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 gzh_articlegit 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/gzh_article)<a href="https://agentmods.dev/skills/mateaix/mateclaw/gzh_article"><img src="https://agentmods.dev/badge/skills/mateaix/mateclaw/gzh_article/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/gzh_article"><img src="https://agentmods.dev/badge/skills/mateaix/mateclaw/gzh_article.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 | $0.00066 | $0.02609 |
| Opus 5.5 | $0.00026 | $0.01044 |
| Sonnet 5.5 | $0.00013 | $0.00522 |
| Haiku 4.5 | $0.00007 | $0.00261 |
Grade A, and why
gzh_article 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
公众号图文创作
把一个选题做成可直接粘进公众号编辑器的图文推文。7 个阶段,每步都接到平台真实工具上。
📌 动笔前务必先读
references/gzh_platform_rules.md—— 那是微信公众号的真实平台规矩(封面尺寸、标题/摘要、编辑器排版、诱导分享/关注红线、群发频次与时机、原创机制),懂了这些才叫"会做公众号",而不只是"会写字"。下面 SOP 的成文/配图/自查各步都以它为准。
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_gzh— 公众号文风topic_interests— 选题方向banned_words— 禁用 / 敏感词signature_blocks— 固定开场 / 结尾 / 引导关注段
取不到就用中性默认,不要编造。
七步 SOP
1. 选题
用 web_search(freshness=week、language=zh-CN)围绕 topic_interests 找近期热点和角度,count 取 5–8。给用户 3–5 个候选选题(每个带一句话切入角度),让其确认或补充后再往下。
2. 搜集汇总(参考文章)
用户给出参考公众号链接时:
- 优先用可能存在的
wechat_article_extract工具直接抽正文(若该工具可用,用load_skill或工具列表确认)。 - 没有该工具,就用
browser_use:先action=open打开链接,再action=snapshot抓取页面可见正文。 - 把每篇参考的核心观点、结构、可借鉴角度提炼成要点。
红线:本技能产出原创内容,参考只用于找角度、补事实,并在文末标注引用来源。严禁洗稿 / 搬运 / 逐段改写他人文章。
3. 成文
按公众号结构模板成文(详见 references/gzh_structure.md):
- 钩子引言 — 用具体场景 / 反常识数据 / 一个问题抓住读者。
- 3–5 个小标题分节 — 每节一个论点,配具体案例或数据,不要空谈。
- 金句 — 每节或结尾埋一句可摘录的话。
- 结尾行动号召 + 引导关注 — 用
signature_blocks里的固定收尾。
全程遵守 writing_style_gzh + content_persona。
同时定好标题和摘要(打开率的命门,见 references/gzh_platform_rules.md):
- 标题:≤30 字为佳(后台上限 64),带具体信息 / 数字 / 悬念 / 情绪;与正文一致,不做标题党、不用"震惊体"、别满屏感叹号(会被限流)。给 2–3 个候选让用户挑。
- 摘要(digest):手写 ≤120 字,补一句标题没说完的钩子(不填会被系统乱截正文前 54 字)。交付时作为
gzh_publish的digest传入。
4. 配图
用 image_generate(action=generate):
- 封面头图:
aspectRatio=landscape(公众号头图是 2.35:1,约 900×383 / 1080×460)。prompt 写清主题、风格、留白;封面文字要大而少(缩略图很小,一行主标题足矣)。 - 分享/朋友圈封面:如需单独出,用
aspectRatio=square(1:1,≥500×500)。 - 关键小节配图:按需为 2–3 个重点小节各生成一张,风格与封面统一。
image_generate 只认 landscape / portrait / square 三种比例,其它比例映射到最近的一个(如 3:4 → portrait)。
5. 去 AI 化
load_skill deai_humanize,然后对全文跑它的"打分→改写→复检"循环,platform=gzh,目标 score ≤ 55。
6. 违禁词 + 平台规则自查
对照 banned_words 和 references/compliance_checklist.md,命中就标注并给出替换建议,不要静默通过。两类都要扫:
- 广告法:极限词(最/第一/唯一/国家级/100%)、虚假功效、承诺收益、敏感内容、侵权。
- 微信平台红线(比广告法更容易封号,见
references/gzh_platform_rules.md第 5 节):诱导分享(集赞/助力/分享解锁)、诱导关注(关注才能看全文)、违规外链/二维码、标题党。引导互动只用话术、不用利诱。
What ships with it
6 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 · 131 lines · 66 tokens per session scan A e04b1073af1a
gzh_article is a skill published in the GitHub repository mateaix/mateclaw (1,170 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 2,609 once invoked, about $0.0003 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
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.
wechat-article-search
A search workflow for finding WeChat public-account articles by keyword and organizing their titles, summaries, dates, account names, and links.
pentest-whitebox-code-review
Source code security audit using backward taint analysis, slot type classification, render context verification, and 3-phase parallel review producing an exploitation queue.
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.