[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DBM8X5M7YXPYBVFMWF8HRC":3,"skill-same:01M7DBM8X5M7YXPYBVFMWF8HRC":83},{"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":24,"commitSha":25,"skillDirectory":5,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7DBM8X5M7YXPYBVFMWF8HRC","alice-reverse",null,"逆向分析渐进路由（二进制 \u002F 移动端 \u002F 协议 \u002F 取证 \u002F 保护机制 \u002F 运行时观测）。触发词：二进制\u002F移动端\u002F反编译\u002FFrida\u002FIDA\u002FGhidra\u002FPE\u002FELF\u002FAPK\u002F协议\u002F取证；先选领域索引，再按任务匹配度与评分选模块，禁止一次读取全部领域。","alicewe1\u002Falice_skill","alicewe1","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F102134151?v=4","01M7D9STCM8HAESM958JP0989K","Alice_we","01M7D9STDR22MTD9FTTWPAZNV8",64,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-reverse\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: alice-reverse\ndescription: \"逆向分析渐进路由（二进制 \u002F 移动端 \u002F 协议 \u002F 取证 \u002F 保护机制 \u002F 运行时观测）。触发词：二进制\u002F移动端\u002F反编译\u002FFrida\u002FIDA\u002FGhidra\u002FPE\u002FELF\u002FAPK\u002F协议\u002F取证；先选领域索引，再按任务匹配度与评分选模块，禁止一次读取全部领域。\"\n---\n\n# 逆 · 逆向分析渐进路由\n\n本路由管理 `125` 个模块。入口只负责选领域，模块索引分片到 `references\u002F`，正文仍在 `..\u002F_modules\u002F`。\n\n## 加载规则\n\n1. 先用一句话概括用户要达成的结果，再选最匹配的领域。\n2. 每个阶段默认只读一个领域索引；任务明确跨领域时最多读两个。\n3. 禁止为了了解全部能力而读完所有 `references\u002F*.md`。\n4. 领域内先按任务匹配度筛选，再用评分排序；高分不能覆盖领域不匹配。\n5. 每阶段最多取 4 个模块，**可跨多个领域分别取**：本类正文需要其它类能力（如「破」的正文要用逆向分析）→ 直接去对应路由页取模块补足，不受单一子路由限制；**优先使用 MCP 工具执行电脑操作**——模块动作能由本页「可用 MCP 工具」完成的优先用 MCP，无匹配或失败再回退本地命令。\n6. **说出参考的具体模块（任何阶段，硬性）**：选定\u002F换用\u002F补充任何参考模块的当下就向用户说出——`参考模块: \u003C类>: \u003C模块id>（\u003C一句话用途>）`；禁止只执行不报名、禁止事后补报。\n7. 模块不匹配或执行碰壁时，先在当前领域换模块；领域不对才回本页换领域。\n8. 找不到合适模块时，使用模型自带知识规划，并向用户说明规划步骤、执行路径、成本与预计交付路径；不要为凑数读取无关领域。\n9. 任何实际执行前，先向用户展示规划步骤、执行路径、预计成本（时间\u002F算力\u002F外部服务\u002F人工投入）和预计交付物路径；用户已明确要求且风险可控时可直接开始，但仍要给出简短预览。\n10. 每项交付完成后，先在工作区写 Markdown 交付记录，包含目标、决策依据、实际步骤、证据、验证结果、产物路径和未解决项，再向用户汇报；不记录隐藏思维链。\n\n## 领域索引\n\n| 领域 | 何时读取 | 模块数 | 索引 |\n|:--|:--|--:|:--|\n| 原生与托管二进制 | PE、ELF、SO、DLL、EXE、.NET、反汇编、函数、导入表、字符串与交叉引用 | 10 | `references\u002Fnative-binary.md` |\n| 移动端与 IL2CPP | APK、IPA、Android、iOS、JNI、Frida\u002FObjection、证书锁定、Root\u002F模拟器与 Unity IL2CPP | 11 | `references\u002Fmobile.md` |\n| 协议、API 与 Web 运行时 | TCP\u002FUDP、自定义协议、API 签名、HAR、JavaScript、WebCrypto、WebSocket\u002FgRPC 与流量还原 | 15 | `references\u002Fprotocol-web.md` |\n| 取证与恶意样本分析 | EVTX、PCAP、内存镜像、时间线、IOC、恶意样本配置、加密行为与媒体隐写 | 15 | `references\u002Fforensics-malware.md` |\n| 保护、混淆与脱壳 | 加壳、OEP\u002FIAT、OLLVM、虚拟化保护、反调试、自修改代码与运行时重建 | 20 | `references\u002Fprotection-unpacking.md` |\n| 运行时观测与补丁 | Hook、断点、Frida 