[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EPHTVZDCRXBJRHWVM3YC8V":3,"skill-same:01M7EPHTVZDCRXBJRHWVM3YC8V":134},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M7EPHTVZDCRXBJRHWVM3YC8V","pentest-tools",null,"Operate 20+ penetration-testing tools (Nmap, Nuclei, SQLMap, FFUF, Hashcat, and more) through structured workflows with consistent output handling.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pentest-tools\ndescription: \"Operate 20+ penetration-testing tools (Nmap, Nuclei, SQLMap, FFUF, Hashcat, and more) through structured workflows with consistent output handling.\"\nrisk: offensive\nsource: \"https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill\"\nsource_repo: \"zhaoxuya520\u002Freverse-skill\"\nsource_type: community\ndate_added: \"2026-08-25\"\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n> **⚠️ AUTHORIZED USE ONLY**\n> This skill is for educational purposes or authorized security assessments only.\n> You must have explicit, written permission from the system owner before using this tool.\n> Misuse of this tool is illegal and strictly prohibited.\n\n> **Mandatory confirmation gate**\n> Before running any command that probes, exploits, changes, persists on, extracts data from, or attempts credential access against a target:\n> 1. Ask the user to state the exact target URL, IP, account, or resource.\n> 2. Ask the user to confirm written authorization and the permitted scope.\n> 3. Show the exact command(s) and explain their expected effect.\n> 4. Wait for explicit confirmation in the current conversation.\n>\n> Without that confirmation, remain read-only and provide defensive guidance only. Prefer a sandbox, disposable VM, or controlled lab.\n\n## When to Use\n\n- An authorized assessment needs standard tooling orchestrated coherently.\n- Choosing and sequencing the right tool per recon\u002Fexploitation phase.\n\n## 适用范围\n\n当任务属于以下场景时使用本 skill：\n\n- 目标信息收集（端口扫描、子域名枚举、服务识别）\n- 漏洞扫描（Web 漏洞、CVE 检测、配置错误）\n- Web 渗透（SQL 注入、XSS、SSRF、目录爆破）\n- 密码破解（哈希破解、字典攻击）\n- 网络渗透（服务利用、横向移动辅助）\n\n### 与其他 skill 的分工\n\n| 场景 | 用什么 |\n|------|--------|\n| 主动扫描\u002F攻击（Nmap\u002FNuclei\u002FSQLMap） | **本 skill** |\n| 逆向分析二进制 | `ida-reverse\u002F` 或 `radare2\u002F` |\n| 前端 JS 签名逆向 | `js-reverse\u002F` |\n| 浏览器\u002F桌面自动化操作 | `browser-automation\u002F` |\n| CTF 竞赛（综合） | `CTF-Sandbox-Orchestrator\u002F` |\n\n简单判断：\n- 需要\"扫描目标、发现漏洞、利用漏洞\" → 本 skill\n- 需要\"分析程序内部逻辑\" → 逆向类 skill\n- 需要\"操作浏览器\u002F桌面\" → browser-automation\n\n---\n\n## 工具矩阵\n\n### 信息收集\n\n| 工具 | 用途 | 典型命令 |\n|------|------|---------|\n| **Nmap** | 端口扫描、服务识别、OS 检测 | `nmap -sV -sC -O target` |\n| **Masscan** | 大规模快速端口扫描 | `masscan -p1-65535 target --rate=1000` |\n| **Subfinder** | 子域名枚举 | `subfinder -d target.com` |\n| **httpx** | HTTP 探测、存活检测 | `httpx -l urls.txt -status-code` |\n\n### 漏洞扫描\n\n| 工具 | 用途 | 典型命令 |\n|------|------|---------|\n| **Nuclei** | 模板化漏洞扫描（CVE\u002F配置\u002F暴露） | `nuclei -u target -t cves\u002F` |\n| **ZAP** | Web 应用安全扫描 | 通过 API 或 MCP 调用 |\n| **Nikto** | Web 服务器漏洞扫描 | `nikto -h target` |\n\n### Web 渗透\n\n| 工具 | 用途 | 典型命令 |\n|------|------|---------|\n| **SQLMap** | SQL 注入自动化 | `sqlmap -u \"url?id=1\" --batch --dbs` |\n| **FFUF** | 目录\u002F参数爆破 | `ffuf -u target\u002FFUZZ -w wordlist.txt` |\n| **Gobuster** | 目录\u002F子域名爆破 | `gobuster dir -u