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 ZJU-REAL/Easel --skill skill-xhs-analyzergit clone --depth 1 https://github.com/ZJU-REAL/EaselWrote 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/zju-real/easel/skill-xhs-analyzer)<a href="https://agentmods.dev/skills/zju-real/easel/skill-xhs-analyzer"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-xhs-analyzer/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/zju-real/easel/skill-xhs-analyzer"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-xhs-analyzer.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 | $0.00095 | $0.01496 |
| Opus 5 | $0.00048 | $0.00748 |
| Sonnet 5 | $0.00019 | $0.00299 |
| Haiku 4.5 | $0.00010 | $0.00150 |
Grade A, and why
redbook 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 8d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Redbook — 小红书内容分析 CLI
用 redbook CLI 搜索笔记、读内容、分析创作者、提取爆款规律、研究选题。OpenClaw 用户： clawhub install redbook 或 npm install -g @lucasygu/redbook。
⚠️ 环境依赖（当前环境不可用）
本 SKILL 依赖以下运行时，在当前"macOS 专属 / Linux"环境下不可用，属于死代码保留，仅供部署到 macOS 桌面时启用：
| 依赖 | 说明 |
|---|---|
| macOS | cookie 抽取用原生 keychain（os: [macos]） |
| Node.js ≥ 22 | 运行 @lucasygu/redbook CLI |
redbook binary |
经 clawhub install redbook / npm 安装 |
| Chrome 登录 cookie | 需在 Chrome 登录 xiaohongshu.com（或 Safari/Firefox + --cookie-source） |
| puppeteer-core + marked | 仅 render 卡片渲染需要（可选） |
与 skill-xhs-publisher 的分工边界
- xhs-analyzer（本 SKILL） = 分析：搜索/数据/爆款规律/关键词矩阵/创作者画像/限流检测。
- skill-xhs-publisher = 发布 + 互动运营：发图文/视频、日常评论/回复/点赞收藏、内容数据、通知抓取。
- 本 SKILL 只读。不得调用
comment/reply/like/collect/post等写命令；发布交给skill-xhs-publisher，评论与回复交给skill-xhs-comment-reply，由对应 Skill 执行确认和出站安全检查。
Research discipline（先读这条）
XHS 风控节流的是读取，不只是写入。任何读超过几篇笔记的研究，都必须走 references/research-loop.md 的研究循环 —— 默认 human-paced（~20 s/篇，一次一篇）。在紧循环里猛敲 read/comments/analyze-viral 会在几十次内触发验证码/IP 封（300012），账号降级数小时。⚡ Fast 模式仅应急，需打印警告 + 用户明确 opt-in。绝不并行或零延迟发读。
Usage
redbook search "AI编程" --json # 搜索笔记
redbook read <webUrl> --json # 读笔记（用 search 返回的 webUrl，含 xsec_token）
redbook user <profileUrl> --json # 创作者档案
redbook analyze-viral <webUrl> --json # 单篇爆款分析（0-100 分）
redbook account-report --file ids.txt --json # 批量账号指标
redbook health --all --json # 笔记限流检测
始终加 --json 供程序解析。全部命令、选项、JSON 结构见 references/commands.md。
能力概览
分析能力拆成 13 个可组合模块（A–M）+ 组合工作流，详见 references/modules.md：
| 模块 | 能力 |
|---|---|
| A 关键词参与度矩阵 · B 跨主题热力图 · C 参与度信号 | 需求版图 |
| D 创作者画像 · D2 已知账号报告 · E 内容形态分解 | 竞争/形态 |
| F 机会评分 · G 受众推断 · H 内容头脑风暴 | 策略产出 |
| I 评论洞察 · J 爆款结构拆解 · K 互动机会识别 | 只读分析 |
| L 卡片渲染（离线） · M 笔记限流检测 | 产出/健康 |
组合示例：快速主题扫描 A→C→F；完整细分分析 A→B→C→D→E→F→G→H；单篇深挖 analyze-viral。
What ships with it
29 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.
- .github/workflows/npm-publish.yml 3.8 KB
- EASEL-META.md 2.1 KB
- package-lock.json 37 KB
- package.json 1.6 KB
- references/commands.md 4.4 KB
- references/modules.md 6.2 KB
- references/platform-signals.md 1.7 KB
- references/research-loop.md 8.2 KB
- references/technical-reference.md 3.8 KB
- scripts/postinstall.js 4.5 KB runs code
- scripts/preuninstall.js 1.4 KB runs code
- social-preview.html 5.1 KB
- social-preview.png 261 KB
- src/cli.ts 77 KB runs code
- src/lib/analyze.ts 20 KB runs code
- src/lib/cdp-cookies.ts 13 KB runs code
- src/lib/client.ts 22 KB runs code
- src/lib/cookies.ts 13 KB runs code
- src/lib/creator-signing.ts 1.8 KB runs code
- src/lib/detect.ts 6.6 KB runs code
- src/lib/fingerprint-data.ts 2.3 KB runs code
- src/lib/health.ts 5.5 KB runs code
- src/lib/platform.ts 2.7 KB runs code
- src/lib/render.ts 19 KB runs code
- src/lib/reply-strategy.ts 6.0 KB runs code
- src/lib/signing.ts 21 KB runs code
- src/lib/template.ts 8.0 KB runs code
- src/lib/url.ts 1.8 KB runs code
- tsconfig.json 458 B
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.
- 8d ago First seen · 91 lines · 95 tokens per session scan A a377eb67dee2
redbook is a skill published in the GitHub repository ZJU-REAL/Easel (841 stars, last pushed yesterday), licensed Apache-2.0. It adds 95 tokens to every session and 1,496 once invoked, about $0.0005 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
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
roadtrip-navigator
Generate North American road-trip itineraries as a map-first, offline-friendly single-file HTML page. Plans around daily driving segments, overnight stops, fuel/EV-charging, national-park reservations (Recreation.gov / NPS), seasonal road closures, and timezone/border crossings — for executable, decision-ready trips.…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.