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
- luolin-ai/openclawWeComzhtheir own version, first seen Oct 8, 2026
- eunomia-bpf/eunomia.devtheir own version, first seen Oct 8, 2026
- iamzifei/red-publisher-skilltheir own version, first seen Aug 12, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- eunomia-bpf/eunomia.dev★ 244same name
- luolin-ai/openclawWeComzh★ 108same name
- iamzifei/red-publisher-skill★ 11same name
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 repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- content-package-managerSkill
- csdn-publisherSkill
- juejin-publisherSkill
- zhihu-publisherSkill
- ddd-java-developerSkill
- doubao-speechSkill
- doubao-videoSkill
- formal-resume-builderSkill
- code-qualitySkill
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
- Distinctive: line 25
If browser automation is available, open the creator platform and fill draft fields only after the package is ready.
- Very specific: line 26
Stop before publish unless the user explicitly says 确认发布到小红书.
- Distinctive: line 30
Prefer 1 cover card plus 3-8 content cards.
- Distinctive: line 31
Keep card text short and readable.
- Distinctive: line 32
Check image count, image order, cover readability, title, body, hashtags, and copyright before draft filling.
- Distinctive: line 33
Avoid exaggerated claims, fake results, sensitive work details, customer information, and internal metrics.
- Distinctive: line 34
Stop before publish unless explicit human confirmation is present.
- Very specific: line 38
Do not read Cookie, Token, password, .env, browser profile, or account files.
- Distinctive: line 39
Do not bypass login, CAPTCHA, audit, or platform risk checks.
- Distinctive: line 40
Do not auto-publish, delete, comment, send private messages, or batch operate.
“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.
Files
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
- Identify source content.
- Generate
channels/xiaohongshu/withnote.xhs.md,cards.json,metadata.json,publish-checklist.md, andbrowser-playbook.md. - Turn long-form logic into a short note, image-card outline, title, and hashtags.
- If browser automation is available, open the creator platform and fill draft fields only after the package is ready.
- 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:...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.

