CtrlK
BlogDocsLog inGet started
Tessl Logo

huashu-wechat-image

为微信公众号文章生成高质量配图。支持封面图(2.35:1)、正文插图(16:9/4:3)、信息图。提供两条路径:AI生成(视觉创意型)和HTML渲染(文字精确型)。当用户提到"公众号配图"、"公众号封面"、"文章配图"、"正文插图"、"公众号图片"时使用此技能。

72

Quality

88%

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

77%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 thorough, highly actionable workflow with strong sequencing, validation checkpoints, and feedback loops, and genuinely useful one-level-deep references. Its main weaknesses are conciseness padding (branding, duplicate tables, opinionated prose) and an inline-heavy body that overlaps its own reference files.

Suggestions

Remove the personal branding footer and collapse the two near-identical path-recommendation tables in Step 2 to tighten conciseness.

Move the full HTML templates, base-style prompt scaffolds, and 花叔科技配色 palette into the existing references (style-gallery.md / a templates file), keeping the body as an overview that links out — improving progressive disclosure.

Replace author-specific absolute paths (/Users/alchain/Documents/写作/…) in the generate_image.py and upload_image.py commands with relative/skill-root references so the commands are copy-paste ready for anyone.

DimensionReasoningScore

Conciseness

Mostly efficient and actionable, but padded with a personal branding footer ('花叔出品…30万+粉丝…小猫补光灯'), duplicate path-recommendation tables (Step 2 lists AI-for-everything twice), and opinionated prose; not every token earns its place, so it stops short of the 'lean and efficient' anchor.

2 / 3

Actionability

Provides fully executable guidance — complete copy-paste HTML templates, structured AI prompt scaffolds, exact Playwright viewport flags and aspect-ratio flags, hex color codes — matching the 'fully executable code/commands; specific examples; copy-paste ready' anchor (the only blemish being author-specific absolute paths in two commands).

3 / 3

Workflow Clarity

Clearly sequences Step 0→4 with ✅ confirmation checkpoints, a decision flow diagram, a 3-B-4 检查项 checklist, and explicit feedback loops ('修改 HTML → 重新截图 → 再次确认'; '文字渲染有误 → 该张改用HTML兜底'), meeting the 'clear sequence with explicit validation steps; feedback loops; checklists' anchor.

3 / 3

Progressive Disclosure

References style-gallery.md and design-guidelines.md are real, one-level deep, and signaled at the right moments, but the body is a heavy ~430-line manual carrying full inline templates, prompt scaffolds, and palette tables that overlap with the reference files — content that could be split out is inline, fitting the 'some structure…content that should be separate is inline' anchor rather than the clean overview of the 3-anchor.

2 / 3

Total

10

/

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 states concrete capabilities, supplies natural Chinese trigger terms, and explicitly pairs the 'what' with a 'when' clause. It is specific to the WeChat OA domain and unlikely to collide with sibling image skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and outputs — '支持封面图(2.35:1)、正文插图(16:9/4:3)、信息图' and '两条路径:AI生成…和HTML渲染' — naming specific image types and generation methods, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both 'what' (generates OA article images via cover/body/infographic across two paths) and 'when' via the explicit clause '当用户提到…时使用此技能', meeting the 'clearly answers both what AND when with explicit triggers' anchor.

3 / 3

Trigger Term Quality

Provides five natural user-facing phrases — '公众号配图'、'公众号封面'、'文章配图'、'正文插图'、'公众号图片' — that a user would actually say, giving good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

Clear niche (WeChat Official Account imagery) with distinct 公众号-prefixed triggers unlikely to fire for the sibling xhs-image skill, matching the 'clear niche with distinct triggers; unlikely to conflict' anchor.

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.