[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7574C37CKJ3BNTVGPZMY1DA":3,"skill-same:01M7574C37CKJ3BNTVGPZMY1DA":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7574C37CKJ3BNTVGPZMY1DA","archi-dependency-topology",null,"Review dependency topology, cycles, direction, and import\u002Fworkspace graph risk. Use when architecture risk depends on dependency direction, circular dependencies, package graph shape, layering imports, workspace coupling, or replacing Architec with source-backed topology evidence.","SeemSeam\u002Fagent-roles-spec","SeemSeam","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F29205273?v=4","01M7572MDYPSM30Y29C9HRMGK7","01M7572MEGCX02T16BHYV9PBVK",19,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FSeemSeam\u002Fagent-roles-spec\u002Fblob\u002Fmain\u002Froles\u002Farchi\u002Fskills\u002Farchi-dependency-topology\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: archi-dependency-topology\ndescription: Review dependency topology, cycles, direction, and import\u002Fworkspace graph risk. Use when architecture risk depends on dependency direction, circular dependencies, package graph shape, layering imports, workspace coupling, or replacing Architec with source-backed topology evidence.\n---\n\n# Archi Dependency Topology\n\nUse this skill to review structural dependency shape. This is a method, not a\ntool requirement.\n\nRead `references\u002Farchitecture-toolbox.md` when selecting optional dependency\ngraph tools or explaining provenance.\n\n## Inputs\n\n- User scope: diff, package, module, workspace, full repo, or target boundary.\n- Source files, package manifests, build files, module docs, and import paths.\n- Existing dependency evidence when present: lockfiles, workspace manifests,\n  dependency-cruiser\u002FMadge\u002FESLint import rules, ArchUnit tests, CodeQL\u002FSemgrep\n  findings, Architec\u002FHippo artifacts, or CI reports.\n\n## Workflow\n\n1. Define the expected direction of dependencies in plain language.\n2. Build the lightest useful topology map from available source:\n   - packages, modules, layers, domains, adapters, generated code, tests;\n   - inbound and outbound dependencies for the reviewed scope;\n   - known cycles, fan-in\u002Ffan-out hotspots, and cross-layer shortcuts.\n3. Compare observed edges with the expected direction.\n4. Classify each concern:\n   - cycle that affects initialization, testing, release, or ownership;\n   - dependency inversion pressure;\n   - shared utility or platform module becoming a hidden domain dependency;\n   - generated or test-only dependency that should not be treated as runtime;\n   - optional edge that is acceptable but needs documentation.\n5. Verify actionable claims against source paths. Tool output is evidence, not\n   fact.\n6. Recommend the smallest topology change or guardrail that reduces risk.\n\n## Optional Evidence Routes\n\n- JS\u002FTS: dependency-cruiser, Madge, ESLint import\u002Fno-cycle or boundaries rules.\n- JVM: ArchUnit slices, layers, and cycle checks.\n- Multi-language repos: workspace\u002Fbuild graph, package manifests, module maps,\n  CI dependency reports, and direct source inspection.\n- Security\u002Fdataflow adjacency: CodeQL or Semgrep evidence only when topology\n  risk includes unsafe flow, not as a general architecture oracle.\n\nDo not install tools or refresh generated graphs unless the user asks for fresh\nevidence or stale topology is central to the answer.\n\n## Degraded Semantics\n\nIf no graph tool is available, produce a source-backed topology sketch from\nmanifests, imports, changed files, and docs. Mark missing graph coverage as\nresidual risk instead of stopping the review.\n\n## Output\n\n```text\nTopology Review\n- expected direction:\n- evidence used:\n- observed graph:\n\nFindings\n- severity:\n- edge or cycle:\n- evidence:\n- impact:\n- recommendation:\n\nGuardrails\n- existing:\n- proposed:\n- verification:\n\nResidual Risk\n- ...\n```\n\n## Boundaries\n\nStay review-only. Do not approve releases, rewrite architecture rules, mutate\ngenerated graph artifacts, or claim that a clean graph proves runtime\ncorrectness.\n","# Archi Dependency Topology\n\nUse this skill to review structural dependency shape. This is a method, not a\ntool requirement.\n\nRead `references\u002Farchitecture-toolbox.md` when selecting optional dependency\ngraph tools or explaining provenance.\n\n## Inputs\n\n- User scope: diff, package, module, workspace, full repo, or target boundary.\n- Source files, package manifests, build files, module docs, and import paths.\n- Existing dependency evidence when present: lockfiles, workspace manifests,\n  dependency-cruiser\u002FMadge\u002FESLint import rules, ArchUnit tests, CodeQL\u002FSemgrep\n  findings, Architec\u002FHippo artifacts, or CI reports.