Post to WeChat
Post to WeChat is a skill in JimLiu/baoyu-skills, not a leftover path at skills/post-to-wechat. The live folder is skills/baoyu-post-to-wechat. SKILL.md name is baoyu-post-to-wechat, version 1.118.2. It posts to a WeChat Official Account via API or Chrome CDP, for 文章 (HTML / markdown / text) and 贴图 (image-text, formerly 图文). README install is npx skills add jimliu/baoyu-skills. Credentials go in ~/.baoyu-skills/.env or a project .baoyu-skills/.env. Do not commit those files.
Compare Claude Skills if you wanted the SKILL.md mechanism, Claude Code if you wanted the host CLI, and NotebookLM Skill if you wanted another third-party skill.
Key Features
- Path moved: Leftover
skills/post-to-wechat404s. Quotebaoyu-post-to-wechat. - Two post types: Article scripts and image-text (贴图) via browser. API path is for articles.
- Markdown becomes WeChat HTML:
scripts/md-to-wechat.tsplus default bottom citations for ordinary external links. - Needs Bun and secrets: README wants Node plus
npx bun. WeChat API credentials are local env, not a public dollar seat.
Use Cases
- People who already have Official Account credentials and will keep
.envoff git. - People installing only the WeChat subset (
baoyu-cover-image,baoyu-article-illustrator,baoyu-post-to-wechat) as the README suggests. - Teams that will accept browser CDP when the API path is not enough.
Limitation: This is not a WeChat-hosted product. Official Account policy, review, and API quotas are Tencent's.
Pricing
GitHub on 2026-08-18.
| Piece | Price | Notes from first-party pages |
|---|---|---|
| baoyu-skills | $0 | MIT. 25,089 stars. npx skills add jimliu/baoyu-skills. |
| WeChat Official Account | Confirm Tencent | Credentials and review are not this repo. |
| Host agent | Confirm Claude Code / Codex | Skill runs in your agent. |
If a leftover blog still points at skills/post-to-wechat, treat this table as the source.
Getting Started
- Open github.com/JimLiu/baoyu-skills and the
baoyu-post-to-wechatfolder. - Confirm Claude Skills if you are installing via Agent Skills.
- Put credentials in the documented
.envpaths. Do not commit them. - Do not paste the leftover unprefixed path.
Frequently Asked Questions
Is the old GitHub tree still valid?
The leftover skills/post-to-wechat path 404s. Use skills/baoyu-post-to-wechat.
Is it official WeChat software?
No. It is a third-party MIT skill that calls WeChat APIs or a browser.
Same as Anthropic example skills?
No. Those live in anthropics/skills. This is JimLiu/baoyu-skills.
Alternatives
- Claude Skills: How skills load.
- NotebookLM Skill: Another third-party Claude Code skill.
- Doc Co-Authoring: Anthropic writing example, not a publisher.
Tips
- Quote 25,089 stars, MIT, and
baoyu-post-to-wechat. - Keep secrets in
.env, not in the skill page. - Confirm WeChat API docs before you treat a draft post as published.
Conclusion
Post to WeChat is the MIT baoyu-post-to-wechat skill in a 25,089-star repo, not a leftover unprefixed path. Start at github.com/JimLiu/baoyu-skills/tree/main/skills/baoyu-post-to-wechat, then decide whether Claude Skills already covers how you install it.
Comments
No comments yet. Be the first to comment!
Related Tools
Related Insights
Anthropic Subagent: The Multi-Agent Architecture Revolution
Deep dive into Anthropic multi-agent architecture design. Learn how Subagents break through context window limitations, achieve 90% performance improvements, and real-world applications in Claude Code.
Seven AI Coding CLIs, Six Months: No Matter How Strong the Model, Work Needs Supervision
Claude Code, Codex, opencode, pi, omp and DeepSeek Harness all have personalities. After six months of deep use I run a division of labor: pi for the fastest cheapest reviews, omp for complex PRs, DeepSeek Harness on V4 Flash for high-frequency low-cost review, and Claude Code, Qoder and Cursor for writing. No matter how strong the model, work needs supervision — ideally from an independent third party.
Skills + Hooks + Plugins: How Anthropic Redefined AI Coding Tool Extensibility
An in-depth analysis of Claude Code's trinity architecture of Skills, Hooks, and Plugins. Explore why this design is more advanced than GitHub Copilot and Cursor, and how it redefines AI coding tool extensibility through open standards.