baijiahao-article-upload
Skill14 starsChanged 6 months agoMITView on GitHub
当 agent 需要完成百家号登录、cookie 校验、自动导入 Markdown/GitHub/网页内容并发布百家号文章(默认保存草稿)时使用。使用本仓库 TypeScript 引擎与 Playwright;命令为 node dist/cli.js baijiahao check|login|publish(或 npm run dev --)。
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- bilibili-uploadSkill
- content-toolkitSkill
- douyin-upload-promptSkill
- douyin-uploadSkill
- growth-content-opsSkill
- growth-content-strategySkill
- growth-content-writingSkill
- kuaishou-uploadSkill
- multi-platform-publish-orchestratorSkill
- personal-knowledge-wikiSkill
- tencent-uploadSkill
- wechatmp-article-uploadSkill
- xiaohongshu-uploadSkill
- zhihu-article-uploadSkill
The file
Files
百家号文章发布 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、安全验证、终端按 Enter)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。 - 自动执行目标命令(
check/login/publish)。 - 仅在扫码、验证码、安全验证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(本仓库)
在 social-publish-skills 根目录:
node dist/cli.js baijiahao check --account <name>
node dist/cli.js baijiahao login --account <name>
node dist/cli.js baijiahao publish \
--account <name> \
--source <absolute_markdown_path_or_url> \
--title "..."来源类型
--source-type auto:默认,自动识别--source-type markdown:本地 Markdown(必须绝对路径)--source-type github:GitHub URL(优先读取 README 或 blob 文件)--source-type url:通用网页 URL(抓取正文后转换)
发布策略
- 默认保存草稿或等待编辑器自动保存(推荐)
- 仅在用户明确要求时增加
--publish直接发布
功能概览
| 功能 | CLI |
| cookie 校验 | baijiahao check |
| 登录 / 刷新 storageState | baijiahao login |
| 发布文章(默认草稿) | baijiahao publish |
cookie 持久化
- 默认目录:
$SOCIAL_PUBLISH_DATA_DIR/cookies/baijiahao/<account>.json - 发布前后引擎会读写 Playwright
storageState
平台边界
- 支持百家号文章,不支持百家号视频、动态、小视频或高级分发设置。
- 百度/百家号风控可能出现安全验证;使用
SOCIAL_PUBLISH_HEADLESS=0时按浏览器提示完成验证。 - 本地 Markdown 来源必须使用绝对路径。
进度可视化
引擎在控制台输出 ⏳/✅/❌ [step/total] STAGE - message;agent 应同步转述给用户。
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.

