[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C45EW428VM2A44PB2P6PN8":3,"skill-same:01M6C45EW428VM2A44PB2P6PN8":73},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":40,"install":41,"resources":54},"01M6C45EW428VM2A44PB2P6PN8","parallel-execution",null,"Build-test orchestration protocol for choosing and running parallel or serial implementation lanes with shared requirement contracts, convergence gates, and triage routing. Use when coordinating multiple concurrent implementation paths, managing convergence gates, or running triage routing. DO NOT USE FOR: exploring ideas or trade-offs (use brainstorming) or evaluating architecture (use software-architecture).","Grimblaz\u002Fagent-orchestra","Grimblaz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F74755849?v=4","01M6C430M9XZDHGHPWQVTQ3KMA","01M6C430RJY3MMX0QAZ3X8DR3Y",3,"MIT","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fparallel-execution\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28],"execution","parallel","parallel execution","triage","orchestration","test","architecture","brainstorming","routing","protocol","use","2026-11-10 10:12:30",false,"---\nname: parallel-execution\ndescription: \"Build-test orchestration protocol for choosing and running parallel or serial implementation lanes with shared requirement contracts, convergence gates, and triage routing. Use when coordinating multiple concurrent implementation paths, managing convergence gates, or running triage routing. DO NOT USE FOR: exploring ideas or trade-offs (use brainstorming) or evaluating architecture (use software-architecture).\"\n---\n# Parallel Execution Skill\n\n## Composite References\n\n- [references\u002Ferror-handling.md](references\u002Ferror-handling.md): canonical R5 subagent-call resilience, common issue routing, escalation patterns, terminal non-interactive guardrails, and terminal lifecycle protocol.\n- [references\u002Flean-dispatch-example.md](references\u002Flean-dispatch-example.md): dispatch-prompt economy — lean before\u002Fafter dispatch example for the canonical-source reference pattern.\n\n## Mode Declaration\n\nDeclare one mode before delegation: `Execution Mode: parallel` or `Execution Mode: serial`.\n\nRecord it in the progress-log header, `step.metadata.execution_mode`, the user-facing update, and any step-commit details tracked in the plan.\n\n## Requirement Contract (Mandatory)\n\nBefore delegation, define one shared Requirement Contract for the step:\n\nAcceptance-criteria slice, explicit invariants and edge cases, and non-goals.\n\nBoth implementation and testing lanes must use the same contract.\n\n## Protocol\n\n1. **Choose mode** using stability\u002Frisk criteria.\n2. **Create Requirement Contract** before any lane starts.\n3. **Run lanes**:\n   - `parallel`: launch Code-Smith and Test-Writer against the same contract.\n   - `serial`: run one lane first, then the second against the same contract.\n4. **Run triage** via Test-Writer after outputs are available.\n5. **Classify failures** as `code defect`, `test defect`, `harness\u002Fenv defect`, or `rc-divergence` with evidence.\n6. **Route corrections bidirectionally** until convergence:\n   - `code defect` -> Code-Smith\n   - `test defect` -> Test-Writer\n   - `harness\u002Fenv defect` -> responsible specialist or tooling path\n   - `rc-divergence` -> Code-Smith fixes implementation to match the Requirement Contract; CC re-evaluates; if divergence remains, Test-Writer re-derives assertions from the Requirement Contract, not the corrected implementation.\n7. **Enforce convergence gate** before advancing.\n8. **Run RC conformance check**: CC evaluates the step's Requirement Contract AC items against delivered code after convergence. Divergences route as `rc-divergence` using step 6.\n\n## Convergence Gate (Mandatory)\n\nDo not advance until Test-Writer explicitly confirms:\n\nGreen tests, valid assertions, and no brittle coupling.\n\nAfter convergence, protocol step 8 verifies the Requirement Contract AC items before step advance.\n\n## Loop Budget\n\n- Maximum 3 correction cycles per step.\n- If exceeded, perform root-cause review and escalate with a recommended option.\n- RC conformance correction gets 1 dedicated cycle outside the main 3-cycle budget. If still unresolved, escalate with the unresolved AC items and recommended options.\n\n## Anti-Test-Chasing Guardrail\n\nCode-Smith must satisfy the Requirement Contract and architecture constraints, not merely optimize for current failing assertions.\n\nIf a property or test appears over-constrained or invalid, classify it as potential `test defect` and route it back for test review with evidence.\n\n## Post-Issue Checkpoint (Mandatory)\n\nAt issue\u002FPR completion, record a short process checkpoint:\n\nWhat slowed us down, what failed late, and what single guardrail should be added next?\n\nTrack this in the completion summary to improve future cycles. For subagent rate-limit handling, execution-time escalation, and terminal guardrails that pair with this execution contract, load [references\u002Ferror-handling.md](references\u002Ferror-handling.md).\n\n## Gotchas\n\n| Trigger                                | Gotcha                                                              | Fix                                                                |\n| -------------------------------------- | ------------------------------------------------------------------- | ------------------------------------------------------------------ |\n| Lanes start with different requirements | Parallel work diverges and convergence turns into rework or churn | Define one shared Requirement Contract before any lane starts      |\n\n## Platform-specific invocation\n\nThis skill's methodology is tool-agnostic. Platform-specific routing lives alongside [platforms\u002Fcopilot.md](platforms\u002Fcopilot.md) and [platforms\u002Fclaude.md](platforms\u002Fclaude.md).