 复发熔断闸, Full-page raster first, and 什么时候才写 SVG sections into a single decision rule with one short fallback list to remove redundancy.

Consider extracting the DOM 选择器速查 and 下载文件命名 tables into a references/ file referenced once from the browser path section, reducing the main body length and improving progressive disclosure.

Tighten the 注意事项 section by merging items that restate the '优先原生 tool call' and '禁止 CLI 命令替代' rules already covered in the 原生路径 section.

DimensionReasoningScore

Conciseness

Operational rather than concept-explaining, but the 'imagegen-first / don't write SVG' message is restated across four to five sections (原生能力校准, SVG 复发熔断闸, Full-page raster first, 什么时候才写 SVG, Common Mistakes), which is redundant padding that could be consolidated; not a 2 because no basic concepts are over-explained.

3 / 5

Actionability

Provides concrete tool names (image_gen, generate_image), exact artifact paths, specific DOM selectors (.ql-editor, #prompt-textarea), numbered browser steps, and a shell example; fully executable and copy-paste ready across the common cases.

5 / 5

Workflow Clarity

The 'Full-page raster first' workflow has a clear 4-step sequence with an explicit feedback loop (视觉评估 → prompt 迭代 → 失败才降级), the SVG circuit-breaker has a 4-step execution order, and the Common Mistakes table functions as a checklist; image generation is non-destructive so no batch-validation cap applies.

5 / 5

Progressive Disclosure

Single self-contained file with clear section headers and no bundle files, so references are not an issue; however the file exceeds 50 lines and inlines reference-style content (DOM selector tables, file-naming conventions) that could be split out, leaving minor organization gaps versus a 5.

4 / 5

Total

17

/

20

Passed

Description

87%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.

A well-constructed description that explicitly states what it does, when to use it, what it is not for, and the expected output. Trigger terms are natural and the Not-for boundary sharply reduces conflict with sibling skills.

DimensionReasoningScore

Specificity

Names two execution paths (native tool call vs browser automation) and seven concrete deliverable types (concept images, UI refs, pixel art, PPT pages, architecture diagrams, infographics, visual mock); not a 5 because the actions are predominantly 'generate X' variants rather than distinct operations.

4 / 5

Completeness

Explicitly answers 'what' (AI 图片生成 with native/browser paths), 'when' (Use when: concrete trigger list), plus Not-for boundaries and Output; clearly and explicitly covers both what and when with concrete triggers.

5 / 5

Trigger Term Quality

Includes natural user-facing terms like '概念图', 'UI 参考', 'PPT 页面', '架构图', '信息图', '视觉 mock' with good synonym coverage; a few natural variations are missing so it does not reach comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

Explicit 'Not for:' clause disambiguates from media_gallery (display) and PPT/HTML pipeline (editable) skills, giving a clear niche with minimal conflict risk.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
zts212653/clowder-ai
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.