agentleFS
autoclaw-ccautoclaw-cc/xiaohongshu-mcp-skills/CLAUDE.md

xiaohongshu-mcp-skills

CLAUDE.md269 starsChanged 9 months agoMITView on GitHub

Skills 层不包含业务实现代码,所有功能通过调用 xiaohongshu-mcp 的 MCP 工具完成。 每个 SKILL.md 包含 YAML frontmatter(name + description)和 Markdown 正文。 正文必须包含:输入判断、约束条件、执行流程(含 MCP 工具调用)、失败处理。 编写原则: - 控制在 200 行以内 - Destructive 操作需用户确认 - 工具名和参数必须与 xiaohongshu-mcp 源码一致

The file

Files
CLAUDE.md

CLAUDE.md

Skills 层不包含业务实现代码,所有功能通过调用 xiaohongshu-mcp 的 MCP 工具完成。

MCP 工具映射表

MCP 工具类型对应 Skill说明
check_login_statusReadOnlyxhs-login检查登录状态
get_login_qrcodeReadOnlyxhs-login获取登录二维码
delete_cookiesDestructivexhs-login删除 cookies 重置登录
publish_contentDestructivepost-to-xhs发布图文笔记
publish_with_videoDestructivepost-to-xhs发布视频笔记
list_feedsReadOnlyxhs-explore获取推荐流
search_feedsReadOnlyxhs-search搜索笔记
get_feed_detailReadOnlyxhs-explore获取笔记详情和评论
user_profileReadOnlyxhs-profile获取用户主页
like_feedDestructivexhs-interact点赞/取消点赞
favorite_feedDestructivexhs-interact收藏/取消收藏
post_comment_to_feedDestructivexhs-interact发表评论
reply_comment_in_feedDestructivexhs-interact回复评论

SKILL.md 编写规范

每个 SKILL.md 包含 YAML frontmatter(name + description)和 Markdown 正文。

正文必须包含:输入判断、约束条件、执行流程(含 MCP 工具调用)、失败处理。

编写原则:

  • 控制在 200 行以内
  • Destructive 操作需用户确认
  • 工具名和参数必须与 xiaohongshu-mcp 源码一致

参考资源

  • xiaohongshu-mcp 源码:~/src/zy/xiaohongshu-mcp(Go MCP 服务)

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.