[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KW4ZD0SG2HHB88WF2T72QD":3,"skill-same:01M6KW4ZD0SG2HHB88WF2T72QD":60},{"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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M6KW4ZD0SG2HHB88WF2T72QD","hook-management",null,"Create, modify, and delete Claude Code hooks and GitHub Copilot hook integrations safely using a discovery-first, non-destructive workflow.","rafsanulhasan\u002FHypermediaEngine","rafsanulhasan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2341142?v=4","01M6KW2HWPTZWK051N7B0HTBVG","Rafsanul Hasan","01M6KW2J0N3613382MF5DRN79H",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhook-management\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"management","hook","hook management","github","workflow","github copilot","copilot","create","delete","code","first","discovery","integrations","claude code hooks","hooks","2026-11-10 10:12:30",false,"---\nname: hook-management\ndescription: Create, modify, and delete Claude Code hooks and GitHub Copilot hook integrations safely using a discovery-first, non-destructive workflow.\n---\n\n# Hook Management\n\nUse this skill when a user asks to create, update, migrate, or remove hook behavior for either Claude Code or GitHub Copilot in this repository.\n\nThis skill is implementation-agnostic but actionable. It always discovers actual hook files and references first, then applies minimal, reversible changes.\n\n---\n\n## Inputs Expected\n\n- Operation: `create` | `modify` | `delete`\n- Platform target: `claude` | `copilot` | `both`\n- Hook scope: repository-wide, agent-specific, skill-specific, or command-specific\n- Hook name and intent: what the hook should do\n- Trigger\u002Fevent conditions: when it should run\n- Safety constraints: destructive actions allowed or not, confirmation requirements\n- Validation constraints: expected outputs, pass\u002Ffail signals, and rollback policy\n\nIf any required input is missing, ask only the minimum clarifying questions needed to proceed safely.\n\n---\n\n## Phase 0 - Context Load (silent)\n\n1. Read `.claude\u002FCLAUDE.md` and `AGENTS.md`.\n2. Invoke `Skill(\"manage-memory\", args: \"agent-manager\")`.\n3. Read repository governance files relevant to skill and command ownership.\n4. Discover current hook surfaces and references before proposing edits.\n\n---\n\n## Phase 1 - Discovery And Classification\n\n1. Detect existing Claude hook assets:\n   - `.claude\u002Fhooks\u002F**`\n   - `.claude\u002Fsettings.json`\n   - Any hook script references from Claude command\u002Fagent files\n2. Detect existing Copilot hook assets (format may vary by repo):\n   - `.github\u002Fhooks\u002F**`\n   - Any files that reference hook scripts, pre\u002Fpost actions, or enforcement callbacks\n3. Build a hook inventory table:\n   - platform\n   - file path\n   - trigger\u002Fevent\n   - linked script\u002Fconfig\n   - ownership and dependency notes\n4. Classify request into one mutation strategy:\n   - create new hook\n   - modify existing hook\n   - delete\u002Fdeprecate hook\n   - migrate\u002Fduplicate behavior across platforms\n\nDecision rule:\n- If target hook is not discoverable and operation is `modify` or `delete`, pause and ask for disambiguation instead of guessing.\n\n---\n\n## Phase 2 - Plan The Change\n\n1. Map requested behavior to one or both platforms.\n2. Choose smallest safe edit set:\n   - script\u002Fbody changes\n   - config wiring changes\n   - command\u002Fprompt\u002Finstruction reference changes\n3. Identify impact radius:\n   - direct dependents\n   - potential execution side effects\n   - test\u002Fvalidation path\n4. For `delete`, require an explicit safety plan:\n   - backup path or reversible rename\n   - confirmation checkpoint before permanent removal\n\nBranch logic:\n\n- `scope = claude`\n  - Edit only Claude hook files and references.\n- `scope = copilot`\n  - Edit only Copilot hook integration files and references.\n- `scope = both`\n  - Keep semantic parity; document intentional differences.\n\n- `operation = create`\n  - Add hook implementation + registration\u002Fwiring + docs note.\n- `operation = modify`\n  - Patch in place with minimal diff; preserve unrelated behavior.\n- `operation = delete`\n  - Prefer soft-delete first (disable\u002Funwire + backup) unless hard delete is explicitly approved.\n\n---\n\n## Phase 3 - Execute Create\u002FModify\u002FDelete\n\n### A. Create\n\n1. Create or extend the hook implementation file in discovered platform convention paths.\n2. Register hook in the relevant platform config\u002Freference files.\n3. Add brief inline comments only where logic is non-obvious.\n4. Ensure cross-platform naming consistency if `scope = both`.