target -w wordlist` |\n| **XSStrike** | XSS 检测 | `xsstrike -u \"url?param=test\"` |\n\n### 密码破解\n\n| 工具 | 用途 | 典型命令 |\n|------|------|---------|\n| **Hashcat** | GPU 哈希破解 | `hashcat -m 0 hash.txt wordlist.txt` |\n| **John the Ripper** | CPU 哈希破解 | `john --wordlist=rockyou.txt hash.txt` |\n| **Hydra** | 在线暴力破解 | `hydra -l admin -P pass.txt target ssh` |\n\n### 利用框架\n\n| 工具 | 用途 | 说明 |\n|------|------|------|\n| **Metasploit** | 漏洞利用框架 | 需要单独安装，体量大 |\n| **Impacket** | Windows 协议利用（SMB\u002FWMI\u002FKerberos） | `pip install impacket` |\n\n---\n\n## MCP 后端选择\n\n本 skill 支持两种 MCP 后端，选一个即可：\n\n### 方案 A：pentestMCP（推荐，Docker 一键）\n\n- **项目**：https:\u002F\u002Fgithub.com\u002Framkansal\u002Fpentestmcp\n- **特点**：20+ 工具打包成单个 Docker 容器，MCP server 直接暴露\n- **工具**：Nmap、Nuclei、ZAP、SQLMap、FFUF、Nikto、Gobuster、Subfinder、httpx 等\n- **安装**：\n\n```bash\n# 拉取并运行\ndocker pull ramkansal\u002Fpentestmcp\ndocker run -d -p 8080:8080 ramkansal\u002Fpentestmcp\n\n# 或本地构建\ngit clone https:\u002F\u002Fgithub.com\u002Framkansal\u002Fpentestmcp.git\ncd pentestmcp\ndocker build -t pentestmcp .\ndocker run -d -p 8080:8080 pentestmcp\n```\n\n- **MCP 注册**：\n\n```json\n{\n  \"mcpServers\": {\n    \"pentest\": {\n      \"url\": \"http:\u002F\u002Flocalhost:8080\u002Fmcp\"\n    }\n  }\n}\n```\n\n### 方案 B：mcp-security-hub（模块化）\n\n- **项目**：https:\u002F\u002Fgithub.com\u002FFuzzingLabs\u002Fmcp-security-hub\n- **特点**：每个工具独立 MCP server，按需启用\n- **工具**：Nmap、Ghidra、Nuclei、SQLMap、Hashcat\n- **安装**：按各子模块 README 操作\n\n### 方案 C：单工具 MCP（最轻量）\n\n如果只需要某一个工具：\n\n| 工具 | MCP 项目 | 安装 |\n|------|---------|------|\n| Nmap | [nmap-mcp-server](https:\u002F\u002Fgithub.com\u002FPhialsBasement\u002Fnmap-mcp-server) | npm |\n| Nuclei | [nuclei-mcp](https:\u002F\u002Fgithub.com\u002Faddcontent\u002Fnuclei-mcp) | npm |\n| SQLMap | mcp-security-hub 子模块 | pip |\n\n### Reqable MCP（本地抓包与 API 工作台）\n\nReqable 桌面客户端可通过官方 [Reqable MCP Server](https:\u002F\u002Fgithub.com\u002Freqable\u002Freqable-mcp-server) 暴露本地抓包、API、断点和规则能力。先单独安装并启动 Reqable，再登记 MCP：\n\n```powershell\npowershell -NoProfile -ExecutionPolicy Bypass -File skills\\scripts\\bootstrap-reverse.ps1 -Capability reqable-mcp -McpHostTarget Codex\n```\n\n将 `Codex` 替换为 `Claude` 或 `Both` 可选择对应客户端；省略 `-McpHostTarget` 时不会写任何客户端全局配置。\n\n登记后的 stdio 配置为：\n\n```json\n{\n  \"mcpServers\": {\n    \"reqable-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"reqable-mcp-server@1.0.1\", \"--scope\", \"minimal\"]\n    }\n  }\n}\n```\n\n- 默认使用 Reqable 的本地 API；必要时按官方文档配置 `--host`、`--port` 或 `--scope minimal|all`。\n- `minimal` 是推荐默认范围；`all` 会暴露更多会改变代理、规则、环境或已保存数据的工具。\n- 对捕获流量、请求重放和规则修改仍须先满足 `scope.md` 的授权与网络限制；不得因 MCP 已注册而扩大目标范围。\n\n---\n\n## 工作流\n\n### 标准渗透流程\n\n> **重要**：执行渗透测试时，必须按 `references\u002Fpentest-loop.md` 的自主循环框架运行。\n> 该框架定义了完整的风险门控、记录规范、上下文压缩和完成检查机制。\n\n```text\n1. 信息收集\n   - Nmap 端口扫描 → 确认开放服务\n   - Subfinder 子域名枚举 → 扩大攻击面\n   - httpx 存活检测 → 过滤有效目标\n\n2. 漏洞扫描\n   - Nuclei 模板扫描 → 快速发现已知漏洞\n   - ZAP\u002FNikto → Web 应用深度扫描\n\n3. 漏洞利用\n   - SQLMap → SQL 注入\n   - FFUF → 发现隐藏路径\u002F参数\n   - 手动验证 → 确认可利用性\n\n4. 后渗透（如果授权范围内）\n   - 权限提升\n   - 横向移动\n   - 数据提取\n\n5. 报告\n   - 调用 docs-generator skill 生成渗透测试报告\n```\n\n### 快速扫描流程（5 分钟出结果）\n\n```text\n1. nmap -sV -sC target → 端口+服务\n2. nuclei -u target -severity critical,high → 高危漏洞\n3. 有 Web 服务 → ffuf -u target\u002FFUZZ -w common.txt → 目录\n4. 