[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AEFXR79PM241QFGHQCFWRK":3,"skill-same:01M7AEFXR79PM241QFGHQCFWRK":54},{"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":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7AEFXR79PM241QFGHQCFWRK","case-review",null,"Reviews a reverse-skill case package for scope readiness, Evidence to Finding to Path traceability, work item coverage, timeline references, and optional artifact hash integrity before report handoff.","Rain-kl\u002FReverseTemplate","Rain-kl","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F63696351?v=4","01M7AE7E8ECRECCF300YM1A8BS","Ryan","01M7AE7E9Q3AYTB7W3NNSV3200",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FRain-kl\u002FReverseTemplate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-skill\u002Fskills\u002Fcase-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: case-review\ndescription: Reviews a reverse-skill case package for scope readiness, Evidence to Finding to Path traceability, work item coverage, timeline references, and optional artifact hash integrity before report handoff.\n---\n\n# Evidence Graph Review\n\nUse this skill when a reverse engineering, forensics, CTF, or authorized security case needs a defensible handoff. It audits the existing `work\u002F\u003Ccase>\u002F` package without changing the case or touching a target.\n\n## Scope\n\nThis skill covers:\n\n- Scope metadata and target-activity readiness\n- Evidence record structure and reproducibility fields\n- References from work items and timeline entries to Evidence\n- Structured Findings and Paths in report Markdown\n- Optional SHA-256 verification for case-local artifacts\n- A Markdown or JSON review result for a report handoff\n\nIt MUST NOT perform reconnaissance, exploitation, dynamic instrumentation, or target changes. Those actions belong to the routed analysis skill and require the case scope gate.\n\n## ACTION REQUIRED\n\n1. `NOW`: read `..\u002Ffield-journal\u002Fprecedent-reverse.md` and confirm that this is a review of an existing authorized case package.\n2. `NOW`: confirm the case path and choose read-only review mode.\n3. `NEXT`: read `..\u002Ftool-index.md`; this skill uses only Python 3 standard library and does not require bootstrap.\n4. `NEXT`: run `python3 scripts\u002Freview_case.py \u003Ccase-root> --format markdown`.\n5. `ACT`: resolve every error, then rerun the review before claiming a handoff is complete.\n\n## Tool dependencies\n\n| Tool | Required | Purpose | Auto-bootstrap |\n|------|----------|---------|---------------|\n| Python 3.9+ | Yes | Runs the read-only case review script | No, use the platform Python installation |\n\nNo network access or third-party package is required.\n\n## Workflow\n\n### Phase 1: Intake\n\nRun the review against the existing case directory:\n\n```bash\npython3 skills\u002Fcase-review\u002Fscripts\u002Freview_case.py work\u002F\u003Ccase> --format markdown\n```\n\nConfirm that `scope.md`, `timeline.md`, `workitems.md`, and `evidence\u002F` are present. A non-strict review reports scope warnings while a strict review treats warnings as handoff blockers.\n\n## 建议下一步（选一个编号）\n\n1. 修复 scope.md 中的授权、范围或 network_profile 字段\n2. 继续检查 Evidence 记录的可复现命令和来源\n3. 导出当前 review 结果并附到阶段性报告\n4. 换 JSON 输出接入 CI 或其他审查工具\n5. 暂停，先确认审查范围\n\n### Phase 2: Traceability\n\nReview the checks for:\n\n- Evidence IDs that do not exist\n- Findings without `evidence_ids`\n- Paths without an allowed `path_type` or Evidence reference\n- Work items and timeline entries pointing to unknown Evidence\n- Unlinked Evidence records\n- Validated Findings with low confidence\n\nAn offline observation may use `repro_command: n\u002Fa` only when its `notes` field explicitly documents the offline limitation.