追踪、参数观测、字节补丁、跳转修改与系统调用关联 | 15 | `references\u002Finstrumentation-patching.md` |\n| 固件、内核与驱动 | 固件镜像、分区\u002F启动链、Binwalk、Windows\u002FLinux\u002FmacOS 内核与驱动 | 7 | `references\u002Ffirmware-kernel.md` |\n| 高级安全研究 | 漏洞机理、Pwn\u002FROP、模糊测试、密码强度验证与防御控制研究；只有任务明确命中时读取 | 7 | `references\u002Fadvanced-security.md` |\n| 综合流程与工具 | 任务编排、工具准备、环境隔离、IDA\u002FGhidra RPC、研究严谨性与综合逆向方法 | 25 | `references\u002Fworkflow-tooling.md` |\n\n## 评分机制\n\n- 评分唯一来源是 `..\u002F_modules\u002Fskill_ratings.json`；索引显示 `【x\u002F10】`。\n- 选择顺序固定为：**任务匹配度 → 评分 → 索引顺序**；无评分模块仍可用。\n- 不得为比较分数加载无关领域；批量评分一次处理一个领域索引。\n- 修改评分后重跑 `..\u002Faliceskill\u002Fscripts\u002Frebuild_menu.py`，不要手改生成的索引。\n\n## 读取具体模块\n\n选定模块后完整读取 `..\u002F_modules\u002F\u003CMODULE_ID>\u002FSKILL.md`；取不到正文时如实报告，不得声称已按该模块执行。\n同一任务已读取的模块直接复用；换领域或新任务才重新路由。\n**任何阶段**选定\u002F换用\u002F补充参考模块，必须当场说出 `参考模块: \u003C类>: \u003C模块id>（\u003C用途>）`，禁止只执行不报名。\n","# 逆 · 逆向分析渐进路由\n\n本路由管理 `125` 个模块。入口只负责选领域，模块索引分片到 `references\u002F`，正文仍在 `..\u002F_modules\u002F`。\n\n## 加载规则\n\n1. 先用一句话概括用户要达成的结果，再选最匹配的领域。\n2. 每个阶段默认只读一个领域索引；任务明确跨领域时最多读两个。\n3. 禁止为了了解全部能力而读完所有 `references\u002F*.md`。\n4. 领域内先按任务匹配度筛选，再用评分排序；高分不能覆盖领域不匹配。\n5. 每阶段最多取 4 个模块，**可跨多个领域分别取**：本类正文需要其它类能力（如「破」的正文要用逆向分析）→ 直接去对应路由页取模块补足，不受单一子路由限制；**优先使用 MCP 工具执行电脑操作**——模块动作能由本页「可用 MCP 工具」完成的优先用 MCP，无匹配或失败再回退本地命令。\n6. **说出参考的具体模块（任何阶段，硬性）**：选定\u002F换用\u002F补充任何参考模块的当下就向用户说出——`参考模块: \u003C类>: \u003C模块id>（\u003C一句话用途>）`；禁止只执行不报名、禁止事后补报。\n7. 模块不匹配或执行碰壁时，先在当前领域换模块；领域不对才回本页换领域。\n8. 找不到合适模块时，使用模型自带知识规划，并向用户说明规划步骤、执行路径、成本与预计交付路径；不要为凑数读取无关领域。\n9. 任何实际执行前，先向用户展示规划步骤、执行路径、预计成本（时间\u002F算力\u002F外部服务\u002F人工投入）和预计交付物路径；用户已明确要求且风险可控时可直接开始，但仍要给出简短预览。\n10. 每项交付完成后，先在工作区写 Markdown 交付记录，包含目标、决策依据、实际步骤、证据、验证结果、产物路径和未解决项，再向用户汇报；不记录隐藏思维链。\n\n## 领域索引\n\n| 领域 | 何时读取 | 模块数 | 索引 |\n|:--|:--|--:|:--|\n| 原生与托管二进制 | PE、ELF、SO、DLL、EXE、.NET、反汇编、函数、导入表、字符串与交叉引用 | 10 | `references\u002Fnative-binary.md` |\n| 移动端与 IL2CPP | APK、IPA、Android、iOS、JNI、Frida\u002FObjection、证书锁定、Root\u002F模拟器与 Unity IL2CPP | 11 | `references\u002Fmobile.md` |\n| 协议、API 与 Web 运行时 | TCP\u002FUDP、自定义协议、API 签名、HAR、JavaScript、WebCrypto、WebSocket\u002FgRPC 与流量还原 | 15 | `references\u002Fprotocol-web.md` |\n| 取证与恶意样本分析 | EVTX、PCAP、内存镜像、时间线、IOC、恶意样本配置、加密行为与媒体隐写 | 15 | `references\u002Fforensics-malware.md` |\n| 保护、混淆与脱壳 | 加壳、OEP\u002FIAT、OLLVM、虚拟化保护、反调试、自修改代码与运行时重建 | 20 | `references\u002Fprotection-unpacking.md` |\n| 运行时观测与补丁 | Hook、断点、Frida 追踪、参数观测、字节补丁、跳转修改与系统调用关联 | 15 | `references\u002Finstrumentation-patching.md` |\n| 固件、内核与驱动 | 固件镜像、分区\u002F启动链、Binwalk、Windows\u002FLinux\u002FmacOS 内核与驱动 | 7 | `references\u002Ffirmware-kernel.md` |\n| 高级安全研究 | 漏洞机理、Pwn\u002FROP、模糊测试、密码强度验证与防御控制研究；只有任务明确命中时读取 | 7 | `references\u002Fadvanced-security.md` |\n| 综合流程与工具 | 任务编排、工具准备、环境隔离、IDA\u002FGhidra RPC、研究严谨性与综合逆向方法 | 25 | `references\u002Fworkflow-tooling.md` |\n\n## 评分机制\n\n- 评分唯一来源是 `..