Token导航 LogoToken导航TokenDH.com
开发敏感数据github未标认证来源可访问clear审计异常

baoyu-post-to-wechat宝玉发微信

Agent Skill

baoyu-post-to-wechat 用于处理浏览器自动化、网页检查和页面信息提取,适合在 Codex、Claude、Cursor、Gemini CLI 中需要让 Agent 打开页面、读取网页或验证前端流程时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

515,088

周安装

21,866

GitHub Stars

16,797

下载量

180,456
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:baoyu-post-to-wechat(宝玉发微信)
来源仓库:https://github.com/jimliu/baoyu-skills
仓库路径:skills/baoyu-post-to-wechat
安装命令:
npx skills add https://github.com/jimliu/baoyu-skills --skill baoyu-post-to-wechat
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/jimliu/baoyu-skills --skill baoyu-post-to-wechat

简介

通过 API 或浏览器自动化将文章和图文帖子发布到微信公众号。

  • 支持三种输入格式:纯文本、Markdown 和 HTML,并自动生成元数据(标题、摘要、封面图片)
  • 两种发布方法:基于 API 的快速草稿(需要凭据)和基于浏览器的发布(需要 Chrome 登录)
  • 通过 EXTEND.md 配置使用每个帐户凭据、Chrome 配置文件和发布首选项进行多帐户管理
  • Markdown 文章自动将外部链接转换为底部引用,以实现微信友好的格式;图文帖子最多支持 9 张图片并自动压缩
  • 可定制的主题(默认、优雅、简单、现代)、颜色、作者和评论设置(打开/关闭、仅限粉丝)存储在项目或用户级配置文件中

SKILL.md

Post to WeChat Official Account

User Input Tools

When this skill prompts the user, follow this tool-selection rule (priority order):

  1. Prefer built-in user-input tools exposed by the current agent runtime — e.g., AskUserQuestion, request_user_input, clarify, ask_user, or any equivalent.
  2. Fallback: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each question.
  3. Batching: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question, ask them one at a time in priority order.

Concrete AskUserQuestion references below are examples — substitute the local equivalent in other runtimes.

Language

Respond in the user's language. If they write in Chinese, reply in Chinese; if English, English. Keep technical tokens (paths, flags, field names) in English.

Script Directory

{baseDir} = this SKILL.md's directory. Resolve ${BUN_X}: prefer bun; else npx -y bun; else suggest brew install oven-sh/bun/bun.

ScriptPurpose
scripts/wechat-browser.tsImage-text posts (图文)
scripts/wechat-article.tsArticle posting via browser (文章)
scripts/wechat-api.tsArticle posting via API (文章)
scripts/md-to-wechat.tsMarkdown → WeChat-ready HTML with image placeholders
scripts/check-permissions.tsVerify environment & permissions

Preferences (EXTEND.md)

Check these paths in order; first hit wins:

PathScope
.baoyu-skills/baoyu-post-to-wechat/EXTEND.mdProject
${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-post-to-wechat/EXTEND.mdXDG
$HOME/.baoyu-skills/baoyu-post-to-wechat/EXTEND.mdUser home

Found → read, parse, apply. Not found → run first-time setup (references/config/first-time-setup.md) before anything else.

Minimum keys (case-insensitive, accept 1/0 or true/false):

KeyDefaultMapping
default_authoremptyFallback for author when CLI/frontmatter not provided
need_open_comment1articles[].need_open_comment in draft/add
only_fans_can_comment0articles[].only_fans_can_comment in draft/add

Recommended EXTEND.md:

default_theme: default
default_color: blue
default_publish_method: api
default_author: 宝玉
need_open_comment: 1
only_fans_can_comment: 0
chrome_profile_path: /path/to/chrome/profile

Theme options: default, grace, simple, modern. Color presets: blue, green, vermilion, yellow, purple, sky, rose, olive, black, gray, pink, red, orange (or hex).