\n\nUse JSON when another tool needs stable fields:\n\n```bash\npython3 skills\u002Fcase-review\u002Fscripts\u002Freview_case.py work\u002F\u003Ccase> --format json\n```\n\n## 建议下一步（选一个编号）\n\n1. 补写缺失的 Evidence，并保留原始命令\n2. 将候选 Finding 绑定到 Evidence 后重新审查\n3. 为调用链或攻击链补充 P-id 和 Path 步骤\n4. 生成 Markdown handoff summary\n5. 换回 PRIMARY skill 继续分析\n\n### Phase 3: Fixity verification\n\nWhen an Evidence record contains both `content_hash` and `artifact_path`, verify the case-local artifact:\n\n```bash\npython3 skills\u002Fcase-review\u002Fscripts\u002Freview_case.py work\u002F\u003Ccase> --verify-hashes --strict\n```\n\nThe script accepts `sha256:\u003C64 hex characters>` and checks that the artifact remains inside the case root. A hash mismatch is a hard failure.\n\nThe PowerShell Evidence helper can record a hash while appending a record:\n\n```powershell\npowershell -File skills\u002Fscripts\u002Fappend-evidence.ps1 -CaseRoot work\\\u003Ccase> -Id E-001 -Title \"Sample hash\" -ReproCommand \"sha256sum evidence\u002Fsample.bin\" -ArtifactPath \"evidence\\sample.bin\"\n```\n\n## 建议下一步（选一个编号）\n\n1. 修复 hash mismatch 或替换已污染的工作副本\n2. 为未固定的原始文件补充 SHA-256 和 artifact_path\n3. 继续进入报告生成阶段\n4. 导出 JSON 结果供 CI 保存\n5. 暂停并请求人工复核\n\n### Phase 4: Handoff\n\nUse strict mode before a final report or specialist handoff:\n\n```bash\npython3 skills\u002Fcase-review\u002Fscripts\u002Freview_case.py work\u002F\u003Ccase> --strict --format markdown > work\u002F\u003Ccase>\u002Freport\u002Fcase-review.md\n```\n\nThe command is read-only with respect to the case unless shell redirection is explicitly used to save its output. The review is not legal advice and does not replace organizational evidence handling procedures.\n\n## 建议下一步（选一个编号）\n\n1. 将通过的 review 结果交给 `docs-generator\u002F` 生成正式报告\n2. 回到 PRIMARY skill 补齐新的分析证据\n3. 归档 Markdown 和 JSON review 结果\n4. 暂停并请求人工复核\n\n## Language behavior contract\n\n- Internal reasoning, tool selection, and phase control: English.\n- User-visible messages, section labels, reports, and next-step menus: Chinese unless the user requests another language.\n- Default bilingual labels place Chinese first and English second, separated by `\u002F`.\n\n## Bootstrap boundary\n\nThis skill has no third-party dependency. If Python 3 is unavailable, the only allowed recovery action is the repository bootstrap path when a Python capability is registered for the current platform. If no such capability is registered, stop and report the missing runtime. Do not guess executable paths, download packages, or perform a manual install from inside this skill.\n\n## Routing context\n\n**Upstream entry**: any reverse, forensics, CTF, or authorized security skill that has produced a case package.\n\n**Downstream exit**: `docs-generator\u002F` for a formal report, or the original PRIMARY skill when the graph is incomplete.\n\n**Related modules**: `ops\u002Fevidence-finding-path.md`, `ops\u002Ftimeline-workitem.md`, `digital-forensics\u002F`, `reverse-engineering\u002F`, and `docs-generator\u002F`.\n\n## References\n\n- [NIST SP 800-86: Guide to Integrating Forensic Techniques into Incident Response](https:\u002F\u002Fcsrc.nist.gov\u002Fpubs\u002Fsp\u002F800\u002F86\u002Ffinal)\n- [SWGDE Best Practices for Computer Forensic Acquisitions](https:\u002F\u002Fwww.swgde.org\u002Fdocuments\u002Fpublished-complete-listing\u002F17-f-002-2-1\u002F)\n- [SWGDE Best Practices for Archiving Digital and Multimedia Evidence](https:\u002F\u002Fwww.swgde.org\u002Fdocuments\u002Fpublished-complete-listing\u002F19-f-003-best-practices-for-archiving-digital-and-multimedia-evidence\u002F)\n\n## 任务完成自检\n\n- [ ] 我是否审查了 scope.md、timeline.md、workitems.md 和 evidence\u002F？