汇总发现 → 决定下一步\n```\n\n---\n\n## 注意事项\n\n- **必须有授权** — 所有扫描\u002F攻击操作必须在授权范围内\n- **控制扫描速率** — 避免触发 WAF\u002FIDS 或打崩目标\n- **先被动后主动** — 先信息收集，再漏洞扫描，最后利用\n- **记录所有操作** — 每个命令和结果都要记录，用于报告\n- **不要盲目自动化** — AI 应该在每个关键步骤等待确认\n\n---\n\n## 按需自举（On-Demand Bootstrap）\n\n### 自动化能力边界\n\n| 工具 | 可自动安装 | 安装方式 | 说明 |\n|------|-----------|---------|------|\n| Nmap | ✓ | winget (`Insecure.Nmap`) | Windows 版 |\n| Nuclei | ✓ | `go install` 或 GitHub Release | 需要 Go 或直接下载二进制 |\n| SQLMap | ✓ | `pip install sqlmap` 或 git clone | Python |\n| FFUF | ✓ | GitHub Release | Go 二进制 |\n| SecLists | ✓ | GitHub Release ZIP | 字典大全（FFUF\u002FGobuster 必备） |\n| Hashcat | ✗ | 手动下载 | 需要 GPU 驱动 |\n| Metasploit | ✗ | 手动安装 | 体量大，建议用 Kali |\n| pentestMCP (Docker) | ✗ | 需要 Docker | `docker run ramkansal\u002Fpentestmcp` |\n| Impacket | ✓ | `pip install impacket` | Python |\n| ProxyCat | ✓ | `pip install proxycat` | 代理池中间件（批量扫描防封） |\n| BurpSuite MCP | ✗ | BurpSuite 扩展市场安装 | 需要 BurpSuite Pro\u002FCommunity |\n| Reqable MCP | ✓ | `npx -y reqable-mcp-server@1.0.1` | 需先手动安装 Reqable 桌面客户端 |\n\n### 自举策略\n\n1. 如果用户有 Docker → 推荐 pentestMCP（一键全家桶）\n2. 如果没有 Docker → 按需单独安装各工具\n3. 优先安装 Nmap + Nuclei + SQLMap（覆盖 80% 场景）\n\n### 手动安装引导\n\n```markdown\n⚠️ **渗透工具未安装**\n\n**推荐方案（需要 Docker）**：\ndocker pull ramkansal\u002Fpentestmcp\ndocker run -d -p 8080:8080 ramkansal\u002Fpentestmcp\n\n**轻量方案（逐个安装）**：\n- Nmap: winget install Insecure.Nmap\n- Nuclei: go install -v github.com\u002Fprojectdiscovery\u002Fnuclei\u002Fv3\u002Fcmd\u002Fnuclei@latest\n- SQLMap: pip install sqlmap\n- FFUF: 从 https:\u002F\u002Fgithub.com\u002Fffuf\u002Fffuf\u002Freleases 下载\n\n**安装后告诉我，我继续当前任务。**\n```\n\n---\n\n## 参考资源\n\n- [awesome-pentest](https:\u002F\u002Fgithub.com\u002Fenaqx\u002Fawesome-pentest) — 25k+ stars 渗透工具大全\n- [SecLists](https:\u002F\u002Fgithub.com\u002Fdanielmiessler\u002FSecLists) — 字典\u002Fpayload 集合（FFUF\u002FGobuster 必备）\n- [PayloadsAllTheThings](https:\u002F\u002Fgithub.com\u002Fswisskyrepo\u002FPayloadsAllTheThings) — 各类漏洞 payload\n- [HackTricks](https:\u002F\u002Fbook.hacktricks.wiki\u002F) — 渗透技巧百科\n- [pentest-ai-agents](https:\u002F\u002Fgithub.com\u002F0xSteph\u002Fpentest-ai-agents) — 35 个 Claude Code 渗透子 agent（参考其 prompt 模式）\n- [Pentest Swarm AI](https:\u002F\u002Fgithub.com\u002FArmur-Ai\u002FPentest-Swarm-AI) — 群体智能自主渗透框架（多 agent 协同，支持 MCP server）\n- [ProxyCat](https:\u002F\u002Fgithub.com\u002Fhonmashironeko\u002FProxyCat) — 代理池中间件（批量扫描防封 IP）\n- [planning-with-files](https:\u002F\u002Fgithub.com\u002Fothmanadi\u002Fplanning-with-files) — 计划任务 skill（循环测试用）\n\n### 本 skill 内参考文档\n\n- `references\u002Fpentest-loop.md` — **核心循环框架**（风险门控 + 记录规范 + 上下文压缩）\n- `references\u002Frecon-pipeline.md` — **授权侦察流水线**（CF 头 \u002F nmap \u002F Evidence）\n- `references\u002Fclient-side-lab-playbook.md` — **DOM XSS \u002F 原型污染 \u002F agent-browser**（靶场客户端面）\n- `references\u002Fburpsuite-mcp-guide.md` — **BurpSuite MCP 完整指南**（63 工具 + 7 大使用场景 + AI Prompt 模板）\n- `references\u002Fautomation-loop-pattern.md` — 自动化循环测试模式（轻量版）\n- `references\u002Fawesome-pentest-digest.md` — 渗透工具精华速查\n- `references\u002Fpentest-ai-agents-matrix.md` — 35 agent 覆盖矩阵\n- `payloads\u002F` — 自定义 payload 目录（AI 优先使用）\n- `templates\u002F` — 渗透测试必需文件模板（scope\u002Frules\u002Fplan\u002Ffindings\u002Fprogress）\n\n### src-hunter 漏洞挖掘知识库\n\n`src-hunter\u002F` 目录包含完整的 SRC\u002FBug Bounty 漏洞挖掘方法论：\n\n- **19 类攻击 playbook**（IDOR、RCE、XSS、SQLi、SSRF、OAuth、文件上传等）\n- **305 个结构化 payload** + 263 个 WAF\u002FEDR 绕过步骤\n- **2887 份 HackerOne 已披露 High\u002FCritical 报告**\n- **88,636 条 WooYun 历史案例统计**\n- **国产组件指纹和默认凭据**\n- **CVSS 4.0 报告模板**\n\n使用方式：AI 在 hunt 阶段自动读取对应 playbook，按其流程测试。