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 HubWu42/hubwu-skills --skill zhuque-detectgit clone --depth 1 https://github.com/HubWu42/hubwu-skillsWrote 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/hubwu42/hubwu-skills/zhuque-detect)<a href="https://agentmods.dev/skills/hubwu42/hubwu-skills/zhuque-detect"><img src="https://agentmods.dev/badge/skills/hubwu42/hubwu-skills/zhuque-detect/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/hubwu42/hubwu-skills/zhuque-detect"><img src="https://agentmods.dev/badge/skills/hubwu42/hubwu-skills/zhuque-detect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00073 | $0.00851 |
| Opus 5 | $0.00036 | $0.00426 |
| Sonnet 5 | $0.00015 | $0.00170 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
zhuque-detect 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 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.
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.
What it actually says
朱雀 AI 检测（zhuque-detect）
把一段中文文本喂给腾讯朱雀（matrix.tencent.com/ai-detect），拿到 AI 生成检测结果，并导出与产品「下载报告」一致的官方检测报告单 PDF（含环形图、AI 分布图、片段解析表、逐段 AIGC 值与原文）。
何时使用
- 用户想知道某段文本「像不像 AI 写的」/ AI 率 / AIGC 占比
- 用户要朱雀的检测报告 PDF
- 批量自检自己产出的文案是否会被判为 AI
前置依赖
- Node 18+，在
scripts/下装一次依赖：npm install（只装playwright-core，不下载浏览器）。 - 本机真实 Chrome，且用调试端口启动（关键——见下方「为什么必须连真机」）：
该 Chrome 需能正常打开 matrix.tencent.com/ai-detect 并手动跑通检测（朱雀匿名即可用，有每日免费额度）。# macOS open -a "Google Chrome" --args --remote-debugging-port=9222 # Linux google-chrome --remote-debugging-port=9222 # Windows chrome.exe --remote-debugging-port=9222
用法
cd scripts
npm install # 一次
node run.mjs # 默认 sample.txt → reports/朱雀报告单-<时间>.pdf
node run.mjs ./my.txt ./out.pdf # 自定义输入文本 / 输出路径
调试端口非 9222 时用 ZHUQUE_CDP=http://127.0.0.1:PORT node run.mjs。
工作原理（要点）
- 检测走 WebSocket，签名由页面运行时按真实浏览器环境实时生成
fp/ARGUS_XSS_V3令牌。空白自动化 chromium 无有效令牌 →Invalid request。连你已登录的真机即天然带齐令牌，故脚本用connectOverCDP接管真机、新开标签页跑。 - 「下载报告」是隐藏 iframe 调
contentWindow.print()（原生打印框，脚本点不动、还冻结页面）。脚本劫持该 iframe 的 print，截获其报告单 HTML，注入<base>后用 CDPPage.printToPDF渲染成等价 PDF —— 全程不弹原生框。
详见 reference/anti-bot-notes.md。
约束 / 注意
- 文本须 ≥350 字，否则朱雀报「检测文本长度需大于350字」。
- 有每日检测次数额度（页面「今日剩余 N 次」），用完次日重置。
- 滑块验证码：冷启动 / 陌生会话（如全新 profile）偶发腾讯滑块验证。脚本会识别并提示——在弹出的 Chrome 窗口手动拖动完成后重跑即可。用你日常常用、已建立信任的 Chrome 一般不触发。
- 仅供个人学习与自检使用，遵守朱雀服务条款，勿规模化滥用。
What ships with it
5 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 · 54 lines · 73 tokens per session scan A 8aecb87b8e24
zhuque-detect is a skill published in the GitHub repository HubWu42/hubwu-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 851 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
add-pdf-report
Internal implementation skill invoked by /add-native for app-generated PDF report workflows using expo-print and, when present, expo-sharing.
add-pdf-viewer
Internal implementation skill invoked by /add-native for native PDF control workflows. Handles HTTPS and file URI PDF viewing with @microsoft/power-apps-native-pdf-viewer 0.2.9+.
review-export
Export CocoReview reports as markdown, html, or pdf-ready status artifacts. Usage: $review export markdown|html|pdf [report-path].
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
anydoc
Convert Word (.doc/.docx/.docm), PowerPoint (.ppt/.pps/.pot/.pptx/.pptm/.ppsx/.ppsm), Excel (.xls/.xlsx/.xlsm/.xlsb), OpenDocument (.odt/.ods/.odp), RTF, EPUB, CSV, and PDF documents to clean GitHub-Flavored Markdown locally with the Any Doc CLI (npx -y @firecrawl/[email protected]): headings, GFM tables, slide structure…