Value priority: CLI args → frontmatter → EXTEND.md (account-level → global) → skill defaults.

Multi-Account Support

EXTEND.md supports an accounts: block for managing multiple Official Accounts. With 2+ entries, the workflow inserts a Step 0.5 to prompt for account selection (or auto-selects based on default: true or --account <alias>).

Full details — compatibility rules, per-account keys, credential resolution, per-account Chrome profiles, CLI usage — in references/multi-account.md.

Pre-flight Check (Optional)

Before first use, suggest the environment check (user can skip):

${BUN_X} {baseDir}/scripts/check-permissions.ts

Checks: Chrome, profile isolation, Bun, Accessibility, clipboard, paste keystroke, API credentials, Chrome conflicts.

Check failsFix
ChromeInstall Chrome or set WECHAT_BROWSER_CHROME_PATH
Profile dirShared profile at baoyu-skills/chrome-profile
Bun runtimebrew install oven-sh/bun/bun or npm install -g bun
Accessibility (macOS)System Settings → Privacy & Security → Accessibility → enable terminal app
Clipboard copyEnsure Swift/AppKit (macOS: xcode-select --install)
Paste keystroke (Linux)Install xdotool (X11) or ydotool (Wayland)
API credentialsFollow guided setup in Step 2, or set in .baoyu-skills/.env

Image-Text Posting (图文)

Short posts with multiple images (up to 9):

${BUN_X} {baseDir}/scripts/wechat-browser.ts --markdown article.md --images ./images/
${BUN_X} {baseDir}/scripts/wechat-browser.ts --title "标题" --content "内容" --image img.png --submit

Details: references/image-text-posting.md.

Article Posting Workflow (文章)

- [ ] Step 0: Load preferences (EXTEND.md)
- [ ] Step 0.5: Resolve account (multi-account only — see references/multi-account.md)
- [ ] Step 1: Determine input type
- [ ] Step 2: Select method and configure credentials
- [ ] Step 3: Resolve theme/color and validate metadata
- [ ] Step 4: Publish to WeChat
- [ ] Step 5: Report completion

Step 0: Load Preferences

Check and load EXTEND.md (see "Preferences" above). If not found, complete first-time setup before any other questions. Resolve and cache for later steps: default_theme, default_color, default_author, need_open_comment, only_fans_can_comment.

Step 1: Determine Input Type

InputDetectionNext
HTML filePath ends .html, file existsSkip to Step 3
Markdown filePath ends .md, file existsStep 2
Plain textNot a file path, or file doesn't existSave to markdown, then Step 2

Plain-text handling:

  1. Generate slug (first 2-4 meaningful words, kebab-case; translate Chinese to English for the slug).
  2. Save to post-to-wechat/YYYY-MM-DD/<slug>.md (create directory if needed).
  3. Continue as a markdown file.

Step 2: Select Publishing Method and Configure

Ask method unless specified in EXTEND.md or CLI:

MethodSpeedRequires
api (Recommended)FastAPI credentials
browserSlowChrome + logged-in session

API selected + missing credentials → run guided setup per references/api-setup.md (writes to .baoyu-skills/.env).

Step 3: Resolve Theme/Color and Validate Metadata

  1. Theme: CLI --theme → EXTEND.md default_themedefault (first match wins; do NOT ask if resolved).
  2. Color: CLI --color → EXTEND.md default_color → omit (theme default applies).
  3. Validate metadata (frontmatter for markdown, meta tags for HTML):
FieldMissing →
TitleAsk, or press Enter to auto-generate from content
SummaryFrontmatter descriptionsummary → ask or auto-generate
AuthorCLI --author → frontmatter author → EXTEND.md default_author

Auto-generation: title = first H1/H2 or first sentence; summary = first paragraph, truncated to 120 chars.

  1. Cover image (required for API article_type=news): CLI --cover → frontmatter (coverImage / featureImage / cover / image) → imgs/cover.png → first inline image → stop and request one if still missing.