\n\n详见 `src-hunter\u002FSKILL.md` 和 `src-hunter\u002Freferences\u002F`。\n\n---\n\n## 路由上下文\n\n**上游入口**: `skills\u002FSKILL.md`（总控）、`routing.md`\n**触发条件**: 需要主动扫描\u002F攻击目标（端口扫描、漏洞检测、注入测试等）\n**下游出口**:\n- 发现 Web 漏洞需要进一步分析 → `js-reverse\u002F`\n- 发现二进制漏洞需要逆向 → `ida-reverse\u002F` 或 `radare2\u002F`\n- 需要操作浏览器验证漏洞 → `browser-automation\u002F`\n- 完成后生成报告 → `docs-generator\u002F`\n\n**同级关联模块**: `CTF-Sandbox-Orchestrator\u002F`（CTF 中的 Web\u002FPwn 题会用到这些工具）\n\n\n## 任务完成自检（声称完成前 MUST 通过）\n\n- [ ] 我是否执行了工作流中的每一步（而不是只阅读）？\n- [ ] 我是否基于 `tool-index` 使用了真实工具路径？\n- [ ] 我是否产出了可复现证据（命令\u002F脚本\u002F截图\u002F报告）？\n- [ ] 我是否完成并回写了 RULES 要求的 Checklist 项？\n\n## Limitations\n\n- Tool availability varies by platform; verify installs before engagements.\n- Noisy scanning can disrupt fragile targets; tune timing and scope.\n\n> Adapted from [zhaoxuya520\u002Freverse-skill](https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill) (MIT).\n","> **⚠️ AUTHORIZED USE ONLY**\n> This skill is for educational purposes or authorized security assessments only.\n> You must have explicit, written permission from the system owner before using this tool.\n> Misuse of this tool is illegal and strictly prohibited.\n\n> **Mandatory confirmation gate**\n> Before running any command that probes, exploits, changes, persists on, extracts data from, or attempts credential access against a target:\n> 1. Ask the user to state the exact target URL, IP, account, or resource.\n> 2. Ask the user to confirm written authorization and the permitted scope.\n> 3. Show the exact command(s) and explain their expected effect.\n> 4. Wait for explicit confirmation in the current conversation.\n>\n> Without that confirmation, remain read-only and provide defensive guidance only. Prefer a sandbox, disposable VM, or controlled lab.\n\n## When to Use\n\n- An authorized assessment needs standard tooling orchestrated coherently.\n- Choosing and sequencing the right tool per recon\u002Fexploitation phase.\n\n## 适用范围\n\n当任务属于以下场景时使用本 skill：\n\n- 目标信息收集（端口扫描、子域名枚举、服务识别）\n- 漏洞扫描（Web 漏洞、CVE 检测、配置错误）\n- Web 渗透（SQL 注入、XSS、SSRF、目录爆破）\n- 密码破解（哈希破解、字典攻击）\n- 网络渗透（服务利用、横向移动辅助）\n\n### 与其他 skill 的分工\n\n| 场景 | 用什么 |\n|------|--------|\n| 主动扫描\u002F攻击（Nmap\u002FNuclei\u002FSQLMap） | **本 skill** |\n| 逆向分析二进制 | `ida-reverse\u002F` 或 `radare2\u002F` |\n| 前端 JS 签名逆向 | `js-reverse\u002F` |\n| 浏览器\u002F桌面自动化操作 | `browser-automation\u002F` |\n| CTF 竞赛（综合） | `CTF-Sandbox-Orchestrator\u002F` |\n\n简单判断：\n- 需要\"扫描目标、发现漏洞、利用漏洞\" → 本 skill\n- 需要\"分析程序内部逻辑\" → 逆向类 skill\n- 需要\"操作浏览器\u002F桌面\" → browser-automation\n\n---\n\n## 工具矩阵\n\n### 信息收集\n\n| 工具 | 用途 | 典型命令 |\n|------|------|---------|\n| **Nmap** | 端口扫描、服务识别、OS 检测 | `nmap -sV -sC -O target` |\n| **Masscan** | 大规模快速端口扫描 | `masscan -p1-65535 target --rate=1000` |\n| **Subfinder** | 子域名枚举 | `subfinder -d target.com` |\n| **httpx** | HTTP 探测、存活检测 | `httpx -l urls.txt -status-code` |\n\n### 漏洞扫描\n\n| 工具 | 用途 | 典型命令 |\n|------|------|---------|\n| **Nuclei** | 模板化漏洞扫描（CVE\u002F配置\u002F暴露） | `nuclei -u target -t cves\u002F` |\n| **ZAP** | Web 应用安全扫描 | 通过 API 或 MCP 调用 |\n| **Nikto** | Web 服务器漏洞扫描 | `nikto -h target` |\n\n### Web 渗透\n\n| 工具 | 用途 | 典型命令 |\n|------|------|---------|\n| **SQLMap** | SQL 注入自动化 | `sqlmap -u \"url?id=1\" --batch --dbs` |\n| **FFUF** | 目录\u002F参数爆破 | `ffuf -u target\u002FFUZZ -w wordlist.txt` |\n| **Gobuster** | 目录\u002F子域名爆破 | `gobuster dir -u target -w wordlist` |\n| **XSStrike** | XSS 检测 | `xsstrike -u \"url?param=test\"` |\n\n### 密码破解\n\n| 工具 | 用途 | 典型命令 |\n|------|------|---------|\n| **Hashcat** | GPU 哈希破解 | `hashcat -m 0 hash.txt wordlist.txt` |\n| **John the Ripper** | CPU 哈希破解 | `john --wordlist=rockyou.txt hash.txt` |\n| **Hydra** | 在线暴力破解 | `hydra -l admin -P pass.txt target ssh` |\n\n### 利用框架\n\n| 工具 | 用途 | 说明 |\n|------|------|------|\n| **Metasploit** | 漏洞利用框架 | 需要单独安装，体量大 |\n| **Impacket** | Windows 协议利用（SMB\u002FWMI\u002FKerberos） | `pip install impacket` |\n\n---\n\n## MCP 后端选择\n\n本 skill 支持两种 MCP 后端，选一个即可：\n\n### 方案 A：pentestMCP（推荐，Docker 一键）\n\n- **项目**：https:\u002F\u002Fgithub.com\u002Framkansal\u002Fpentestmcp\n- **特点**：20+ 工具打包成单个 Docker 容器，MCP server 直接暴露\n- **工具**：Nmap、Nuclei、ZAP、SQLMap、FFUF、Nikto、Gobuster、Subfinder、httpx 等\n- **安装**：\n\n```bash\n# 拉取并运行\ndocker pull ramkansal\u002Fpentestmcp\ndocker run -d -p 8080:8080 ramkansal\u002Fpentestmcp\n\n# 或本地构建\ngit clone https:\u002F\u002Fgithub.com\u002Framkansal\u002Fpentestmcp.git\ncd pentestmcp\ndocker build -t pentestmcp .\ndocker run -d -p 8080:8080 pentestmcp\n```\n\n- **MCP 注册**：\n\n```json\n{\n  \"mcpServers\": {\n    \"pentest\": {\n      \"url\": \"http:\u002F\u002Flocalhost:8080\u002Fmcp\"\n    }\n  }\n}\n```\n\n### 方案 B：mcp-security-hub（模块化）\n\n- **项目**：https:\u002F\u002Fgithub.com\u002FFuzzingLabs\u002Fmcp-security-hub\n- **特点**：每个工具独立 MCP server，按需启用\n- **工具**：Nmap、Ghidra、Nuclei、SQLMap、Hashcat\n- **安装**：按各子模块 README 操作\n\n### 方案 C：单工具 MCP（最轻量）\n\n如果只需要某一个工具：\n\n| 工具 | MCP 项目 | 安装 |\n|------|---------|------|\n| Nmap | [nmap-mcp-server](https:\u002F\u002Fgithub.com\u002FPhialsBasement\u002Fnmap-mcp-server) | npm |\n| Nuclei | [nuclei-mcp](https:\u002F\u002Fgithub.com\u002Faddcontent\u002Fnuclei-mcp) | npm |\n| SQLMap | mcp-security-hub 子模块 | pip |\n\n### Reqable MCP（本地抓包与 API 工作台）\n\nReqable 桌面客户端可通过官方 [Reqable MCP Server](https:\u002F\u002Fgithub.com\u002Freqable\u002Freqable-mcp-server) 暴露本地抓包、API、断点和规则能力。先单独安装并启动 Reqable，再登记 MCP：\n\n```powershell\npowershell -NoProfile -ExecutionPolicy Bypass -File skills\\scripts\\bootstrap-reverse.ps1 -Capability reqable-mcp -McpHostTarget Codex\n```\n\n将 `Codex` 替换为 `Claude` 或 `Both` 可选择对应客户端；省略 `-McpHostTarget` 时不会写任何客户端全局配置。\n\n登记后的 stdio 配置为：\n\n```json\n{\n  \"mcpServers\": {\n    \"reqable-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"reqable-mcp-server@1.0.1\", \"--scope\", \"minimal\"]\n    }\n  }\n}\n```\n\n- 默认使用 Reqable 的本地 API；必要时按官方文档配置 `--host`、`--port` 或 `--scope minimal|all`。\n- `minimal` 是推荐默认范围；`all` 会暴露更多会改变代理、规则、环境或已保存数据的工具。\n- 对捕获流量、请求重放和规则修改仍须先满足 `scope.md` 的授权与网络限制；不得因 MCP 已注册而扩大目标范围。\n\n---\n\n## 工作流\n\n### 标准渗透流程\n\n> **重要**：执行渗透测试时，必须按 `references\u002Fpentest-loop.md` 的自主循环框架运行。\n> 该框架定义了完整的风险门控、记录规范、上下文压缩和完成检查机制。\n\n```text\n1. 信息收集\n   - Nmap 端口扫描 → 确认开放服务\n   - Subfinder 子域名枚举 → 扩大攻击面\n   - httpx 存活检测 → 过滤有效目标\n\n2. 