wechat-article-publisher

从 Markdown 文件或网页链接提取文章并发布到微信公众号。适用于需要“自动创建草稿/提交发布”、统一微信样式（standard/viral）和批量复用发布流程的场景。

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%

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

The content is concise, actionable, and presents a well-sequenced workflow with a dry-run validation checkpoint and concrete error-code recovery guidance. The main weakness is progressive disclosure: the body repeatedly references scripts/publish_wechat.py and config.json, but no bundle files are present, so the one-level-deep references do not resolve.

Suggestions

Bundle the referenced scripts/publish_wechat.py (and a starter config.json) under the skill directory so the documented commands actually resolve; the body cites these files but scripts/ and assets/ are empty.

Add one concrete worked example with a literal input (e.g. a sample .md path or URL) run through --dry-run, so the workflow is immediately reproducible without substitution.

Make the dependency-install step explicit (what --install pulls in) or point to a requirements file, since the actionability of step 2 currently depends on an undocumented installer.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned (何时使用, 工作流, 命令参数, 执行约束, 输出结果) with no padding explaining concepts Claude already knows; every line (commands, flags, error codes 48001/41005, output fields) earns its place. Not a 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands (e.g. `python scripts/publish_wechat.py --install`, `... <输入> --dry-run`, `... --publish --status`) with a complete flag reference and documented input forms (local md path or URL). Not a 2 because these are real executable commands rather than pseudocode or missing key details.	3 / 3
Workflow Clarity	A clearly sequenced workflow (配置→安装→预览→创建草稿→提交发布) with an explicit validation checkpoint ("发布前优先做 --dry-run，检查标题、摘要和渲染 HTML") and error-recovery feedback loops for 48001 and 41005. Not a 2 because validation and recovery are explicit, satisfying the destructive/batch-operation feedback-loop requirement.	3 / 3
Progressive Disclosure	The body is well-organized into clear sections and references only one-level-deep targets (scripts/publish_wechat.py, config.json), but the referenced bundle files are absent — the actual scripts/ and assets/ directories are empty, so the signaled references do not resolve. Not a 3 because navigation to the referenced material is broken; not a 1 because structure and signaling are otherwise sound.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 is strong: it names several concrete capabilities, includes natural Chinese trigger phrases, and explicitly pairs a what-clause with a 适用于…场景 when-clause. It occupies a clear niche (WeChat Official Account publishing) with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "从 Markdown 文件或网页链接提取文章并发布", "自动创建草稿/提交发布", "统一微信样式（standard/viral）", "批量复用发布流程" — which matches the score-3 anchor for multiple specific concrete actions; not a 2 because the actions are comprehensive rather than partial.	3 / 3
Completeness	States both what ("提取文章并发布到微信公众号") and an explicit when ("适用于需要…的场景"), an explicit Use-when trigger; not a 2 because the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	Includes natural phrases a user would say — "发布到微信公众号", "Markdown 文件", "网页链接", "微信样式 standard/viral" — giving good coverage of natural terms; not a 2 because common user phrasings are present rather than only jargon.	3 / 3
Distinctiveness Conflict Risk	"发布到微信公众号" is a narrow, distinct niche with specific triggers unlikely to conflict with other skills; not a 2 because it is clearly distinguishable rather than merely somewhat specific.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	15 / 16 Passed

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/clawhub/wechat-article-publisher/2/SKILL.md
Commit: f618458

Reviewed: about 12 hours ago

Table of Contents

Discovery Implementation Validation

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.