Step 4: Publish

Important — never pre-convert markdown to HTML. Publishing scripts handle the conversion internally and the two methods render images differently: API renders <img> tags for upload, browser uses placeholders for paste-and-replace. Passing a pre-converted HTML breaks one or the other.

Markdown citation default: for markdown input, ordinary external links are converted to bottom citations by default. Use --no-cite only if the user explicitly wants to keep inline links. Existing HTML input is left as-is.

API method (accepts .md or .html):

${BUN_X} {baseDir}/scripts/wechat-api.ts <file> --theme <theme> [--color <color>] [--title <title>] [--summary <summary>] [--author <author>] [--cover <cover_path>] [--no-cite]

Always pass --theme even if it's default. Only pass --color when explicitly set by the user or EXTEND.md.

draft/add payload rules:

  • Endpoint: POST https://api.weixin.qq.com/cgi-bin/draft/add?access_token=ACCESS_TOKEN
  • article_type: news (default) or newspic
  • For news, include thumb_media_id (cover required)
  • Always include need_open_comment (default 1) and only_fans_can_comment (default 0) in the request body, even if the CLI doesn't expose them

Browser method (accepts --markdown or --html):

${BUN_X} {baseDir}/scripts/wechat-article.ts --markdown <markdown_file> --theme <theme> [--color <color>] [--no-cite]
${BUN_X} {baseDir}/scripts/wechat-article.ts --html <html_file>

Step 5: Completion Report

WeChat Publishing Complete!

Input: [type] - [path]
Method: [API | Browser]
Theme: [theme] [color if set]

Article:
• Title: [title]
• Summary: [summary]
• Images: [N] inline
• Comments: [open/closed], [fans-only/all]    ← API method only

Result:
✓ Draft saved to WeChat Official Account
• media_id: [media_id]                         ← API method only

Next Steps (API):
→ Manage drafts: https://mp.weixin.qq.com (登录后进入「内容管理」→「草稿箱」)

Files created:
[• post-to-wechat/YYYY-MM-DD/slug.md (if plain text input)]
[• slug.html (converted)]

Feature Comparison

FeatureImage-TextArticle (API)Article (Browser)
Plain text input
HTML input
Markdown inputTitle/content
Multiple images✓ (up to 9)✓ (inline)✓ (inline)
Themes
Auto-generate metadata
Default cover fallback (imgs/cover.png)
Comment control
Requires Chrome
Requires API credentials
SpeedMediumFastSlow

Troubleshooting

IssueFix
Missing API credentialsFollow guided setup in Step 2
Access token errorVerify credentials valid and not expired
Not logged in (browser)First run opens browser — scan QR to log in
Chrome not foundSet WECHAT_BROWSER_CHROME_PATH
Title/summary missingUse auto-generation or provide manually
No cover imageAdd frontmatter cover or place imgs/cover.png in article directory
Wrong comment defaultsCheck need_open_comment / only_fans_can_comment in EXTEND.md
Paste failsCheck system clipboard permissions

References

FileContent
references/image-text-posting.mdImage-text parameters, auto-compression
references/article-posting.mdArticle themes, image handling
references/multi-account.mdMulti-account compatibility, credentials, Chrome profiles, CLI
references/api-setup.mdGuided credential setup
references/config/first-time-setup.mdFirst-time EXTEND.md setup

Extension Support

Custom configurations via EXTEND.md. See "Preferences" for paths and supported options.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

26.8%
按下载量换算48,362

OpenCode

24.94%
按下载量换算45,006

Gemini CLI

16.82%
按下载量换算30,353

Cursor

11.72%
按下载量换算21,149

Antigravity

7.4%
按下载量换算13,354

Codex

3.5%
按下载量换算6,316

安全审计

Gen Agent Trust Hub

可疑

Socket

通过

Snyk

未通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。

来源信息

继续浏览同类 Skills