CtrlK
BlogDocsLog inGet started
Tessl Logo

wechat-article-spider

微信公众号文章爬虫 - 将微信公号文章转换为 Markdown + 本地图片

56

Quality

64%

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-spider/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is highly actionable with executable commands, examples, and an output map, and it is sensibly sectioned for a single-purpose tool. Its main weaknesses are minor redundancy in the install instructions and the absence of any verification step for the batch image download.

Suggestions

Collapse the redundant '执行指令' and '安装' sections into one consistent install/run block (reconcile the 'wechat-article-dl/scripts' vs 'scripts' path).

Add a verification checkpoint after running, e.g. confirm the expected .md file and images/ count exist and that image links resolve, to lift workflow clarity.

Trim the '功能' checklist where it merely restates the '用法' examples to tighten token efficiency.

DimensionReasoningScore

Conciseness

The body is lean with no concept-padding, but it duplicates the install step in both '执行指令' and '安装' (with an inconsistent path 'wechat-article-dl/scripts' vs 'scripts') and the '功能' list restates behavior already shown in '用法', so it could be tightened rather than earning a 3.

2 / 3

Actionability

It provides fully executable, copy-paste commands ('cd scripts && pip install -r requirements.txt && python main.py'), a concrete CLI signature with realistic mp.weixin.qq.com URL examples, an output structure tree, and a pinned dependency list, matching the 'copy-paste ready' anchor.

3 / 3

Workflow Clarity

The single-action invocation (python main.py <URL> [output]) is unambiguous, but the operation involves batch image downloading with no validation/verification step confirming images succeeded or the Markdown is well-formed, which per the guidelines caps workflow clarity at 2.

2 / 3

Progressive Disclosure

It is a single-purpose skill with well-organized sections (功能, 安装, 用法, 输出结构, 注意事项, 依赖) and no nested external references; the scripts/ bundle is surfaced via the run command, so the simple-skill allowance yields a 3.

3 / 3

Total

10

/

12

Passed

Description

57%

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 states the skill's purpose and occupies a distinct niche, but it lacks an explicit 'Use when...' trigger and leans on the jargon term '爬虫' rather than natural user phrasing. It conveys 'what' well but not 'when'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to save or archive a 微信公众号文章 as Markdown with images downloaded locally.'

Replace or supplement the jargon '爬虫/spider' with natural user terms like '下载/保存微信公众号文章' to improve trigger-term quality.

List concrete actions as verbs (fetch article, download images, convert to Markdown) to lift specificity toward 3.

DimensionReasoningScore

Specificity

Names the domain ('微信公众号文章爬虫') and one concrete action ('将微信公号文章转换为 Markdown + 本地图片'), but does not enumerate multiple distinct actions like fetching, image downloading, and saving as separate verbs, so it falls short of a 3.

2 / 3

Completeness

It answers 'what' (convert WeChat articles to Markdown + local images) but has no explicit 'when/Use when' trigger clause, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Relevant natural terms appear ('微信公号文章', 'Markdown'), but the jargon '爬虫/spider' is technical and common user phrasings like '下载微信文章' or a 'Use when...' trigger are absent, matching the 'some keywords but missing variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The WeChat-official-account-article-to-Markdown niche is highly specific with distinct triggers, making it unlikely to fire for an unrelated skill; it is not a 2 because the domain is unmistakably narrow rather than overlapping.

3 / 3

Total

9

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

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.