漏洞扫描\n   - Nuclei 模板扫描 → 快速发现已知漏洞\n   - ZAP\u002FNikto → Web 应用深度扫描\n\n3. 漏洞利用\n   - SQLMap → SQL 注入\n   - FFUF → 发现隐藏路径\u002F参数\n   - 手动验证 → 确认可利用性\n\n4. 后渗透（如果授权范围内）\n   - 权限提升\n   - 横向移动\n   - 数据提取\n\n5. 报告\n   - 调用 docs-generator skill 生成渗透测试报告\n```\n\n### 快速扫描流程（5 分钟出结果）\n\n```text\n1. nmap -sV -sC target → 端口+服务\n2. nuclei -u target -severity critical,high → 高危漏洞\n3. 有 Web 服务 → ffuf -u target\u002FFUZZ -w common.txt → 目录\n4. 汇总发现 → 决定下一步\n```\n\n---\n\n## 注意事项\n\n- **必须有授权** — 所有扫描\u002F攻击操作必须在授权范围内\n- **控制扫描速率** — 避免触发 WAF\u002FIDS 或打崩目标\n- **先被动后主动** — 先信息收集，再漏洞扫描，最后利用\n- **记录所有操作** — 每个命令和结果都要记录，用于报告\n- **不要盲目自动化** — AI 应该在每个关键步骤等待确认\n\n---\n\n## 按需自举（On-Demand Bootstrap）\n\n### 自动化能力边界\n\n| 工具 | 可自动安装 | 安装方式 | 说明 |\n|------|-----------|---------|------|\n| Nmap | ✓ | winget (`Insecure.Nmap`) | Windows 版 |\n| Nuclei | ✓ | `go install` 或 GitHub Release | 需要 Go 或直接下载二进制 |\n| SQLMap | ✓ | `pip install sqlmap` 或 git clone | Python |\n| FFUF | ✓ | GitHub Release | Go 二进制 |\n| SecLists | ✓ | GitHub Release ZIP | 字典大全（FFUF\u002FGobuster 必备） |\n| Hashcat | ✗ | 手动下载 | 需要 GPU 驱动 |\n| Metasploit | ✗ | 手动安装 | 体量大，建议用 Kali |\n| pentestMCP (Docker) | ✗ | 需要 Docker | `docker run ramkansal\u002Fpentestmcp` |\n| Impacket | ✓ | `pip install impacket` | Python |\n| ProxyCat | ✓ | `pip install proxycat` | 代理池中间件（批量扫描防封） |\n| BurpSuite MCP | ✗ | BurpSuite 扩展市场安装 | 需要 BurpSuite Pro\u002FCommunity |\n| Reqable MCP | ✓ | `npx -y reqable-mcp-server@1.0.1` | 需先手动安装 Reqable 桌面客户端 |\n\n### 自举策略\n\n1. 如果用户有 Docker → 推荐 pentestMCP（一键全家桶）\n2. 如果没有 Docker → 按需单独安装各工具\n3. 优先安装 Nmap + Nuclei + SQLMap（覆盖 80% 场景）\n\n### 手动安装引导\n\n```markdown\n⚠️ **渗透工具未安装**\n\n**推荐方案（需要 Docker）**：\ndocker pull ramkansal\u002Fpentestmcp\ndocker run -d -p 8080:8080 ramkansal\u002Fpentestmcp\n\n**轻量方案（逐个安装）**：\n- Nmap: winget install Insecure.Nmap\n- Nuclei: go install -v github.com\u002Fprojectdiscovery\u002Fnuclei\u002Fv3\u002Fcmd\u002Fnuclei@latest\n- SQLMap: pip install sqlmap\n- FFUF: 从 https:\u002F\u002Fgithub.com\u002Fffuf\u002Fffuf\u002Freleases 下载\n\n**安装后告诉我，我继续当前任务。**\n```\n\n---\n\n## 参考资源\n\n- [awesome-pentest](https:\u002F\u002Fgithub.com\u002Fenaqx\u002Fawesome-pentest) — 25k+ stars 渗透工具大全\n- [SecLists](https:\u002F\u002Fgithub.com\u002Fdanielmiessler\u002FSecLists) — 字典\u002Fpayload 集合（FFUF\u002FGobuster 必备）\n- [PayloadsAllTheThings](https:\u002F\u002Fgithub.com\u002Fswisskyrepo\u002FPayloadsAllTheThings) — 各类漏洞 payload\n- [HackTricks](https:\u002F\u002Fbook.hacktricks.wiki\u002F) — 渗透技巧百科\n- [pentest-ai-agents](https:\u002F\u002Fgithub.com\u002F0xSteph\u002Fpentest-ai-agents) — 35 个 Claude Code 渗透子 agent（参考其 prompt 模式）\n- [Pentest Swarm AI](https:\u002F\u002Fgithub.com\u002FArmur-Ai\u002FPentest-Swarm-AI) — 群体智能自主渗透框架（多 agent 协同，支持 MCP server）\n- [ProxyCat](https:\u002F\u002Fgithub.com\u002Fhonmashironeko\u002FProxyCat) — 代理池中间件（批量扫描防封 IP）\n- [planning-with-files](https:\u002F\u002Fgithub.com\u002Fothmanadi\u002Fplanning-with-files) — 计划任务 skill（循环测试用）\n\n### 本 skill 内参考文档\n\n- `references\u002Fpentest-loop.md` — **核心循环框架**（风险门控 + 记录规范 + 上下文压缩）\n- `references\u002Frecon-pipeline.md` — **授权侦察流水线**（CF 头 \u002F nmap \u002F Evidence）\n- `references\u002Fclient-side-lab-playbook.md` — **DOM XSS \u002F 原型污染 \u002F agent-browser**（靶场客户端面）\n- `references\u002Fburpsuite-mcp-guide.md` — **BurpSuite MCP 完整指南**（63 工具 + 7 