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/chubbyguan/chubbyskillsnpx agentmods add skills/chubbyguan/chubbyskills/xiaohongshu-ingestWrote 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/chubbyguan/chubbyskills/xiaohongshu-ingest)<a href="https://agentmods.dev/skills/chubbyguan/chubbyskills/xiaohongshu-ingest"><img src="https://agentmods.dev/badge/skills/chubbyguan/chubbyskills/xiaohongshu-ingest/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/chubbyguan/chubbyskills/xiaohongshu-ingest"><img src="https://agentmods.dev/badge/skills/chubbyguan/chubbyskills/xiaohongshu-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 29 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00076 | $0.01244 |
| Opus 5 | $0.00038 | $0.00622 |
| Sonnet 5 | $0.00015 | $0.00249 |
| Haiku 4.5 | $0.00008 | $0.00124 |
Grade B, and why
xiaohongshu-ingest scanned grade B 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 11d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
# macOS: brew install ffmpeg | Ubuntu: sudo apt install ffmpeg How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书采集 + 爆款拆解 Skill
把小红书笔记抓成结构化 Markdown 入库,再用 DeepSeek 拆解爆款逻辑、衍生可直接写的选题。 自动区分图文与视频笔记:图文 → 下载图片本地嵌入;视频 → 像抖音那样转成文字稿。 补齐了仓库在「中文内容采集」上最大的平台缺口,也是「采集 → 选题」创作工作流的起点。
环境要求
# 图文采集零依赖(仅 Python 标准库)
# 视频笔记转录需要(与抖音/B站转录同一套依赖):
pip install funasr modelscope torch torchaudio
# macOS: brew install ffmpeg | Ubuntu: sudo apt install ffmpeg
# 强烈建议:配置 cookie 以规避风控(从浏览器登录后复制)
export XHS_COOKIE="你的小红书 cookie 字符串"
# 爆款拆解需要 DeepSeek API Key
export DEEPSEEK_API_KEY="your-api-key"
使用方法
# 1) 采集笔记 → 统一 frontmatter Markdown
python scripts/fetch_note.py "https://www.xiaohongshu.com/explore/xxxx" -o ./out
python scripts/fetch_note.py "http://xhslink.com/xxxx" -o ./out
python scripts/fetch_note.py "链接" -o ./out --no-images # 图文:只留图片链接不下载
python scripts/fetch_note.py "链接" -o ./out --no-video # 视频:不转录,只留视频链接
python scripts/fetch_note.py "链接" -o ./out --fallback-text 手动正文.txt
# 2) 爆款拆解 → 拆解报告 + 5 条衍生选题
python scripts/analyze_hook.py ./out/某笔记.md -o ./out
产出
fetch_note.py:标题、正文、标签、作者、互动数据(赞/藏/评)→ 统一 frontmatter Markdown(platform: xiaohongshu,含note_type: image|video)。按笔记类型分流:- 图文笔记:图片下载到本地
<标题>.assets/并以![]()嵌入(正文常在图里,本地化后 Obsidian 直接可见)。--no-images只留链接,单张失败自动回退为链接 - 视频笔记:提取视频直链 → ffmpeg 抽音频 → SenseVoice 转录为文字稿写入
## 视频文字稿。--no-video只留视频链接;缺 funasr/ffmpeg 时自动降级为存链接
- 图文笔记:图片下载到本地
analyze_hook.py:目标人群 / 场景 / 痛点 / 情绪价值 / 标题钩子 / 正文结构 / 可复用模板 / 5 条衍生选题(带- [ ]勾选,可直接进选题库)
⚠️ 关于反爬(务必先读)
小红书风控严格,未登录的纯脚本访问经常被拦。本 skill 的策略:
- 优先解析页面内嵌的
__INITIAL_STATE__结构化数据 - 失败则回退到
og:元标签 - 仍失败时给出明确提示——此时可手动复制笔记正文存成
.txt,用--fallback-text继续生成统一 Markdown,或直接走analyze_hook.py拆解(拆解环节不依赖抓取)
提供 XHS_COOKIE 能显著提高采集成功率。页面结构若调整,需更新 fetch_note.py 里的选择器。
合规声明
仅供个人学习与研究使用。请遵守小红书用户协议与 robots 规则,控制请求频率,不要用于批量抓取、商用爬取或侵犯他人权益的场景。
衔接工作流
- 采集产物 →
knowledge-base-management入库(统一 frontmatter,按platform聚合) - 衍生选题 → 创作者选题流(采集 → 拆解 → 选题库 → 初稿)
- 多篇拆解 → 沉淀「爆款选题库」,对接
industry-intelligence-radar的趋势信号
参考
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 83 lines · 76 tokens per session scan B 23b75a33d121
xiaohongshu-ingest is a skill published in the GitHub repository chubbyguan/chubbyskills (667 stars, last pushed 23d ago), licensed MIT. It adds 76 tokens to every session and 1,244 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Chinese Market Content Engineer
A guide for creating and adapting content for major Chinese digital platforms, including WeChat, Xiaohongshu, Douyin, Zhihu, and Bilibili. It covers Chinese and English writing with attention to each platform's audience and format.
xiaohongshu-title
A Chinese-language title-writing and editing assistant for Xiaohongshu, a Chinese social-media platform for image and video posts. It creates titles for posts, covers, tutorials, reviews, recommendations, and services.
xiaohongshu-magazine
A Chinese-language planning guide for treating a Xiaohongshu account as a magazine. Xiaohongshu is a Chinese social platform where people publish and follow posts, and the guide helps define recurring content themes and columns.
xiaohongshu-suite
A Chinese-language workflow guide for improving a Xiaohongshu account, its content, and its path from posts to private messages or sales. It routes a request to a more specific skill, such as titles, profile text, topic planning, comments, or conversion paths.
xiaohongshu-comment-reply
A Xiaohongshu comment-reply guide helps write replies for Xiaohongshu, a Chinese social-content platform, including pinned comments and responses to doubts or hostile comments.
xiaohongshu-conversion-path
A Xiaohongshu conversion-path guide maps how people move from seeing content on Xiaohongshu, a Chinese social-content platform, to taking a next step such as messaging, booking, trying a tool, or buying.