\n- [ ] 所有 Finding 是否引用了现存 Evidence？\n- [ ] 所有 Path 是否包含合法 path_type 和 Evidence 引用？\n- [ ] 是否执行了 hash verification，或记录了未执行原因？\n- [ ] 是否以 strict 模式重新运行并保存了 review 结果？\n","# Evidence Graph Review\n\nUse this skill when a reverse engineering, forensics, CTF, or authorized security case needs a defensible handoff. It audits the existing `work\u002F\u003Ccase>\u002F` package without changing the case or touching a target.\n\n## Scope\n\nThis skill covers:\n\n- Scope metadata and target-activity readiness\n- Evidence record structure and reproducibility fields\n- References from work items and timeline entries to Evidence\n- Structured Findings and Paths in report Markdown\n- Optional SHA-256 verification for case-local artifacts\n- A Markdown or JSON review result for a report handoff\n\nIt MUST NOT perform reconnaissance, exploitation, dynamic instrumentation, or target changes. Those actions belong to the routed analysis skill and require the case scope gate.\n\n## ACTION REQUIRED\n\n1. `NOW`: read `..\u002Ffield-journal\u002Fprecedent-reverse.md` and confirm that this is a review of an existing authorized case package.\n2. `NOW`: confirm the case path and choose read-only review mode.\n3. `NEXT`: read `..\u002Ftool-index.md`; this skill uses only Python 3 standard library and does not require bootstrap.\n4. `NEXT`: run `python3 scripts\u002Freview_case.py \u003Ccase-root> --format markdown`.\n5. `ACT`: resolve every error, then rerun the review before claiming a handoff is complete.\n\n## Tool dependencies\n\n| Tool | Required | Purpose | Auto-bootstrap |\n|------|----------|---------|---------------|\n| Python 3.9+ | Yes | Runs the read-only case review script | No, use the platform Python installation |\n\nNo network access or third-party package is required.\n\n## Workflow\n\n### Phase 1: Intake\n\nRun the review against the existing case directory:\n\n```bash\npython3 skills\u002Fcase-review\u002Fscripts\u002Freview_case.py work\u002F\u003Ccase> --format markdown\n```\n\nConfirm that `scope.md`, `timeline.md`, `workitems.md`, and `evidence\u002F` are present. A non-strict review reports scope warnings while a strict review treats warnings as handoff blockers.\n\n## 建议下一步（选一个编号）\n\n1. 修复 scope.md 中的授权、范围或 network_profile 字段\n2. 继续检查 Evidence 记录的可复现命令和来源\n3. 导出当前 review 结果并附到阶段性报告\n4. 换 JSON 输出接入 CI 或其他审查工具\n5. 暂停，先确认审查范围\n\n### Phase 2: Traceability\n\nReview the checks for:\n\n- Evidence IDs that do not exist\n- Findings without `evidence_ids`\n- Paths without an allowed `path_type` or Evidence reference\n- Work items and timeline entries pointing to unknown Evidence\n- Unlinked Evidence records\n- Validated Findings with low confidence\n\nAn offline observation may use `repro_command: n\u002Fa` only when its `notes` field explicitly documents the offline limitation.\n\nUse JSON when another tool needs stable fields:\n\n```bash\npython3 skills\u002Fcase-review\u002Fscripts\u002Freview_case.py work\u002F\u003Ccase> --format json\n```\n\n## 建议下一步（选一个编号）\n\n1. 补写缺失的 Evidence，并保留原始命令\n2. 将候选 Finding 绑定到 Evidence 后重新审查\n3. 为调用链或攻击链补充 P-id 和 Path 步骤\n4. 生成 Markdown handoff summary\n5. 换回 PRIMARY skill 继续分析\n\n### Phase 3: Fixity verification\n\nWhen an Evidence record contains both `content_hash` and `artifact_path`, verify the case-local artifact:\n\n```bash\npython3 skills\u002Fcase-review\u002Fscripts\u002Freview_case.py work\u002F\u003Ccase> --verify-hashes --strict\n```\n\nThe script accepts `sha256:\u003C64 hex characters>` and checks that the artifact remains inside the case root. A hash mismatch is a hard failure.