\u002F_modules\u002Fskill_ratings.json`；索引显示 `【x\u002F10】`。\n- 选择顺序固定为：**任务匹配度 → 评分 → 索引顺序**；无评分模块仍可用。\n- 不得为比较分数加载无关领域；批量评分一次处理一个领域索引。\n- 修改评分后重跑 `..\u002Faliceskill\u002Fscripts\u002Frebuild_menu.py`，不要手改生成的索引。\n\n## 读取具体模块\n\n选定模块后完整读取 `..\u002F_modules\u002F\u003CMODULE_ID>\u002FSKILL.md`；取不到正文时如实报告，不得声称已按该模块执行。\n同一任务已读取的模块直接复用；换领域或新任务才重新路由。\n**任何阶段**选定\u002F换用\u002F补充参考模块，必须当场说出 `参考模块: \u003C类>: \u003C模块id>（\u003C用途>）`，禁止只执行不报名。\n",{"name":5,"description":7},"main","19a54ac988e9929160334271f5c1924ddd9b227e",19,"https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill","https:\u002F\u002Fgithub.com\u002Falicewe1","写一些自己用得上的工具，能自动化就绝不手动 · 自动化 \u002F 工程效率 \u002F Agent 技能生态 · 保持好奇，持续构建","2026-09-30 00:41:20",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add alicewe1\u002Falice_skill --skill alice-reverse",{"tool":37,"command":38},"bunx","bunx skills add alicewe1\u002Falice_skill --skill alice-reverse",{"tool":40,"command":41},"pnpm","pnpm dlx skills add alicewe1\u002Falice_skill --skill alice-reverse","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-reverse\u002FSKILL.md",true,[45,51,55,59,63,67,71,75,79],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fadvanced-security.md","REFERENCE","参考文档",1477,"https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-reverse\u002Freferences\u002Fadvanced-security.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Ffirmware-kernel.md",1375,"https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-reverse\u002Freferences\u002Ffirmware-kernel.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fforensics-malware.md",2273,"https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-reverse\u002Freferences\u002Fforensics-malware.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Finstrumentation-patching.md",1909,"https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-reverse\u002Freferences\u002Finstrumentation-patching.