baoyu-post-to-wechat
Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citations for WeChat-friendly output. Use when user mentions "发布公众号", "post to wechat", "微信公众号", or "贴图/图文/文章".
81
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
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.
This is an excellent skill description that covers all dimensions thoroughly. It provides specific capabilities (article posting, image-text posting, markdown conversion with citation handling), includes bilingual trigger terms that users would naturally use, has an explicit 'Use when' clause, and occupies a very distinct niche around WeChat Official Account publishing.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: posting articles via API or Chrome CDP, supporting HTML/markdown/plain text input, image-text posting with multiple images, and converting external links into bottom citations. Very detailed and actionable. | 3 / 3 |
Completeness | Clearly answers both 'what' (posts content to WeChat Official Account with various formats and conversion features) and 'when' (explicit 'Use when...' clause with specific trigger phrases in both languages). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms in both English and Chinese: '发布公众号', 'post to wechat', '微信公众号', '贴图/图文/文章'. These are exactly what bilingual users would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche targeting WeChat Official Account posting specifically, with Chinese-language triggers and platform-specific details like Chrome CDP and WeChat-friendly citation formatting. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with excellent workflow clarity, featuring concrete commands, clear step sequences, and proper validation checkpoints. However, it suffers significantly from verbosity — the multi-account support, credential resolution, and configuration details bloat the main file when they should be in reference documents. The progressive disclosure structure exists but is underutilized, with too much detail kept inline.
Suggestions
Move the entire Multi-Account Support section (account selection, credential resolution, Chrome profile, CLI --account) to a reference file like references/multi-account.md, leaving only a brief mention and link in SKILL.md
Move the detailed EXTEND.md configuration (examples, key tables, priority rules) to references/config/extend-reference.md, keeping only the check-existence commands and a link in the main file
Consolidate the cross-platform shell examples (bash + PowerShell) — either pick one primary platform or move the PowerShell variants to a separate reference, since providing both doubles the token cost for each check
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It includes extensive configuration details (multi-account support, credential resolution chains, EXTEND.md examples, PowerShell equivalents) that could be offloaded to reference files. The multi-account section alone is massive and could be a separate reference. Tables explaining EXTEND.md paths, check-fix mappings, and feature comparisons add significant bulk. | 1 / 3 |
Actionability | The skill provides fully executable bash/PowerShell commands, concrete CLI invocations with all parameters, specific file paths, and copy-paste ready code blocks. The credential setup guide, publishing commands, and completion report templates are all highly specific and actionable. | 3 / 3 |
Workflow Clarity | The article posting workflow has a clear numbered checklist (Steps 0-5) with explicit validation checkpoints: credential checking before publishing, cover image verification with a 5-step fallback chain, metadata validation with prompts for missing fields, and a 'stop and request' gate if cover image is missing. The progress checklist at the top is a nice touch. | 3 / 3 |
Progressive Disclosure | While there are references to external files (references/image-text-posting.md, references/article-posting.md, references/config/first-time-setup.md), the SKILL.md itself contains enormous amounts of detail that should be in those reference files — particularly the multi-account support section, credential resolution chains, and Chrome profile configuration. The main file tries to be both overview and comprehensive reference. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
63%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 7 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (509 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 7 / 11 Passed | |
- Repository
- jimliu/baoyu-skills
- Commit
9eb032a
- 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.