CtrlK
BlogDocsLog inGet started
Tessl Logo

wechat-article-pro

微信公众号文章发布专业版。功能:1)联网搜索热点信息 2)AI生成微信公众号封面图 3)撰写3000-5000字深度文章 4)使用公众号AI配图功能自动生成并上传封面 5)参考刘润公众号风格写作 6)自动排版 7)不加话题标签

54

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./configs/microservice/bff-service/configs/agent-skills/clawhub/wechat-article-pro/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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.

The body provides a clearly sequenced, reasonably actionable workflow for WeChat article publishing with good section structure and a useful style guide. Its weaknesses are repeated rules that waste tokens, missing execution details for search and text entry, and the complete absence of validation checkpoints between steps.

Suggestions

Add validation checkpoints after each risky step: verify word count is 3000-5000 before saving, confirm the cover image is applied, and verify the draft appears in 草稿箱 after clicking 保存.

State the no-hashtag rule and the word-count requirement once each (in 注意事项) and delete the duplicated mentions in 禁止事项 and the 功能 list, which restates the frontmatter description.

Make step 1 and step 5 executable: specify how to search for hot topics (concrete query strategy or tool invocation) and how the title and body text are entered into the editor.

DimensionReasoningScore

Conciseness

The body is mostly efficient with no concept-teaching padding, but it is tightened poorly: the no-hashtag rule appears three times ('❌ 文章末尾禁止加任何话题标签', '4. **禁止话题** - 末尾绝对不要加任何 #标签'), and the '## 功能' section restates the frontmatter description almost verbatim, matching the 'could be tightened' level-3 anchor.

3 / 5

Actionability

Concrete UI sequences exist ('点击封面区域', '选择 AI配图', '输入封面描述 - 主体+场景+风格') with word-count budgets and a structure template, but key execution details are missing: '使用 web_fetch 搜索主题相关热点信息' specifies no actual search method or query, and how the title/body text is entered into the editor is never stated.

3 / 5

Workflow Clarity

The seven steps ('步骤 1: 搜索热点' through '步骤 7: 保存草稿') form a clear sequence, but there are no validation checkpoints — no word-count verification, no confirmation the cover was applied, no check that the draft actually saved — matching the 'sequence present but checkpoints missing' level-3 anchor.

3 / 5

Progressive Disclosure

With no bundle files present, the ~110-line body is well organized into clear sections (风格参考, 执行流程, 注意事项) that are easy to navigate. It does not reach 5 because the ~40-line Liu Run style guide is inlined content that would sit better in a separate reference file, and the body exceeds the 50-line simple-skill threshold.

4 / 5

Total

13

/

20

Passed

Description

66%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.

The description clearly communicates a rich set of specific capabilities for WeChat official-account article publishing, with natural domain keywords and a distinct niche. Its main weakness is the complete absence of 'when to use' trigger guidance, which caps completeness, plus a redundant duplicate cover-generation item and padding like '专业版'.

Suggestions

Add an explicit trigger clause such as '当用户要求发布、撰写微信公众号文章或生成公众号封面时使用' to answer 'when should Claude use it' and lift completeness above 3.

Merge the redundant cover-related items (2 and 4) into one and drop the '专业版' buzzword to make every clause earn its place.

Include common user phrasings/synonyms (e.g. '发公众号', '推文', '排版') to broaden natural trigger-term coverage toward level 5.

DimensionReasoningScore

Specificity

Enumerates seven concrete actions ('联网搜索热点信息', '撰写3000-5000字深度文章', '使用公众号AI配图功能自动生成并上传封面'), approaching comprehensive coverage, but items 2 and 4 redundantly both describe cover generation and '专业版' adds no capability information, leaving minor gaps versus the level-5 anchor.

4 / 5

Completeness

The 'what' is clearly answered by the enumerated 功能 list, but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Contains natural keywords a user would say such as '微信公众号', '文章', '封面图', and '刘润', giving good coverage; however common variations and synonyms (e.g. '发公众号', '推文', '写作') are missing, so it does not reach the comprehensive level-5 anchor.

4 / 5

Distinctiveness Conflict Risk

The WeChat official-account publishing niche with Liu Run style and no-hashtag rules is mostly distinct from other skills with only minor overlap risk against generic article-writing skills; not 5 because no explicit trigger boundary distinguishes it from those near neighbors.

4 / 5

Total

15

/

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
UnicomAI/wanwu
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.