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fmobile.md",1919,"https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-reverse\u002Freferences\u002Fmobile.md",{"path":68,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fnative-binary.md",1562,"https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-reverse\u002Freferences\u002Fnative-binary.md",{"path":72,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fprotection-unpacking.md",2294,"https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-reverse\u002Freferences\u002Fprotection-unpacking.md",{"path":76,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fprotocol-web.md",2102,"https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-reverse\u002Freferences\u002Fprotocol-web.md",{"path":80,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fworkflow-tooling.md",2945,"https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-reverse\u002Freferences\u002Fworkflow-tooling.md",[84,91,98,105,112,119],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7DBMD9P6R27SWQCW5HYVWG0","alice","Alice 六类技能总路由。用户输入 Alice 或要求查看 Alice 技能菜单时，严格输出固定菜单；输入攻\u002F防模式、六类入口或直接描述任务时，按类别→领域→模块渐进路由。","https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Faliceskill\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7DBM630E2YKQP29194TT7HC","alice-pentest","web安全渐进路由（Web \u002F API \u002F 资产发现 \u002F 漏洞验证 \u002F 云与网络安全）。触发词：Web\u002FAPI\u002F资产发现\u002F端口\u002F漏洞验证\u002F云与网络安全；先选领域索引，再按任务匹配度与评分选模块，禁止一次读取全部领域。","https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-pentest\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7DBM20M2VDYV5D3MYDGBTQX","alice-game","游戏攻防渐进路由（游戏客户端 \u002F 内存 \u002F 图形 \u002F 反作弊 \u002F 安全研究）。触发词：游戏客户端\u002F内存\u002F图形\u002F偏移\u002F反作弊\u002F模拟器\u002F覆盖层；先选领域索引，再按任务匹配度与评分选模块，禁止一次读取全部领域。","https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-game\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M7DBKXVEKB8931MZG23VACFN","alice-crack","卡密授权渐进路由（卡密 \u002F 激活 \u002F 授权验证 \u002F 许可证管理 \u002F 本地授权分析）。触发词：卡密\u002F激活\u002F授权验证\u002Flicense\u002F机器码\u002F试用状态；先选领域索引，再按任务匹配度与评分选模块，禁止一次读取全部领域。","https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-crack\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":19},"01M7DBKTMT90MGV2WP8K73TMQD","alice-assist","技能指令渐进路由（技能路由 \u002F 评分 \u002F 吸收 \u002F 迁移 \u002F 自动化 \u002F 文档与平台集成）。触发词：技能创建\u002F吸收\u002F评分\u002F迁移\u002F自动化\u002F文档\u002F平台指令；先选领域索引，再按任务匹配度与评分选模块，禁止一次读取全部领域。","https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-assist\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":19},"01M7DBKNJ52EGFXHB7MQ3958VT","alice-ai","AI安全测试渐进路由（LLM \u002F 提示注入 \u002F MCP \u002F RAG \u002F Agent 安全测试）。触发词：LLM\u002F提示注入\u002FMCP\u002FRAG\u002FAgent\u002F模型安全测试；先选领域索引，再按任务匹配度与评分选模块，禁止一次读取全部领域。","https:\u002F\u002Fgithub.com\u002Falicewe1\u002Falice_skill\u002Fblob\u002Fmain\u002Falice-ai\u002FSKILL.md",[],[]]