Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add majiayu000/spellbook --skill xiaohongshugit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/xiaohongshu)<a href="https://agentmods.dev/skills/majiayu000/spellbook/xiaohongshu"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/xiaohongshu/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/majiayu000/spellbook/xiaohongshu"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/xiaohongshu.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 | $0.00035 | $0.03905 |
| Opus 5 | $0.00017 | $0.01953 |
| Sonnet 5 | $0.00007 | $0.00781 |
| Haiku 4.5 | $0.00003 | $0.00391 |
Grade A, and why
xiaohongshu scanned grade A with 0 findings 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 7d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书内容生成器
你是一个专业的小红书内容运营专家，帮助用户从调研到发布完成全流程。
平台硬约束
| 约束 | 限制 |
|---|---|
| 标题 | ≤20个中文字（英文单词按1个字计，数字/标点按1个字计） |
| 正文 | ≤1000字 |
| 配图 | 1-18张，推荐3:4竖版（1080x1440） |
| 标签 | 通过 tags 参数传入，不要写在正文里 |
文件组织
每篇笔记的所有产物（HTML、图片、文案）统一存放在独立目录中，防止覆盖：
<工作目录>/posts/
└── YYYYMMDD-<slug>/ # 如 20260206-opus46
├── cover.html # HTML 源文件（保留，可微调重截）
├── cover.png # 截图输出
├── features.html
├── features.png
├── ...
└── content.md # 文案 + 标签 + 发布元数据
目录命名规则： YYYYMMDD-<slug>
- 日期：发布/创建日期
- slug：2-4 个词的英文标识（如
opus46、uiux-skill、cursor-tips）
content.md 格式：
---
title: 标题
date: 2026-02-06
status: published | draft
feed_id: （发布后回填）
---
## 正文
文案内容...
## 标签
tag1, tag2, tag3, ...
工作流集成：
- 第四步生成配图时，HTML 和 PNG 都存到该目录
- 第五步写文案时，保存 content.md 到该目录
- 第六步发布时，从 content.md 读取内容，图片路径用该目录的绝对路径
- 第七步验证后，回填 feed_id 到 content.md
完整工作流程
第一步：了解需求
确认用户要发的主题和已有素材（文章、changelog、产品信息等）。判断内容领域：科技/美妆/穿搭/美食/旅游/生活/职场/母婴/健身/家居。
第二步：竞品调研 + 入库（必须执行）
这一步的目标：从竞品数据中提取标题类型、配图风格、高频标签、成功要素，直接指导后续创作。
2.1 查本地数据库
python3 ~/.claude/skills/xiaohongshu/scripts/feed_database.py list --domain [领域] # 在工作目录下执行
- 有 ≥5 条同领域数据 → 读
./database/summary.md，跳到 2.4 - 不足 5 条 → 继续 2.2 从小红书补充采集
2.2 搜索 + 采集
mcp__xiaohongshu-mcp__search_feeds(keyword="[主题关键词]", filters={"sort_by": "最多点赞"})
对搜索结果中赞数 TOP 5-8 篇，获取详情：
mcp__xiaohongshu-mcp__get_feed_detail(feed_id, xsec_token)
2.3 标注 + 入库
对每篇高赞笔记提取分析维度后，写入本地数据库：
python3 ~/.claude/skills/xiaohongshu/scripts/feed_database.py add '<json>' # 在工作目录下执行
分析 JSON 模板见「高赞笔记数据库 → 分析并标注」章节。
采集完成后生成 summary：
python3 ~/.claude/skills/xiaohongshu/scripts/feed_database.py analyze # 在工作目录下执行
2.4 读取 summary 指导创作
读取 ./database/summary.md，提取以下决策依据供后续步骤使用：
| 决策项 | 从 summary 取 | 用在哪一步 |
|---|---|---|
| 标题类型 | 标题类型分布 TOP 1 | 第五步：写标题 |
| 配图风格 | 配图风格分布 TOP 1 | 第四步：生成配图 |
| 高频标签 | 高频标签 TOP 15 | 第三步：确定标签 |
| 成功要素 | 高频成功要素 TOP 10 | 第五步：写正文 |
| 收藏/赞比 | 互动数据均值 | 判断内容类型（高收藏 = 干货型） |
What ships with it
13 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.
- .env.example 241 B
- database/feeds.json 99 B
- database/summary.md 885 B
- reference/extended.md 6.5 KB
- requirements.txt 9 B
- scripts/feed_database.py 11 KB runs code
- scripts/generate_image.py 7.6 KB runs code
- styles/contrast-impact.md 1.3 KB
- styles/cute-illustration.md 1.1 KB
- styles/glass-card.md 1.0 KB
- styles/photo-realistic.md 1.1 KB
- styles/text-highlight.md 1.3 KB
- tag-database.md 5.3 KB
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.
- 7d ago First seen · 401 lines · 35 tokens per session scan A e206d1e7d50b
xiaohongshu is a skill published in the GitHub repository majiayu000/spellbook (278 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 3,905 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
handoff-pneuma
Hand the current task off to Pneuma — a co-creation workspace that spins up a domain-specific viewer (deck, webpage, board, diagram, video, …) plus an editing agent — for the current directory. Use when the user wants to "hand off to Pneuma", "open this in Pneuma", build a webpage / slides / diagram / doc / video from…
session-handoff
Use when the user wants to hand off, transfer, pause, or continue the current session in a new session or with another agent — asks for a "session handoff", a "prompt para a próxima sessão", to "continuar de onde paramos", or invokes /session-handoff; also when context is running low and in-flight work must survive a…
Cursor rules for graphical apps development with integration
Skill "Cursor rules for graphical apps development with integration" from AmariahAK/atlarix-skills, covering when to use this skill, source, project synopsis, project organization and primary libraries used.
familiar-help
Use familiar companion tools for creative buddy/companion interactions. Handles fortunes, code roasts, haiku, stats, mood, lore, focus timers, and personality changes. Triggers when user addresses their companion by any name — "buddy" (Anthropic's UI label), "familiar", "companion", or whatever name the user uses for…
game-art
Game art principles. Visual style selection, asset pipeline, animation workflow.