大使用场景 + AI Prompt 模板）\n- `references\u002Fautomation-loop-pattern.md` — 自动化循环测试模式（轻量版）\n- `references\u002Fawesome-pentest-digest.md` — 渗透工具精华速查\n- `references\u002Fpentest-ai-agents-matrix.md` — 35 agent 覆盖矩阵\n- `payloads\u002F` — 自定义 payload 目录（AI 优先使用）\n- `templates\u002F` — 渗透测试必需文件模板（scope\u002Frules\u002Fplan\u002Ffindings\u002Fprogress）\n\n### src-hunter 漏洞挖掘知识库\n\n`src-hunter\u002F` 目录包含完整的 SRC\u002FBug Bounty 漏洞挖掘方法论：\n\n- **19 类攻击 playbook**（IDOR、RCE、XSS、SQLi、SSRF、OAuth、文件上传等）\n- **305 个结构化 payload** + 263 个 WAF\u002FEDR 绕过步骤\n- **2887 份 HackerOne 已披露 High\u002FCritical 报告**\n- **88,636 条 WooYun 历史案例统计**\n- **国产组件指纹和默认凭据**\n- **CVSS 4.0 报告模板**\n\n使用方式：AI 在 hunt 阶段自动读取对应 playbook，按其流程测试。\n\n详见 `src-hunter\u002FSKILL.md` 和 `src-hunter\u002Freferences\u002F`。\n\n---\n\n## 路由上下文\n\n**上游入口**: `skills\u002FSKILL.md`（总控）、`routing.md`\n**触发条件**: 需要主动扫描\u002F攻击目标（端口扫描、漏洞检测、注入测试等）\n**下游出口**:\n- 发现 Web 漏洞需要进一步分析 → `js-reverse\u002F`\n- 发现二进制漏洞需要逆向 → `ida-reverse\u002F` 或 `radare2\u002F`\n- 需要操作浏览器验证漏洞 → `browser-automation\u002F`\n- 完成后生成报告 → `docs-generator\u002F`\n\n**同级关联模块**: `CTF-Sandbox-Orchestrator\u002F`（CTF 中的 Web\u002FPwn 题会用到这些工具）\n\n\n## 任务完成自检（声称完成前 MUST 通过）\n\n- [ ] 我是否执行了工作流中的每一步（而不是只阅读）？\n- [ ] 我是否基于 `tool-index` 使用了真实工具路径？\n- [ ] 我是否产出了可复现证据（命令\u002F脚本\u002F截图\u002F报告）？\n- [ ] 我是否完成并回写了 RULES 要求的 Checklist 项？\n\n## Limitations\n\n- Tool availability varies by platform; verify installs before engagements.\n- Noisy scanning can disrupt fragile targets; tune timing and scope.\n\n> Adapted from [zhaoxuya520\u002Freverse-skill](https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill) (MIT).\n",{"name":5,"risk":24,"source":25,"license":15,"date_added":26,"description":7,"source_repo":27,"source_type":28,"license_source":29},"offensive","https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill","2026-08-25","zhaoxuya520\u002Freverse-skill","community","https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill\u002Fblob\u002Fmain\u002FLICENSE","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fpentest-tools",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill pentest-tools",{"tool":44,"command":45},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill pentest-tools",{"tool":47,"command":48},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill pentest-tools","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002FSKILL.md",true,[52,58,62,66,70,74,78,82,86,90,94,98,102,106,110,114,118,122,126,130],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fai-pentest-agents.md","REFERENCE","参考文档",6171,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fai-pentest-agents.md",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fai-pentesting-landscape-2026.md",3503,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fai-pentesting-landscape-2026.md",{"path":63,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fautomation-loop-pattern.md",5346,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fautomation-loop-pattern.md",{"path":67,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fawesome-pentest-digest.md",6090,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fawesome-pentest-digest.md",{"path":71,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fburpsuite-mcp-guide.md",23570,