CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

wechat-article-reader

Read 微信公众号 articles from mp.weixin.qq.com links using available web or browser tools. Report verification walls honestly; reading alone does not modify notes or queues.

Quality

76%

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 ./.codex/skills/wechat-article-reader/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 lean, highly operational instruction-only skill: it names concrete tools and error signatures, gives explicit verification checkpoints and honest-failure rules, and correctly relies on the host's live tool list rather than guessing APIs. Its main weaknesses are mild — some permission-boundary repetition and prose that would benefit from headers or an explicit step ordering.

DimensionReasoningScore

Conciseness

The body is dense host-specific policy that assumes Claude's competence — e.g. "Ego CLI 报 `Failed to connect to ego_cli bootstrap` 等连接错误时,失败发生在 shell 到宿主的连接阶段,不等于浏览器里的文章也被挡住" — with no explanation of known concepts. However, the permission-boundary theme is restated three times ("不导出 Cookie 或索取凭证", "不通过另一条路径扩大授权", "不获得额外权限"), so a few tokens could be trimmed, matching anchor 4 rather than 5's 'every token earns its place'.

4 / 5

Actionability

As an instruction-only skill its guidance is mostly concrete: the named tool "read_public_url", a named error signature, a verification checklist ("核对标题、作者、正文、发布日期和原始链接"), and a concrete output spec ("输出精要摘要、证据范围、引用与未验证项"). Minor gaps remain — "按已安装的浏览器 skill 使用 CLI" and "交给当前项目的素材管理流程" name no specifics — so anchor 4 rather than 5.

4 / 5

Workflow Clarity

A clear layered flow is present — tool discovery, read-path selection, verification-wall fallbacks, content verification, output — with explicit checkpoints such as "检查截断与读取范围,只有真正看到的内容才能标为已读" and layer-specific failure reporting ("分别说明失败在哪一层,不把它们统称为'微信验证'"). It is read-only (explicitly "仅阅读时不修改"), so the destructive-operation cap does not apply; it scores 4 rather than 5 only because the sequence is implied by paragraph order rather than enumerated.

4 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references (no references/, scripts/, or assets/ exist, and it explicitly states "此公开版不附旧机专用 Playwright 脚本"), and all content is appropriately inline. But the body is dense unheaded paragraphs plus one bullet list rather than well-organized sections, so it earns anchor 4 (minor organization gaps) instead of the simple-skill 5.

4 / 5

Total

16

/

20

Passed

Description

65%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 names a distinct, well-scoped niche with the right natural trigger terms (微信公众号, mp.weixin.qq.com), but its action coverage is thin and it lacks an explicit 'Use when...' trigger clause. Adding one sentence of trigger guidance and a couple of English synonyms would raise it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user shares a mp.weixin.qq.com link or asks to read a 微信公众号/WeChat official account article."

Include English-language synonyms ("WeChat official account article", "公众号文章") so the description triggers for users who refer to it in English.

Mention one or two more concrete capabilities, such as producing a summary with cited and unverified items, or handling verification/login walls via an available browser tool.

DimensionReasoningScore

Specificity

"Read 微信公众号 articles from mp.weixin.qq.com links" names the domain and one concrete action, and "Report verification walls honestly" adds a second, but there is no coverage of how articles are read or what output is produced — matching anchor 3 (domain plus 1-2 concrete actions, not comprehensive). It is not 4 because it does not list several specific actions, and not 2 because the actions given are concrete, not generic.

3 / 5

Completeness

The 'what' is clearly stated ("Read 微信公众号 articles from mp.weixin.qq.com links using available web or browser tools"), but there is no 'Use when...' clause or equivalent explicit trigger guidance, only a weakly implied 'when' from the domain mention — per the guidelines this caps completeness at 3. It is not 4 because the 'when' is not explicit, and not 2 because the 'what' is clear rather than vague.

3 / 5

Trigger Term Quality

"微信公众号", "mp.weixin.qq.com links", and "articles" are exactly what a user would naturally say when asking to read a WeChat article, giving good keyword coverage; missing common synonyms such as "WeChat official account", "公众号文章", or "公众号推送". This fits anchor 4 (good coverage, a few natural terms missing) rather than 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"mp.weixin.qq.com links" and "微信公众号 articles" form a clear niche with distinct triggers and minimal conflict risk; only the generic phrase "web or browser tools" trivially overlaps with general web-reading skills. This matches anchor 5 (clear niche with distinct triggers) rather than 4, which requires meaningful overlap with closely related skills.

5 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

huangruiteng/CS-Notes

Path

.codex/skills/wechat-article-reader/SKILL.md

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.