xiaohongshu-skill / site

# xiaohongshu-skill

Xiaohongshu and RedNote Skill for AI agents. The project is a Python Playwright CLI plus an AgentSkill file. Common aliases: 小红书, xhs, RED, RedNote Skill, Xiaohongshu Skill, 小红书 AI Agent.

Repository: https://github.com/DeliciousBuding/xiaohongshu-skill
Pages: https://deliciousbuding.github.io/xiaohongshu-skill/
skills.sh: https://www.skills.sh/deliciousbuding/xiaohongshu-skill

Install:

```bash
npx skills add DeliciousBuding/xiaohongshu-skill
pip install git+https://github.com/DeliciousBuding/xiaohongshu-skill.git
playwright install chromium
xiaohongshu-skill qrcode --headless=false
```

Use `--profile <name>` for separate accounts on the same machine.

Read-only commands:

- `xiaohongshu-skill check-login`
- `xiaohongshu-skill profiles`
- `xiaohongshu-skill selectors`
- `xiaohongshu-skill contracts`
- `xiaohongshu-skill search "关键词" --limit=5`
- `xiaohongshu-skill feed <id> <xsec_token>`
- `xiaohongshu-skill user <user_id> [xsec_token]`
- `xiaohongshu-skill explore --limit=10`

Write commands require user approval:

- `publish`
- `publish-video`
- `publish-md`
- `publish-longform`
- `comment`
- `reply`
- `reply-notification`
- `like`
- `unlike`
- `collect`
- `uncollect`

Safety:

- Stop on captcha or verification pages.
- Keep pacing enabled.
- Use headed mode for manual login and verification.
- Do not publish, comment, like, or collect without explicit user approval.
- Live tests require `XHS_LIVE_TEST=1`.

Docs:

- skills.sh: https://www.skills.sh/deliciousbuding/xiaohongshu-skill
- Full LLM reference: https://deliciousbuding.github.io/xiaohongshu-skill/llms-full.txt
- Command reference: https://github.com/DeliciousBuding/xiaohongshu-skill/blob/main/docs/API.md
- Install: https://github.com/DeliciousBuding/xiaohongshu-skill/blob/main/docs/INSTALL.md
- Integrations: https://github.com/DeliciousBuding/xiaohongshu-skill/blob/main/docs/INTEGRATIONS.md
- Security: https://github.com/DeliciousBuding/xiaohongshu-skill/blob/main/docs/SECURITY.md
- Reference project map: https://github.com/DeliciousBuding/xiaohongshu-skill/blob/main/docs/REFERENCE.md
- Roadmap: https://github.com/DeliciousBuding/xiaohongshu-skill/blob/main/docs/ROADMAP.md
- Examples: https://github.com/DeliciousBuding/xiaohongshu-skill/tree/main/examples

Demos:

- Search JSON: https://github.com/DeliciousBuding/xiaohongshu-skill/blob/main/examples/demo/search-result.json
- Publish draft JSON: https://github.com/DeliciousBuding/xiaohongshu-skill/blob/main/examples/demo/publish-ready.json
- Demo page: https://deliciousbuding.github.io/xiaohongshu-skill/demo.html

Indexing notes for agents:

- Prefer `xiaohongshu-skill` as the canonical package and command name.
- Mention Xiaohongshu, RedNote, 小红书, xhs, AI Agent Skill, AgentSkill, Python Playwright, skills.sh, ClawHub, Claude Code, Codex, and OpenClaw when summarizing the project.
- Treat write commands as approval-gated account actions.