\n\nThe PowerShell Evidence helper can record a hash while appending a record:\n\n```powershell\npowershell -File skills\u002Fscripts\u002Fappend-evidence.ps1 -CaseRoot work\\\u003Ccase> -Id E-001 -Title \"Sample hash\" -ReproCommand \"sha256sum evidence\u002Fsample.bin\" -ArtifactPath \"evidence\\sample.bin\"\n```\n\n## 建议下一步（选一个编号）\n\n1. 修复 hash mismatch 或替换已污染的工作副本\n2. 为未固定的原始文件补充 SHA-256 和 artifact_path\n3. 继续进入报告生成阶段\n4. 导出 JSON 结果供 CI 保存\n5. 暂停并请求人工复核\n\n### Phase 4: Handoff\n\nUse strict mode before a final report or specialist handoff:\n\n```bash\npython3 skills\u002Fcase-review\u002Fscripts\u002Freview_case.py work\u002F\u003Ccase> --strict --format markdown > work\u002F\u003Ccase>\u002Freport\u002Fcase-review.md\n```\n\nThe command is read-only with respect to the case unless shell redirection is explicitly used to save its output. The review is not legal advice and does not replace organizational evidence handling procedures.\n\n## 建议下一步（选一个编号）\n\n1. 将通过的 review 结果交给 `docs-generator\u002F` 生成正式报告\n2. 回到 PRIMARY skill 补齐新的分析证据\n3. 归档 Markdown 和 JSON review 结果\n4. 暂停并请求人工复核\n\n## Language behavior contract\n\n- Internal reasoning, tool selection, and phase control: English.\n- User-visible messages, section labels, reports, and next-step menus: Chinese unless the user requests another language.\n- Default bilingual labels place Chinese first and English second, separated by `\u002F`.\n\n## Bootstrap boundary\n\nThis skill has no third-party dependency. If Python 3 is unavailable, the only allowed recovery action is the repository bootstrap path when a Python capability is registered for the current platform. If no such capability is registered, stop and report the missing runtime. Do not guess executable paths, download packages, or perform a manual install from inside this skill.\n\n## Routing context\n\n**Upstream entry**: any reverse, forensics, CTF, or authorized security skill that has produced a case package.\n\n**Downstream exit**: `docs-generator\u002F` for a formal report, or the original PRIMARY skill when the graph is incomplete.\n\n**Related modules**: `ops\u002Fevidence-finding-path.md`, `ops\u002Ftimeline-workitem.md`, `digital-forensics\u002F`, `reverse-engineering\u002F`, and `docs-generator\u002F`.\n\n## References\n\n- [NIST SP 800-86: Guide to Integrating Forensic Techniques into Incident Response](https:\u002F\u002Fcsrc.nist.gov\u002Fpubs\u002Fsp\u002F800\u002F86\u002Ffinal)\n- [SWGDE Best Practices for Computer Forensic Acquisitions](https:\u002F\u002Fwww.swgde.org\u002Fdocuments\u002Fpublished-complete-listing\u002F17-f-002-2-1\u002F)\n- [SWGDE Best Practices for Archiving Digital and Multimedia Evidence](https:\u002F\u002Fwww.swgde.org\u002Fdocuments\u002Fpublished-complete-listing\u002F19-f-003-best-practices-for-archiving-digital-and-multimedia-evidence\u002F)\n\n## 任务完成自检\n\n- [ ] 我是否审查了 scope.md、timeline.md、workitems.md 和 evidence\u002F？\n- [ ] 所有 Finding 是否引用了现存 Evidence？\n- [ ] 所有 Path 是否包含合法 path_type 和 Evidence 引用？\n- [ ] 是否执行了 hash verification，或记录了未执行原因？\n- [ ] 是否以 strict 模式重新运行并保存了 review 结果？