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fburpsuite-mcp-guide.md",{"path":75,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fclient-side-lab-playbook.md",4936,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fclient-side-lab-playbook.md",{"path":79,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fkali-mcp-ecosystem.md",4527,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fkali-mcp-ecosystem.md",{"path":83,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fmsf-protocol.md",6042,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fmsf-protocol.md",{"path":87,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fnetwork-attack-defense.md",10119,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fnetwork-attack-defense.md",{"path":91,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fnuclei-guide-2026.md",4070,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fnuclei-guide-2026.md",{"path":95,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fpayloads.md",1088,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fpayloads.md",{"path":99,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fpentest-ai-agents-matrix.md",5731,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fpentest-ai-agents-matrix.md",{"path":103,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fpentest-loop.md",6719,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fpentest-loop.md",{"path":107,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002Frecon-pipeline.md",5793,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Frecon-pipeline.md",{"path":111,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Ftemplates\u002Ffindings.md",328,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Ftemplates\u002Ffindings.md",{"path":115,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Ftemplates\u002Fprogress.md",242,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Ftemplates\u002Fprogress.md",{"path":119,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Ftemplates\u002Frules.md",722,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Ftemplates\u002Frules.md",{"path":123,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":124,"sourceHtmlUrl":125},"references\u002Ftemplates\u002Fscope.md",422,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Ftemplates\u002Fscope.md",{"path":127,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":128,"sourceHtmlUrl":129},"references\u002Ftemplates\u002Ftask_plan.md",543,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Ftemplates\u002Ftask_plan.md",{"path":131,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":132,"sourceHtmlUrl":133},"references\u002Fweb-attack-cheatsheet.md",7700,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpentest-tools\u002Freferences\u002Fweb-attack-cheatsheet.md",[135,143,148,155,162,169],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":142},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":144,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":142},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":142},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":142},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"publishedAt":142},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":142},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]