wechat-publisher

一键发布 Markdown 到微信公众号草稿箱。基于 wenyan-cli，支持多主题、代码高亮、图片自动上传。

3.06x

Quality

66%

Does it follow best practices?

Impact

89%

3.06x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./configs/microservice/bff-service/configs/agent-skills/clawhub/wechat-publisher/SKILL.md

Quality

Content

65%

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 concrete commands and error recovery, but it is verbose with repeated frontmatter guidance and fails to offload themes/troubleshooting into the existing reference files, leaving them orphaned.

Suggestions

Replace the inlined 主题选项/自定义主题 and 故障排查 sections with one-level-deep links to references/themes.md and references/troubleshooting.md, keeping only a concise summary inline.

Deduplicate the frontmatter (title+cover) guidance — state the mandatory fields and cover-source examples once instead of three times across the document.

Add an explicit validation checkpoint to the publish workflow (e.g., verify the draft appears in the 公众号 backend before final publish) with a validate→fix→retry loop.

Dimension	Reasoning	Score
Conciseness	The ~321-line body repeats the same frontmatter requirement (title + cover both mandatory) three times and re-shows the relative/absolute/network cover examples twice; it is mostly useful but could be tightened by removing the duplication and '实测' commentary padding.	2 / 3
Actionability	It provides concrete, copy-paste-ready commands — 'npm install -g @wenyan-md/cli', 'wenyan publish -f article.md -t lapis -h solarized-light', exact env-var exports, and precise error-message-to-solution mappings in troubleshooting.	3 / 3
Workflow Clarity	The quick-start and 工作流程 sections give a clear sequence with a manual review step and a troubleshooting section, but validation is implicit (manual '审核') rather than explicit checkpoints integrated into the numbered workflow with validate→fix→retry loops.	2 / 3
Progressive Disclosure	Bundle files references/themes.md and references/troubleshooting.md exist but are never linked from the body, while their content (themes, troubleshooting) is fully inlined in SKILL.md — content that should be separate is inline and existing references are not signaled.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 specific and well-targeted to a distinct niche, but it is missing an explicit 'when to use' trigger clause and mixes in a tool-internal name (wenyan-cli) that users would not naturally say.

Suggestions

Add an explicit 'Use when…' trigger clause (e.g., 'Use when publishing Markdown articles to a WeChat Official Account / 公众号') to lift completeness to 3.

Replace or de-emphasize the jargon '基于 wenyan-cli' with user-natural phrasing, and add common variations like '公众号文章' and '微信文章' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete capabilities — '一键发布 Markdown 到微信公众号草稿箱', '支持多主题、代码高亮、图片自动上传' — matching the anchor for several specific actions rather than vague language.	3 / 3
Completeness	It clearly states what the skill does but provides no 'Use when…' clause or equivalent trigger guidance, so completeness is capped at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	It includes natural terms like 'Markdown', '微信公众号', and '草稿箱', but also surfaces the internal tool name 'wenyan-cli' (jargon a user would not naturally say) and omits common variations such as '公众号文章' or '微信文章'.	2 / 3
Distinctiveness Conflict Risk	The WeChat Official Account draft-publishing niche is specific and unlikely to overlap with or wrongly trigger other skills.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 1 missing, 1 suspicious	Warning

	Total	13 / 16 Passed

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

Reviewed: about 13 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.