\n\n### B. Modify\n\n1. Patch only required logic and references.\n2. Keep input\u002Foutput contracts stable unless explicitly requested.\n3. Preserve existing guardrails (error handling, loop prevention, safety checks).\n\n### C. Delete\n\n1. Backup target hook content to a reversible location or branch-safe file before removal.\n2. Remove registration\u002Fwiring first, then implementation.\n3. Remove or update stale references.\n4. If permanent delete was not explicitly approved, leave a reversible deprecation marker.\n\n---\n\n## Phase 4 - Safety And Validation\n\nValidation checklist:\n\n- [ ] Discovery evidence captured (what existed before changes)\n- [ ] Correct platform scope honored (`claude`, `copilot`, or `both`)\n- [ ] No unrelated files modified\n- [ ] Hook wiring references resolve to valid files\n- [ ] Delete path is reversible unless explicit hard-delete approval exists\n- [ ] Behavior parity documented when targeting both platforms\n- [ ] Governance rules respected (agent-manager owns skill\u002Fcommand artifacts)\n\nCompletion criteria:\n\n1. Requested operation is fully implemented for the declared scope.\n2. Hook configuration and implementation are consistent.\n3. Risks and any assumptions are reported explicitly.\n4. User receives a concise delta summary and suggested next checks.\n\n---\n\n## Ambiguity And Weak-Spot Detection\n\nBefore finalizing, surface the most important unresolved points:\n\n1. Copilot hook substrate ambiguity:\n   - Whether this repo treats prompts\u002Finstructions\u002Fagents as hook surfaces or uses separate script hooks.\n2. Delete semantics ambiguity:\n   - Whether deletion means disable, deprecate, or permanently remove files.\n3. Execution contract ambiguity:\n   - Expected input\u002Foutput schema and fail-open vs fail-closed behavior for each platform.\n\nWhen these are unresolved, return targeted clarification questions with one recommended default.\n\n---\n\n## Example Invocations\n\n- `Skill(\"hook-management\", args: \"create claude pre-stop hook to enforce dotnet test before finish\")`\n- `Skill(\"hook-management\", args: \"modify copilot hook to add repository quality-gate reminder\")`\n- `Skill(\"hook-management\", args: \"delete both hook named enforce-tests using soft-delete with backup\")`\n- `Skill(\"hook-management\", args: \"migrate claude hook behavior to copilot and keep event semantics aligned\")`\n","# Hook Management\n\nUse this skill when a user asks to create, update, migrate, or remove hook behavior for either Claude Code or GitHub Copilot in this repository.\n\nThis skill is implementation-agnostic but actionable. It always discovers actual hook files and references first, then applies minimal, reversible changes.\n\n---\n\n## Inputs Expected\n\n- Operation: `create` | `modify` | `delete`\n- Platform target: `claude` | `copilot` | `both`\n- Hook scope: repository-wide, agent-specific, skill-specific, or command-specific\n- Hook name and intent: what the hook should do\n- Trigger\u002Fevent conditions: when it should run\n- Safety constraints: destructive actions allowed or not, confirmation requirements\n- Validation constraints: expected outputs, pass\u002Ffail signals, and rollback policy\n\nIf any required input is missing, ask only the minimum clarifying questions needed to proceed safely.\n\n---\n\n## Phase 0 - Context Load (silent)\n\n1. Read `.claude\u002FCLAUDE.md` and `AGENTS.md`.\n2. Invoke `Skill(\"manage-memory\", args: \"agent-manager\")`.\n3. Read repository governance files relevant to skill and command ownership.\n4. Discover current hook surfaces and references before proposing edits.\n\n---\n\n## Phase 1 - Discovery And Classification\n\n1. Detect existing Claude hook assets:\n   - `.claude\u002Fhooks\u002F**`\n   - `.claude\u002Fsettings.json`\n   - Any hook script references from Claude command\u002Fagent files\n2. Detect existing Copilot hook assets (format may vary by repo):\n   - `.github\u002Fhooks\u002F**`\n   - Any files that reference hook scripts, pre\u002Fpost actions, or enforcement callbacks\n3. Build a hook inventory table:\n   - platform\n   - file path\n   - trigger\u002Fevent\n   - linked script\u002Fconfig\n   - ownership and dependency notes\n4. Classify request into one mutation strategy:\n   - create new hook\n   - modify existing hook\n   - delete\u002Fdeprecate hook\n   - migrate\u002Fduplicate behavior across platforms\n\nDecision rule:\n- If target hook is not discoverable and operation is `modify` or `delete`, pause and ask for disambiguation instead of guessing.\n\n---\n\n## Phase 2 - Plan The Change\n\n1. Map requested behavior to one or both platforms.