multi-platform-publish-orchestrator
Skill1 starsChanged 34 days agoMITView on GitHub
当 agent 需要按 JSON 配置顺序执行多平台发布、统一 cookie/进度阶段、并兼容 Linux/macOS/Windows 时使用。本仓库引擎为 TypeScript + Playwright,已实现 tencent / douyin / kuaishou / xiaohongshu / wechatmp / zhihu / baijiahao 七个平台。 Use when the user wants to publish the same content to multiple platforms in one run.
- Reads credentials
- Installs packages
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- puppyfront-web/social-publish-skillsedited, first seen Oct 17, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- puppyfront-web/social-publish-skills★ 1487% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ark-agent-plan-imageSkill
- ark-seedance-videoSkill
- ark-seedream-imageSkill
- bilibili-uploadSkill
- chinese-ttsSkill
- douyin-publishSkill
- dreamina-canvas-cliSkill
- feishu-bitableSkill
- image-to-videoSkill
- media-verifySkill
- quad-platform-publishSkill
- tangshi-data-reviewSkill
- tangshi-pipelineSkill
- tencent-uploadSkill
- video-composeSkill
- video-coverSkill
- video-pipelineSkill
- xiaohongshu-skillsSkill
The file
Files
本机引擎位置
引擎已安装于 %USERPROFILE%\.tools\social-publish-skills(引擎根目录)。
所有 node dist/cli.js ... 命令必须先 Set-Location 到该目录执行;依赖与 dist/ 已就绪,缺文件时在引擎根目录 npm run build(Windows 构建坑已修)。
浏览器走系统 Chrome(channel: chrome),不要跑 npx playwright install chromium(下载源被墙)。
Cookie 目录:%USERPROFILE%\.social-publish-skills\cookies\。
多平台发布统一调度 Skill
Agent 执行规则(重要)
- 默认由 Agent 在仓库根目录直接执行命令,不要让用户手动复制粘贴命令。
- 只有在必须人工完成的步骤(扫码、短信验证码、账号确认、终端按 Enter、Inspector Resume)才请求用户介入。
- 若缺少
dist/cli.js或依赖未安装,Agent 先自动执行npm install、npx playwright install chromium、npm run build,再继续业务命令。
标准执行模板(全自动优先)
- 在仓库根目录检查
dist/cli.js是否可用。 - 若不可用,自动执行
npm install、npx playwright install chromium、npm run build。 - 自动执行
node dist/cli.js orchestrate --config <path>或verify-scan-login。 - 仅在扫码、Inspector Resume 或显式人工确认时暂停并请求用户操作;完成后由 Agent 继续后续步骤。
执行入口
在 social-publish-skills 根目录:
npm install
npx playwright install chromium # 本机首次
npm run build # 生成 dist/(仓库不提交 dist)
node dist/cli.js orchestrate --config path/to/config.json示例配置:references/orchestrator.config.example.json(本 skill 目录下)。可选字段 data_dir 会写入 process.env.SOCIAL_PUBLISH_DATA_DIR。
Shell 封装:scripts/examples/run_orchestrate.sh。
扫码登录链路验收(人工扫码,机器校验):node dist/cli.js verify-scan-login --account <别名>。抖音/快手 login 扫码阶段默认轮询;视频号多依赖 Inspector Resume 或 SOCIAL_PUBLISH_LOGIN_STDIN=1。各站保存后默认无头 check,可用 --skip-verify 关闭。
核心实现
src/orchestrator.ts:读取任务列表,按 platform 分发src/platforms/tencent.ts:微信视频号src/platforms/douyin.ts:抖音创作者平台src/platforms/kuaishou.ts:快手创作者平台src/platforms/xiaohongshu.ts:小红书创作者平台src/platforms/wechatmp.ts:微信公众号图文src/platforms/zhihu.ts:知乎文章src/platforms/baijiahao.ts:百家号文章
已支持平台
| 平台 | CLI 子命令 | cookie 路径 | 状态 |
|---
---|-----------|------------|------|
| 微信视频号 | tencent | cookies/tencent/<account>.json | 已实现 |
| 抖音 | douyin | cookies/douyin/<account>.json | 已实现 |
| 快手 | kuaishou | cookies/kuaishou/<account>.json | 已实现 |
| 小红书 | xiaohongshu | cookies/xiaohongshu/<account>.json | 已实现 |
| 微信公众号图文 | wechatmp | cookies/wechatmp/<account>.json | 已实现 |
| 知乎文章 | zhihu | cookies/zhihu/<account>.json | 已实现 |
| 百家号文章 | baijiahao | cookies/baijiahao/<account>.json | 已实现 |
扩展新平台
在 src/platforms/ 实现发布函数 → 在 orchestrator.ts 增加 switch 分支 → 在 cli.ts 添加子命令 → 更新本 SKILL 与 references/orchestrator.config.example.json(或同类示例)。
进度协议
8 阶段:INIT → COOKIE_CHECK → COOKIE_REFRESH → OPEN_PUBLISH_PAGE → UPLOAD_START → UPLOAD_TRANSFERRING → PUBLISHING → DONE
参考
references/orchestration-contract.mdreferences/runtime-requirements-cross-platform.mdreferences/browser-cookie-compatibility.mdreferences/troubleshooting.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