\n",{"name":5,"description":7},"main","5b045f5effb9db25a3199f06d549a00373078082",".agents\u002Fskills\u002Freverse-skill\u002Fskills\u002Fcase-review","https:\u002F\u002Fgithub.com\u002FRain-kl\u002FReverseTemplate","https:\u002F\u002Fgithub.com\u002FRain-kl","2026-09-19 20:30:24",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add Rain-kl\u002FReverseTemplate --skill case-review",{"tool":36,"command":37},"bunx","bunx skills add Rain-kl\u002FReverseTemplate --skill case-review",{"tool":39,"command":40},"pnpm","pnpm dlx skills add Rain-kl\u002FReverseTemplate --skill case-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRain-kl\u002FReverseTemplate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-skill\u002Fskills\u002Fcase-review\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Freview_case.py","SCRIPT","脚本",20450,"https:\u002F\u002Fgithub.com\u002FRain-kl\u002FReverseTemplate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-skill\u002Fskills\u002Fcase-review\u002Fscripts\u002Freview_case.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_review_case.py",6924,"https:\u002F\u002Fgithub.com\u002FRain-kl\u002FReverseTemplate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-skill\u002Fskills\u002Fcase-review\u002Ftests\u002Ftest_review_case.py",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7AEMCR7PHAB7SRFX17KAKKS","windows-ad","Use for authorized Active Directory and Windows identity attacks including Kerberos, AD CS, BloodHound paths, NTLM relay, and domain privilege escalation research.","https:\u002F\u002Fgithub.com\u002FRain-kl\u002FReverseTemplate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-skill\u002Fskills\u002Fwindows-ad\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7AEMA913F9CGJPHXGRA4DMW","wifi-wireless","Use for authorized wireless security assessment including Wi-Fi capture, WPA handshake analysis, rogue AP detection research, and lab-only deauth testing.","https:\u002F\u002Fgithub.com\u002FRain-kl\u002FReverseTemplate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-skill\u002Fskills\u002Fwifi-wireless\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7AEM7SKHX0JD2HKD4EP7FCH","threat-hunting","Use for blue-team threat hunting, detection engineering with Sigma\u002FYARA, SIEM query design, and incident detection validation.","https:\u002F\u002Fgithub.com\u002FRain-kl\u002FReverseTemplate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-skill\u002Fskills\u002Fthreat-hunting\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7AEM4S61F6E0F20A2HB50QM","thick-client","Use for authorized security testing of desktop thick clients including local storage, update channels, IPC, traffic, and client-side trust boundaries.","https:\u002F\u002Fgithub.com\u002FRain-kl\u002FReverseTemplate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-skill\u002Fskills\u002Fthick-client\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7AEM1KQQHZBD9RDQ2P3GKWH","supply-chain-security","Use for software supply-chain security assessment covering SBOM, SCA, CI\u002FCD pipelines, container images, build integrity, dependency provenance, and vulnerability reachability.","https:\u002F\u002Fgithub.com\u002FRain-kl\u002FReverseTemplate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-skill\u002Fskills\u002Fsupply-chain-security\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7AEKXA2PNZA2NYRW63RFNZS","dsl-vm-reverse","Reverse JavaScript-based custom DSL\u002FVM interpreters, non-standard WASM-like runtimes, and risk-control engines. Use when analyzing IIFE or switch-based opcode dispatchers, extracting instruction tables, recovering bytecode semantics, capturing VM state at runtime, or reconstructing execution flow.","https:\u002F\u002Fgithub.com\u002FRain-kl\u002FReverseTemplate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-skill\u002Fskills\u002Freverse-engineering\u002Fdsl-vm-reverse\u002FSKILL.md",[],[]]