CtrlK
BlogDocsLog inGet started
Tessl Logo

huashu-xhs-image

为小红书笔记生成高质量配图。默认AI生成(Gemini),仅精确数据表格用HTML兜底。当用户提到"小红书配图"、"小红书封面"、"小红书图片"、"做张小红书图"、"笔记配图"时使用此技能。

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

73%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.

A well-structured, highly actionable workflow with an excellent sequenced feedback loop and clean one-level-deep references. Its main weakness is conciseness: style guidance is restated across multiple sections (and duplicated in the reference file) and a promotional footer adds noise.

Suggestions

Remove the promotional footer (公众号/粉丝数/代表作) and consolidate the style preferences so they appear once — either in the aesthetic profile or in references/style-gallery.md — rather than restated in Golden Rules and the color-scheme table.

Replace hardcoded paths (/Users/alchain/Documents/写作/...) with a parameterized or relative-path convention so the generation and upload commands are copy-paste ready for any user.

De-duplicate the inlined '验证过的好风格' and '花叔科技账号配色' tables against references/style-gallery.md, keeping only a quick pointer inline and the full detail in the reference.

DimensionReasoningScore

Conciseness

Mostly efficient and much of the content is genuinely skill-specific domain knowledge Claude lacks, but style guidance is repeated across the aesthetic profile, Golden Rules, and the color-scheme table (which overlaps references/style-gallery.md), and the promotional footer (公众号/粉丝数/代表作) is pure padding unrelated to the task.

3 / 5

Actionability

Provides a complete prompt template, concrete bash commands for AI generation and Playwright screenshots, explicit file-naming rules, and a 10-point design-review rubric; the main gap is hardcoded user-specific paths (/Users/alchain/...) and bracketed placeholders that prevent true copy-paste readiness.

4 / 5

Workflow Clarity

A clear five-step sequence with explicit validation checkpoints (基础检查项 checklist, 设计审查 scoring) and a concrete feedback loop (用户反馈处理: satisfied→upload, text error→HTML fallback, wrong style→regenerate, major change→back to Step 2) for error recovery.

5 / 5

Progressive Disclosure

Clean one-level-deep bundle (references/style-gallery.md, references/design-guidelines.md, scripts/generate_image.py) all verified to exist and clearly signaled in a 参考文件 section; minor gap is that inlined style/color tables overlap the style-gallery reference rather than being fully split out.

4 / 5

Total

16

/

20

Passed

Description

90%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 strong description: it explicitly states what the skill does and when to use it, with a comprehensive set of natural Chinese trigger phrases and a clear platform-specific niche. The only weakness is specificity, since the described actions collapse to one generation task with two methods rather than a comprehensive action list.

DimensionReasoningScore

Specificity

Names the domain (小红书配图) and ~2 concrete actions ('默认AI生成(Gemini)', '仅精确数据表格用HTML兜底'), but these are two methods of one core action rather than several distinct actions, and the multi-step workflow (proposal/preview/upload) is not surfaced, so coverage is not comprehensive.

3 / 5

Completeness

Explicitly answers both what ('为小红书笔记生成高质量配图...HTML兜底') and when ('当用户提到...时使用此技能') with concrete trigger phrases, in third-person voice.

5 / 5

Trigger Term Quality

Five natural trigger phrases a user would actually say are listed ('小红书配图', '小红书封面', '小红书图片', '做张小红书图', '笔记配图'), covering synonyms and colloquial variations of the request.

5 / 5

Distinctiveness Conflict Risk

A clear niche (Xiaohongshu-specific image generation) with platform-specific triggers that distinguish it from the sister wechat-image skill, yielding 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
alchaincyf/huashu-skills
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.