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。
67
55%
Does it follow best practices?
Impact
89%
3.06xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0731coderlee-sudo/wechat-publisher/wechat-publisher/SKILL.mdQuality
Discovery
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 strong in specificity and distinctiveness, clearly identifying a niche tool for publishing Markdown content to WeChat Official Accounts via wenyan-cli. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The trigger terms are decent but could benefit from including common user phrasings and English equivalents.
Suggestions
Add an explicit 'Use when...' clause, e.g., '当用户需要将 Markdown 文章发布到微信公众号、排版公众号文章、或提到 wenyan/微信排版时使用。'
Include common user trigger variations in both Chinese and English, such as 'WeChat article', '公众号排版', '微信发文', 'publish to WeChat' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: publishing Markdown to WeChat Official Account drafts, multi-theme support, code highlighting, and automatic image uploading. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (publish Markdown to WeChat drafts with themes, code highlighting, image upload), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes good domain-specific terms like 'Markdown', '微信公众号' (WeChat Official Account), '草稿箱' (drafts), 'wenyan-cli', '代码高亮' (code highlighting), but misses common user variations like 'WeChat', 'MP', 'publish article', or English equivalents that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche: the combination of Markdown, WeChat Official Account (微信公众号), wenyan-cli, and draft publishing is highly specific and unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with concrete, executable commands and good troubleshooting coverage, but severely undermined by extreme verbosity and repetition. The same information (frontmatter requirements, cover image options) is repeated 2-3 times, and the document includes unnecessary sections (changelog, license, feature checklists) that waste context window. The lack of any content splitting or bundle structure makes this a monolithic wall of text.
Suggestions
Eliminate the repeated frontmatter/cover explanations — consolidate into a single section with one set of examples and one warning about the cover requirement.
Remove changelog, license, feature checklist, and reference links sections — these add no actionable value for Claude.
Replace hardcoded user paths (/Users/leebot/, /Users/bruce/) with generic placeholders like <workspace_path> or $HOME.
Split theme catalog and troubleshooting into separate referenced files (e.g., THEMES.md, TROUBLESHOOTING.md) to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with heavy repetition. The frontmatter requirements (title + cover are mandatory) are explained at least 3 separate times with nearly identical content. The cover image options (relative/absolute/network) are shown twice. Feature checklists, emoji decorations, and changelog/license sections add no value for Claude. Hardcoded user paths (/Users/leebot/, /Users/bruce/) waste tokens. | 1 / 3 |
Actionability | Provides fully executable, copy-paste ready commands throughout: installation, environment setup, publish commands with various theme options, custom theme management, and troubleshooting with specific error messages mapped to solutions. The frontmatter examples are concrete and complete. | 3 / 3 |
Workflow Clarity | The high-level workflow (prepare → publish → review) is listed but lacks validation checkpoints. There's no explicit step to verify environment variables are set before publishing, no feedback loop for handling upload failures, and no verification that the article actually landed in the draft box. The troubleshooting section partially compensates but isn't integrated into the workflow. | 2 / 3 |
Progressive Disclosure | Everything is in one monolithic file with no references to supporting bundle files. Content that could be split (theme catalog, troubleshooting, frontmatter examples) is all inline, creating a very long document. No bundle files are provided despite the skill referencing scripts/publish.sh and TOOLS.md, making navigation unclear. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 |
Total | 9 / 11 Passed | |
- Repository
- NeverSight/skills_feed
- Commit
83d60e9
- 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.