\n2. Choose smallest safe edit set:\n   - script\u002Fbody changes\n   - config wiring changes\n   - command\u002Fprompt\u002Finstruction reference changes\n3. Identify impact radius:\n   - direct dependents\n   - potential execution side effects\n   - test\u002Fvalidation path\n4. For `delete`, require an explicit safety plan:\n   - backup path or reversible rename\n   - confirmation checkpoint before permanent removal\n\nBranch logic:\n\n- `scope = claude`\n  - Edit only Claude hook files and references.\n- `scope = copilot`\n  - Edit only Copilot hook integration files and references.\n- `scope = both`\n  - Keep semantic parity; document intentional differences.\n\n- `operation = create`\n  - Add hook implementation + registration\u002Fwiring + docs note.\n- `operation = modify`\n  - Patch in place with minimal diff; preserve unrelated behavior.\n- `operation = delete`\n  - Prefer soft-delete first (disable\u002Funwire + backup) unless hard delete is explicitly approved.\n\n---\n\n## Phase 3 - Execute Create\u002FModify\u002FDelete\n\n### A. Create\n\n1. Create or extend the hook implementation file in discovered platform convention paths.\n2. Register hook in the relevant platform config\u002Freference files.\n3. Add brief inline comments only where logic is non-obvious.\n4. Ensure cross-platform naming consistency if `scope = both`.\n\n### B. Modify\n\n1. Patch only required logic and references.\n2. Keep input\u002Foutput contracts stable unless explicitly requested.\n3. Preserve existing guardrails (error handling, loop prevention, safety checks).\n\n### C. Delete\n\n1. Backup target hook content to a reversible location or branch-safe file before removal.\n2. Remove registration\u002Fwiring first, then implementation.\n3. Remove or update stale references.\n4. If permanent delete was not explicitly approved, leave a reversible deprecation marker.\n\n---\n\n## Phase 4 - Safety And Validation\n\nValidation checklist:\n\n- [ ] Discovery evidence captured (what existed before changes)\n- [ ] Correct platform scope honored (`claude`, `copilot`, or `both`)\n- [ ] No unrelated files modified\n- [ ] Hook wiring references resolve to valid files\n- [ ] Delete path is reversible unless explicit hard-delete approval exists\n- [ ] Behavior parity documented when targeting both platforms\n- [ ] Governance rules respected (agent-manager owns skill\u002Fcommand artifacts)\n\nCompletion criteria:\n\n1. Requested operation is fully implemented for the declared scope.\n2. Hook configuration and implementation are consistent.\n3. Risks and any assumptions are reported explicitly.\n4. User receives a concise delta summary and suggested next checks.\n\n---\n\n## Ambiguity And Weak-Spot Detection\n\nBefore finalizing, surface the most important unresolved points:\n\n1. Copilot hook substrate ambiguity:\n   - Whether this repo treats prompts\u002Finstructions\u002Fagents as hook surfaces or uses separate script hooks.\n2. Delete semantics ambiguity:\n   - Whether deletion means disable, deprecate, or permanently remove files.\n3. Execution contract ambiguity:\n   - Expected input\u002Foutput schema and fail-open vs fail-closed behavior for each platform.\n\nWhen these are unresolved, return targeted clarification questions with one recommended default.\n\n---\n\n## Example Invocations\n\n- `Skill(\"hook-management\", args: \"create claude pre-stop hook to enforce dotnet test before finish\")`\n- `Skill(\"hook-management\", args: \"modify copilot hook to add repository quality-gate reminder\")`\n- `Skill(\"hook-management\", args: \"delete both hook named enforce-tests using soft-delete with backup\")`\n- `Skill(\"hook-management\", args: \"migrate claude hook behavior to copilot and keep event semantics aligned\")`\n",{"name":5,"description":7},"main","00b2c68281930728ee390bb16cec32b88d2caac7",".claude\u002Fskills\u002Fhook-management","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine","https:\u002F\u002Fgithub.com\u002Frafsanulhasan","\r\n    MCSD || A-CSD || Software Architect\r\n\r\n","2026-06-06 07:47:06",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add rafsanulhasan\u002FHypermediaEngine --skill hook-management",{"tool":52,"command":53},"bunx","bunx skills add rafsanulhasan\u002FHypermediaEngine --skill hook-management",{"tool":55,"command":56},"pnpm","pnpm dlx skills add rafsanulhasan\u002FHypermediaEngine --skill hook-management","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhook-management\u002FSKILL.md",true,[],[61,93,112,131,160,183],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":72,"publishedAt":34},"01M6KWEJD606FG3DBBRM0W4DKW","write-tests","Test implementation skill for HypermediaEngine. Takes a confirmed test plan from design-test-cases and