\n\n## Workflow\n\n1. Define the expected direction of dependencies in plain language.\n2. Build the lightest useful topology map from available source:\n   - packages, modules, layers, domains, adapters, generated code, tests;\n   - inbound and outbound dependencies for the reviewed scope;\n   - known cycles, fan-in\u002Ffan-out hotspots, and cross-layer shortcuts.\n3. Compare observed edges with the expected direction.\n4. Classify each concern:\n   - cycle that affects initialization, testing, release, or ownership;\n   - dependency inversion pressure;\n   - shared utility or platform module becoming a hidden domain dependency;\n   - generated or test-only dependency that should not be treated as runtime;\n   - optional edge that is acceptable but needs documentation.\n5. Verify actionable claims against source paths. Tool output is evidence, not\n   fact.\n6. Recommend the smallest topology change or guardrail that reduces risk.\n\n## Optional Evidence Routes\n\n- JS\u002FTS: dependency-cruiser, Madge, ESLint import\u002Fno-cycle or boundaries rules.\n- JVM: ArchUnit slices, layers, and cycle checks.\n- Multi-language repos: workspace\u002Fbuild graph, package manifests, module maps,\n  CI dependency reports, and direct source inspection.\n- Security\u002Fdataflow adjacency: CodeQL or Semgrep evidence only when topology\n  risk includes unsafe flow, not as a general architecture oracle.\n\nDo not install tools or refresh generated graphs unless the user asks for fresh\nevidence or stale topology is central to the answer.\n\n## Degraded Semantics\n\nIf no graph tool is available, produce a source-backed topology sketch from\nmanifests, imports, changed files, and docs. Mark missing graph coverage as\nresidual risk instead of stopping the review.\n\n## Output\n\n```text\nTopology Review\n- expected direction:\n- evidence used:\n- observed graph:\n\nFindings\n- severity:\n- edge or cycle:\n- evidence:\n- impact:\n- recommendation:\n\nGuardrails\n- existing:\n- proposed:\n- verification:\n\nResidual Risk\n- ...\n```\n\n## Boundaries\n\nStay review-only. Do not approve releases, rewrite architecture rules, mutate\ngenerated graph artifacts, or claim that a clean graph proves runtime\ncorrectness.\n",{"name":5,"description":7},"main","d07398b0a36ffa994efd970a554dd9596932ed5c","roles\u002Farchi\u002Fskills\u002Farchi-dependency-topology",2,"https:\u002F\u002Fgithub.com\u002FSeemSeam\u002Fagent-roles-spec","https:\u002F\u002Fgithub.com\u002FSeemSeam","2026-08-14 10:00:06",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add SeemSeam\u002Fagent-roles-spec --skill archi-dependency-topology",{"tool":36,"command":37},"bunx","bunx skills add SeemSeam\u002Fagent-roles-spec --skill archi-dependency-topology",{"tool":39,"command":40},"pnpm","pnpm dlx skills add SeemSeam\u002Fagent-roles-spec --skill archi-dependency-topology","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSeemSeam\u002Fagent-roles-spec\u002Fblob\u002Fmain\u002Froles\u002Farchi\u002Fskills\u002Farchi-dependency-topology\u002FSKILL.md",true,[],[45,51,58,65,72,79],{"skillNo":46,"name":47,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":48,"categories":49,"keywords":50,"publishedAt":18},"01M757C4HNYHR92Z3MDGPW9JSA","example-skill","https:\u002F\u002Fgithub.com\u002FSeemSeam\u002Fagent-roles-spec\u002Fblob\u002Fmain\u002Ftemplates\u002Frole-with-skills\u002Fskills\u002Fexample-skill\u002FSKILL.md",[],[],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M757C2B2YT62JBH98CG1BKWG","su-status","从 docs 人读真相源与 .ccb 协调件读取当前项目、Requirement 或子任务状态。","https:\u002F\u002Fgithub.com\u002FSeemSeam\u002Fagent-roles-spec\u002Fblob\u002Fmain\u002Froles\u002Fsu-ccb\u002Fskills\u002Fsu-status\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M757C0DVFT88AFBXN1PFXH9D","su-revise-breakdown","根据用户反馈重写 Requirement breakdown draft。","https:\u002F\u002Fgithub.com\u002FSeemSeam\u002Fagent-roles-spec\u002Fblob\u002Fmain\u002Froles\u002Fsu-ccb\u002Fskills\u002Fsu-revise-breakdown\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M757BY5XVMPKEK118D782PRM","su-review","审查执行回执、diff 和验证证据，决定通过、返工、replan 或升级用户。","https:\u002F\u002Fgithub.com\u002FSeemSeam\u002Fagent-roles-spec\u002Fblob\u002Fmain\u002Froles\u002Fsu-ccb\u002Fskills\u002Fsu-review\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M757BW1R61F61X7JJF2SSJET","su-resume","从 docs 人读真相源与 .ccb 协调件恢复 paused\u002Fdeferred\u002Fin-progress 主体的上下文。","https:\u002F\u002Fgithub.com\u002FSeemSeam\u002Fagent-roles-spec\u002Fblob\u002Fmain\u002Froles\u002Fsu-ccb\u002Fskills\u002Fsu-resume\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M757BTEAFRRXA9DY3KBRTRNY","su-reconcile","AI-native 自检 docs 人读真相源、.ccb 协调件与 Console 投影漂移，并按审批结果执行修复。","https:\u002F\u002Fgithub.com\u002FSeemSeam\u002Fagent-roles-spec\u002Fblob\u002Fmain\u002Froles\u002Fsu-ccb\u002Fskills\u002Fsu-reconcile\u002FSKILL.md",[],[]]