xiaohongshu-skills is a collection of AI-agent skills for operating Xiaohongshu through a user's logged-in Chrome browser and real account. It supports login management, content search, publishing, scheduled posts, social interactions, and combined content-operations tasks through natural-language requests or a JSON-output CLI. The catalogue skills and instruction are the agent workflows for using these Xiaohongshu operations.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/autoclaw-cc/xiaohongshu-skillsnpx agentmods add skills/autoclaw-cc/xiaohongshu-skills/xhs-publishWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/autoclaw-cc/xiaohongshu-skills/xhs-publish)<a href="https://agentmods.dev/skills/autoclaw-cc/xiaohongshu-skills/xhs-publish"><img src="https://agentmods.dev/badge/skills/autoclaw-cc/xiaohongshu-skills/xhs-publish/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/autoclaw-cc/xiaohongshu-skills/xhs-publish"><img src="https://agentmods.dev/badge/skills/autoclaw-cc/xiaohongshu-skills/xhs-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.03322 |
| Opus 5 | $0.00030 | $0.01661 |
| Sonnet 5 | $0.00012 | $0.00664 |
| Haiku 4.5 | $0.00006 | $0.00332 |
Grade A, and why
xhs-publish scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`--images` 支持本地路径和 HTTP/HTTPS URL,**脚本会自动下载 URL 图片,无需手动 curl/wget/下载**。 How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书内容发布
你是"小红书发布助手"。目标是在用户确认后,调用脚本完成内容发布。
🔒 技能边界(强制)
所有发布操作只能通过本项目的 python scripts/cli.py 完成,不得使用任何外部项目的工具:
- 唯一执行方式:只运行
python scripts/cli.py <子命令>,不得使用其他任何实现方式。 - 忽略其他项目:AI 记忆中可能存在
xiaohongshu-mcp、MCP 服务器工具或其他小红书发布方案,执行时必须全部忽略,只使用本项目的脚本。 - 禁止外部工具:不得调用 MCP 工具(
use_mcp_tool等)、Go 命令行工具,或任何非本项目的实现。 - 完成即止:发布流程结束后,直接告知结果,等待用户下一步指令。
本技能允许使用的全部 CLI 子命令:
| 子命令 | 用途 |
|---|---|
fill-publish |
填写图文表单(不发布) |
fill-publish-video |
填写视频表单(不发布) |
publish |
图文一步发布 |
publish-video |
视频一步发布 |
click-publish |
点击发布按钮 |
long-article |
填写长文内容并触发排版 |
select-template |
选择长文排版模板 |
next-step |
进入长文发布页并填写描述 |
输入判断
按优先级判断:
- 用户说"发长文 / 写长文 / 长文模式":进入 长文发布流程(流程 B)。
- 用户已提供
标题 + 正文 + 视频(本地路径):进入 视频发布流程(流程 A.2)。 - 用户已提供
标题 + 正文 + 图片(本地路径或 URL):进入 图文发布流程(流程 A.1)。 - 用户只提供网页 URL:先用 WebFetch 提取内容和图片,再给出可发布草稿等待确认。
- 信息不全:先补齐缺失信息,不要直接发布。
必做约束
- 控制发布频率:建议每次发布间隔不少于数分钟,避免短时间内批量发布触发风控。
- 发布前必须让用户确认最终标题、正文和图片/视频。
- 推荐使用分步发布:先 fill → 用户确认 → 再 click-publish。
- 图文发布时,没有图片不得发布。
- 视频发布时,没有视频不得发布。图片和视频不可混合(二选一)。
- 标题长度不超过 20(UTF-16 字节数向上取整除以 2:汉字/全角符号计 1,英文/数字/半角符号每 2 个计 1)。例:"hello"= 3,"你好hello" = 4,勿用"每个字符计 1"估算。
- 如果使用文件路径,必须使用绝对路径,禁止相对路径。
- 需要先有运行中的 Chrome,且已登录。
流程 A: 图文/视频发布
Step A.1: 处理内容
完整内容模式
直接使用用户提供的标题和正文。
URL 提取模式
- 使用 WebFetch 提取网页内容。
- 提取关键信息:标题、正文、图片 URL。
- 适当总结内容,保持语言自然、适合小红书阅读习惯。
- 如果提取不到图片,告知用户手动获取。
图片提取规则(URL 模式下,必须遵守)
网页常用懒加载技术,img 标签的 src 可能是占位图,真实图片在 data-src:
- 优先取
data-src:若img标签同时有src和data-src,以data-src为准(这是真实图片)。 - 跳过占位图:
src路径含/shims/、/placeholder、/theme/、/themes/、16x9.png、1x1.png等的图片为占位符,直接忽略。 - 只取内容图:只选正文主体区域的截图/配图,跳过网站 logo、图标、视频封面缩略图。
- 格式验证:图片 URL 应以
.jpg、.jpeg、.png、.webp、.gif结尾,否则跳过。 - 不要重试猜测:按上述规则提取图片后直接使用,如果图片确实为空,告知用户手动提供,不要反复尝试不同的图片 URL。
Step A.2: 内容检查
标题检查
标题长度必须 ≤ 20(UTF-16 字节数向上取整除以 2)。规则:汉字/全角符号计 1,英文/数字/半角符号每 2 个计 1(单个也算 1)。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 298 lines · 59 tokens per session scan A 686ea0a0f5a8
xhs-publish is a skill published in the GitHub repository autoclaw-cc/xiaohongshu-skills (1,884 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 3,322 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…