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。

68

Quality

82%

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 highly actionable, well-sequenced workflow with strong validation checkpoints and clean reference structure, undermined mainly by redundant AI-preference messaging, a self-promotional footer, and hardcoded author-specific paths that break copy-paste executability.

Suggestions

State the AI-first preference exactly once and delete the redundant repetitions (the Step 2 HTML-vs-AI comparison table that is immediately overridden, the 花叔偏好 box, and the 默认推荐AI路径 line), and remove the promotional author bio/footer to reclaim tokens.

Replace the hardcoded absolute paths (/Users/alchain/Documents/写作/.claude/skills/wechat-image/scripts/generate_image.py and .../tools/upload_image.py) with skill-relative paths or explicit placeholders so the generate and upload commands run verbatim for any user.

Move the two full inline HTML template examples into a reference file (or deduplicate them against the base-style blocks already in references/style-gallery.md) to shorten the body and remove overlap with the style-gallery reference.

DimensionReasoningScore

Conciseness

Most of the body is operational and free of concept-explanation padding, but the AI-first preference is restated 3-4 times (Step 2 comparison table, 花叔偏好 box, 路径推荐规则 table, 默认推荐AI路径 line), a comparison table is presented and then immediately overridden, and a promotional author bio/footer occupies tokens — several sections that could be tightened, fitting the mostly-efficient-but-includes-unnecessary-parts anchor.

3 / 5

Actionability

Provides copy-paste-ready HTML templates, exact Playwright viewport commands, structured AI prompt templates, and a generate_image.py invocation with aspect flags, but the generate and upload commands embed hardcoded absolute paths (/Users/alchain/Documents/写作/...) that fail verbatim for any non-author user — a concrete executability gap keeping it just below 5.

4 / 5

Workflow Clarity

A clearly sequenced Step 0→4 workflow with explicit ✅ 用户确认 validation checkpoints, per-step preview checklists (检查项 1-5), feedback loops (修改HTML→重新截图→再次确认; 满意/重新生成/调整prompt), and a decision flowchart with error-recovery branches — matching the explicit-validation-with-feedback-loops-and-checklists anchor.

5 / 5

Progressive Disclosure

The body is an overview that clearly signals one-level-deep references (references/style-gallery.md and references/design-guidelines.md via an inline pointer and a 参考文件 section), with bulk detail correctly offloaded; the gap is that two full HTML templates and prompt base-styles are inlined and overlap with content already in style-gallery.md, a minor organization redundancy.

4 / 5

Total

16

/

20

Passed

Description

91%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, well-structured description that clearly states what the skill does and gives explicit, natural trigger phrases for when to use it. Its only weakness is minor overlap risk between a couple of generic trigger terms and sibling image skills.

DimensionReasoningScore

Specificity

Names the domain (WeChat article images) and lists several concrete items — cover (2.35:1), body illustrations (16:9/4:3), infographics, plus two generation paths (AI生成 and HTML渲染) — but the underlying verb is essentially a single action (生成配图) rather than multiple distinct operations, so it sits just below the comprehensive 5 anchor.

4 / 5

Completeness

Explicitly answers both 'what' (为微信公众号文章生成高质量配图,支持封面/正文/信息图,两条路径) and 'when' with a concrete '当用户提到…时使用此技能' clause listing real trigger phrases, matching the explicit-what-and-when-with-triggers anchor.

5 / 5

Trigger Term Quality

Provides five natural Chinese trigger phrases a user would actually say (公众号配图, 公众号封面, 文章配图, 正文插图, 公众号图片) with synonym coverage across 配图/封面/图片/插图, matching the comprehensive-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

The 公众号-prefixed triggers carve a clear niche, but the unprefixed terms 文章配图 and 正文插图 could overlap with the sibling xhs-image skill, leaving minor overlap risk with a closely related skill rather than the minimal-conflict 5 anchor.

4 / 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.