produces compilable, runnable xUnit tests following project conventions. Validates coverage quality through mutation testing. Invoked by the sqa-engineer agent after the test plan is approved.","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fwrite-tests\u002FSKILL.md",[67],{"categoryNo":68,"categoryName":69,"taxonomyType":70,"taxonomyTypeDesc":71},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92],"write tests","write","tests","testing","design","test","project conventions","test plan","Bash","plan","quality","xunit","read","edit","coverage","engineer","mutation testing","project","mutation","for",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":34},"01M6KWEF2XQ00C1Y6QCK7YHZ1H","write-documentation","Structured documentation writing workflow for HypermediaEngine. Writes or updates README.md files at the repo root and in each project directory (src\u002F, tests\u002F, samples\u002F, etc.) based on current implementation, ADRs, and architecture decisions.","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fwrite-documentation\u002FSKILL.md",[],[100,74,101,102,103,23,104,81,105,106,107,108,85,86,109,90,75,110,111,92],"documentation","write documentation","writing","directory","architecture","src","repo","decisions","README","files","updates","at",{"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":34},"01M6KWEBDXTXAVPQ3BHS3YYYNT","write-adr","Writes a numbered Architecture Decision Record (ADR) for a significant architectural choice in the HypermediaEngine project. Invoked by the software-architect agent whenever a consequential design decision is made or ratified. Saves the ADR to docs\u002Farchitecture\u002Fdecisions\u002F.","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fwrite-adr\u002FSKILL.md",[],[119,74,120,77,121,104,122,123,124,125,107,85,126,127,90,128,129,92,130],"adr","write adr","docs","architect","decision","choice","grep","architecture decision record","record","software","opus","architecture decision",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":143,"publishedAt":34},"01M6KWE76TM3QHGQ08PEB3KY6D","tunit-playwright-ui-testing","Comprehensive guidance for writing coded end-to-end UI tests in C# using TUnit.Playwright. Tests inherit from PageTest — the base class manages all browser lifecycle. Covers NuGet setup, PageTest inheritance, Page Object Model, browser configuration, parallelism limiting, and CI integration. Based on the official TUnit docs at https:\u002F\u002Ftunit.dev\u002Fdocs\u002Fexamples\u002Fplaywright.","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ftunit-playwright-ui-testing\u002FSKILL.md",[137,138],{"categoryNo":68,"categoryName":69,"taxonomyType":70,"taxonomyTypeDesc":71},{"categoryNo":139,"categoryName":140,"taxonomyType":141,"taxonomyTypeDesc":142},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[76,144,145,146,147,148,149,102,150,151,152,153,154,155,156,157,75,158,159,92],"playwright","ui","playwright ui testing","ui testing","tunit","tunit playwright ui testing","official","dev","examples","ci","lifecycle","model","page","inheritance","end","object",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":169,"publishedAt":34},"01M6KWE44A738GDK65QS02XJBG","triage","Task classification, decomposition, dependency mapping, and routing skill. Invoked by the triage-agent to break any user request into discrete, independently-routable work items with assigned priorities and agent chains.","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ftriage\u002FSKILL.md",[166],{"categoryNo":167,"categoryName":168,"taxonomyType":70,"taxonomyTypeDesc":71},"01JBSEEDCAT000000000000023","Skill与智能体开发",[162,170,171,172,173,174,175,176,177,178,179,180,181,182],"routing","classification","work","user","dependency","task","priorities","decomposition","user request","mapping","with","break","request",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":193,"publishedAt":34},"01M6KWDZ3W9ZKPR7FTTTSX8H2K","system-design","Expert system design skill. Use PROACTIVELY to design systems, review architectures, and assist software engineers in learning design principles and implementing them in the code with design patterns.","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fsystem-design\u002FSKILL.md",[189,192],{"categoryNo":190,"categoryName":191,"taxonomyType":70,"taxonomyTypeDesc":71},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":139,"categoryName":140,"taxonomyType":141,"taxonomyTypeDesc":142},[77,194,195,196,197,198,199,125,85,200,201,202,203,204,205,128,206,207,180,208],"system","system design","web","design systems","learning","haiku","use","design patterns","design principles","expert","patterns","systems","architectures","principles","implementing"]