MateClaw is a pluggable agent runtime that coordinates AI agents, tools, conversations, memory, and workflows. It is designed for personal and multi-user AI assistants, including agents used through chat platforms. Catalogue add-ons provide skills for extending its agent workflows.
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 mateaix/mateclaw --skill xhs_notegit clone --depth 1 https://github.com/mateaix/mateclawWrote 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/mateaix/mateclaw/xhs_note)<a href="https://agentmods.dev/skills/mateaix/mateclaw/xhs_note"><img src="https://agentmods.dev/badge/skills/mateaix/mateclaw/xhs_note/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/mateaix/mateclaw/xhs_note"><img src="https://agentmods.dev/badge/skills/mateaix/mateclaw/xhs_note.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00114 | $0.02325 |
| Opus 5.5 | $0.00046 | $0.00930 |
| Sonnet 5.5 | $0.00023 | $0.00465 |
| Haiku 4.5 | $0.00011 | $0.00232 |
Grade A, and why
xhs_note 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 1mo 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书图文创作
把一个主题做成可直接发布的小红书笔记:文案 + 竖版图文卡片。
🖼️ 小红书是「以图为主、文字辅助」的平台。读者先滑图、再看字——首图(封面)决定点不点进来,图不够好、不够多,文案再好也没人看。
硬性要求:每篇笔记至少 3 张竖版图(1 封面 + ≥2 张内容图/照片)。
xhs_package会强制校验,不足 3 张直接拒绝打包。图要成组、风格统一、信息落在图上(大标题/清单/对比都做进图里),正文只作补充。
开工前:读取共享人设记忆
先用 recall_structured 取回并全程遵守:
content_persona— 人设 / 口吻writing_style_xhs— 小红书文风topic_interests— 选题方向banned_words— 禁用 / 敏感词signature_blocks— 固定开场 / 结尾段
取不到就用中性默认,不要编造。
SOP
1. 成文(小红书文案公式)
标题(≤20 字,四件套任选组合)
- 数字:「30天」「省了800块」「3个动作」
- 悬念:「原来一直做错了……」
- 情绪:😭 😮💨 🤯 直给情绪
- 对比 / 反转:「从烂脸到裸妆出门」
正文
- 碎句、一句一断,用 emoji 分段。
- 开头痛点共鸣,戳中读者才往下看。
- 中段干货清单:可操作、具体、有数字。
- 全程
writing_style_xhs+content_persona,大量第一人称和"姐妹们 / 你"。
话题标签(3–8 个)
大词 + 中词 + 长尾组合,例:#护肤 #敏感肌护肤 #学生党平价护肤。
2. 配图(以图为主,≥3 张竖版)
这是小红书的重头戏。至少出 3 张 3:4 竖版图,一组风格统一:
- 封面(第 1 张,必出) — 大标题 + 一句钩子,缩略图上就能读懂、想点进来。
- 内容图(≥2 张) — 把干货做进图里:清单卡、步骤卡、对比卡、金句卡,或用
image_generate(aspectRatio=portrait)出实拍风照片/场景图。一条要点一张,别把所有字堆一张。 - 结尾图(可选) — 关注 / 互动引导卡。
两种出图方式,按需混用,凑够 ≥3 张:
- HTML 卡片 → 图:用下面的模板库填文案后
render_html_image渲染。 - AI 生成照片/背景:
image_generate(action=generate, aspectRatio=portrait)(3:4 竖版),做封面底图或实拍风内容图。
卡片模板库(竖版 3:4,挑选组合或据用户口味自创):
references/xhs_card_cover.html— 封面 / 大标题。references/xhs_card_content.html— 干货清单。references/xhs_card_end.html— 关注 CTA。references/xhs_card_quote.html— 金句 / 大字引用卡。
想要别的视觉风格时,直接生成一份新的自包含 HTML 卡片(可参考现有模板结构),不必局限于现成几款。render_html_image 渲染出的 PNG 本身就是预览——先把图给用户看,满意再进入第 4 步打包。
填充占位符:每个模板里有 {{TITLE}} {{SUBTITLE}} {{POINTS}} {{CTA}} 等占位 token。把第 1 步的文案填进去——{{POINTS}} 是清单,按模板注释里的格式(每条一个 <li>)注入。
渲染成图:用 render_html_image 把填好的 HTML 渲染成 PNG。两种传法:
- 写入临时文件后传
filePath:render_html_image(filePath="<填好的卡片.html>", filename="xhs_cover", width=1080, height=1440, fullPage=false) - 或直接内联传
html="<填好的完整HTML字符串>",其余参数同上。
竖版 3:4 用 width=1080 height=1440。fullPage=false 保证输出严格 3:4,不因内容溢出而拉长。
What ships with it
4 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.
- 1mo ago First seen · 141 lines · 114 tokens per session scan A 02300e5510ea
xhs_note is a skill published in the GitHub repository mateaix/mateclaw (1,164 stars, last pushed yesterday), licensed Apache-2.0. It adds 114 tokens to every session and 2,325 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
xhs-cli
A terminal tool for Xiaohongshu, also called RedNote, a Chinese social platform for user-posted notes, photos, and videos.
app
A skill-management module for storing, organising, sharing, and managing reusable skills, including their descriptions, content, tags, and files.
openclaw-security-checker
A security checker for OpenClaw installations, including their configuration, permissions, containers, network access, and logs.
caixun-work-hours
A work-hours reporting assistant for RichPMS, a project time-tracking system. It turns conversation details, code records, or your description into a daily report, lets you confirm it, and then saves or submits it.
seclens-enterprise-web
Professional web application and API security testing workflows using OWASP Top 10 methodologies.
pentest-recon-attack-surface
White-box attack surface mapping — correlate external scans, browser exploration, and source code into structured endpoint inventory, role architecture, and authorization vulnerability candidates.