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。

75

Quality

92%

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

85%Weight 40%Scale 1-3

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

A well-sequenced, highly actionable workflow with strong validation checkpoints and properly offloaded reference files. Its main weakness is token efficiency: a non-functional personal bio footer and some redundant emphasis/tables dilute an otherwise lean skill.

Suggestions

Remove the personal branding footer ('花叔出品 | AI Native Coder | 公众号 | 30万+粉丝 | 代表作') — it carries no skill function and wastes context-window tokens.

Collapse the three repetitions of 'do not skip the proposal step' (核心原则 / 禁止跳过 / 这是最关键的一步) into a single emphatic statement to cut redundancy.

De-duplicate the inline aesthetic tables (验证过的好风格, 花叔科技账号配色) against references/style-gallery.md, keeping only essentials inline and pointing to the gallery for the full set.

DimensionReasoningScore

Conciseness

Most content is genuinely domain-specific (aesthetic profile, palettes, prompt keywords) and earns its place, but the personal bio footer ('花叔出品 | 30万+粉丝 | 代表作:小猫补光灯'), triple-repeated 'don't skip the proposal' emphasis, and overlapping inline style/palette tables are padding that could be tightened.

2 / 3

Actionability

Provides a copy-paste-ready prompt template, exact commands with flags (uv run generate_image.py --resolution 2K), concrete hex colors, and HTML specs with explicit dimensions and font-family — concrete and executable.

3 / 3

Workflow Clarity

Clear 5-step sequence with explicit validation in Step 4 (中文渲染/比例/风格/署名 checklist, design review scoring) and feedback loops for error recovery (文字有误→HTML兜底, 大改→回到Step 2重新提案).

3 / 3

Progressive Disclosure

Body serves as an overview with clearly signaled, one-level-deep references to real files (references/style-gallery.md, references/design-guidelines.md) listed in a dedicated '参考文件' section, with easy navigation.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that concretely states the skill's actions, defaults, and fallback, paired with explicit natural-language triggers. It cleanly answers both 'what' and 'when' with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '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' — rather than vague language, matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what (generate images via AI default with HTML fallback for data tables) and when ('当用户提到…时使用此技能'), satisfying the explicit 'Use when…' requirement.

3 / 3

Trigger Term Quality

Provides five natural trigger phrases a user would actually say ('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'), giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (Xiaohongshu image generation) with platform-specific triggers, making it unlikely to fire for the sibling wechat-image or unrelated skills.

3 / 3

Total

12

/

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
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.