agentleFS
ArchAIHarnessArchAIHarness/agent-workflows/skills/content/xiaohongshu-publisher/SKILL.md

xiaohongshu-publisher

Skill1 starsChanged 5 months agoMITView on GitHub

Use when preparing or publishing Xiaohongshu/小红书/XHS/RED notes, 小红书图文笔记, image cards, hashtags, creator-platform drafts, or safe Xiaohongshu publishing workflows.

  • Reads credentials

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If browser automation is available, open the creator platform and fill draft fields only after the package is ready.

    line 25
  2. Very specific:

    Stop before publish unless the user explicitly says 确认发布到小红书.

    line 26
  3. Distinctive:

    Prefer 1 cover card plus 3-8 content cards.

    line 30
  4. Distinctive:

    Keep card text short and readable.

    line 31
  5. Distinctive:

    Check image count, image order, cover readability, title, body, hashtags, and copyright before draft filling.

    line 32
  6. Distinctive:

    Avoid exaggerated claims, fake results, sensitive work details, customer information, and internal metrics.

    line 33
  7. Distinctive:

    Stop before publish unless explicit human confirmation is present.

    line 34
  8. Very specific:

    Do not read Cookie, Token, password, .env, browser profile, or account files.

    line 38
  9. Distinctive:

    Do not bypass login, CAPTCHA, audit, or platform risk checks.

    line 39
  10. Distinctive:

    Do not auto-publish, delete, comment, send private messages, or batch operate.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

xiaohongshu-publisher

Goal

Adapt long-form Markdown or a content package into Xiaohongshu-ready note content and card planning.

Default Tools

  • Note package: xhs_prepare_note
  • Browser guidance: xhs_browser_setup_guide
  • Draft playbook: xhs_draft_playbook

Workflow

  1. Identify source content.
  2. Generate channels/xiaohongshu/ with note.xhs.md, cards.json, metadata.json, publish-checklist.md, and browser-playbook.md.
  3. Turn long-form logic into a short note, image-card outline, title, and hashtags.
  4. If browser automation is available, open the creator platform and fill draft fields only after the package is ready.
  5. Stop before publish unless the user explicitly says 确认发布到小红书.

Content Rules

  • Prefer 1 cover card plus 3-8 content cards.
  • Keep card text short and readable.
  • Check image count, image order, cover readability, title, body, hashtags, and copyright before draft filling.
  • Avoid exaggerated claims, fake results, sensitive work details, customer information, and internal metrics.
  • Stop before publish unless explicit human confirmation is present.

Safety Rules

  • Do not read Cookie, Token, password, .env, browser profile, or account files.
  • Do not bypass login, CAPTCHA, audit, or platform risk checks.
  • Do not auto-publish, delete, comment, send private messages, or batch operate.

Output Format

建议:...
事实:...
已执行:...
小红书渠道包:...
卡片规划:...
发布门禁:已停在发布前 / 未发布,原因...
下一步:...

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.