\n","# Parallel Execution Skill\n\n## Composite References\n\n- [references\u002Ferror-handling.md](references\u002Ferror-handling.md): canonical R5 subagent-call resilience, common issue routing, escalation patterns, terminal non-interactive guardrails, and terminal lifecycle protocol.\n- [references\u002Flean-dispatch-example.md](references\u002Flean-dispatch-example.md): dispatch-prompt economy — lean before\u002Fafter dispatch example for the canonical-source reference pattern.\n\n## Mode Declaration\n\nDeclare one mode before delegation: `Execution Mode: parallel` or `Execution Mode: serial`.\n\nRecord it in the progress-log header, `step.metadata.execution_mode`, the user-facing update, and any step-commit details tracked in the plan.\n\n## Requirement Contract (Mandatory)\n\nBefore delegation, define one shared Requirement Contract for the step:\n\nAcceptance-criteria slice, explicit invariants and edge cases, and non-goals.\n\nBoth implementation and testing lanes must use the same contract.\n\n## Protocol\n\n1. **Choose mode** using stability\u002Frisk criteria.\n2. **Create Requirement Contract** before any lane starts.\n3. **Run lanes**:\n   - `parallel`: launch Code-Smith and Test-Writer against the same contract.\n   - `serial`: run one lane first, then the second against the same contract.\n4. **Run triage** via Test-Writer after outputs are available.\n5. **Classify failures** as `code defect`, `test defect`, `harness\u002Fenv defect`, or `rc-divergence` with evidence.\n6. **Route corrections bidirectionally** until convergence:\n   - `code defect` -> Code-Smith\n   - `test defect` -> Test-Writer\n   - `harness\u002Fenv defect` -> responsible specialist or tooling path\n   - `rc-divergence` -> Code-Smith fixes implementation to match the Requirement Contract; CC re-evaluates; if divergence remains, Test-Writer re-derives assertions from the Requirement Contract, not the corrected implementation.\n7. **Enforce convergence gate** before advancing.\n8. **Run RC conformance check**: CC evaluates the step's Requirement Contract AC items against delivered code after convergence. Divergences route as `rc-divergence` using step 6.\n\n## Convergence Gate (Mandatory)\n\nDo not advance until Test-Writer explicitly confirms:\n\nGreen tests, valid assertions, and no brittle coupling.\n\nAfter convergence, protocol step 8 verifies the Requirement Contract AC items before step advance.\n\n## Loop Budget\n\n- Maximum 3 correction cycles per step.\n- If exceeded, perform root-cause review and escalate with a recommended option.\n- RC conformance correction gets 1 dedicated cycle outside the main 3-cycle budget. If still unresolved, escalate with the unresolved AC items and recommended options.\n\n## Anti-Test-Chasing Guardrail\n\nCode-Smith must satisfy the Requirement Contract and architecture constraints, not merely optimize for current failing assertions.\n\nIf a property or test appears over-constrained or invalid, classify it as potential `test defect` and route it back for test review with evidence.\n\n## Post-Issue Checkpoint (Mandatory)\n\nAt issue\u002FPR completion, record a short process checkpoint:\n\nWhat slowed us down, what failed late, and what single guardrail should be added next?\n\nTrack this in the completion summary to improve future cycles. For subagent rate-limit handling, execution-time escalation, and terminal guardrails that pair with this execution contract, load [references\u002Ferror-handling.md](references\u002Ferror-handling.md).\n\n## Gotchas\n\n| Trigger                                | Gotcha                                                              | Fix                                                                |\n| -------------------------------------- | ------------------------------------------------------------------- | ------------------------------------------------------------------ |\n| Lanes start with different requirements | Parallel work diverges and convergence turns into rework or churn | Define one shared Requirement Contract before any lane starts      |\n\n## Platform-specific invocation\n\nThis skill's methodology is tool-agnostic. Platform-specific routing lives alongside [platforms\u002Fcopilot.md](platforms\u002Fcopilot.md) and [platforms\u002Fclaude.md](platforms\u002Fclaude.md).\n",{"name":5,"description":7},"main","d5486aacc32c9ca1b07173cfd530f8fe75c29e58","skills\u002Fparallel-execution",0,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra","https:\u002F\u002Fgithub.com\u002FGrimblaz","2026-08-16 01:12:46",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add Grimblaz\u002Fagent-orchestra --skill parallel-execution",{"tool":47,"command":48},"bunx","bunx skills add Grimblaz\u002Fagent-orchestra --skill parallel-execution",{"tool":50,"command":51},"pnpm","pnpm dlx skills add Grimblaz\u002Fagent-orchestra --skill parallel-execution","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fparallel-execution\u002FSKILL.md",true,[55,61,65,69],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"platforms\u002Fclaude.md","REFERENCE","参考文档",802,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fparallel-execution\u002Fplatforms\u002Fclaude.md",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"platforms\u002Fcopilot.md",396,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fparallel-execution\u002Fplatforms\u002Fcopilot.md",{"path":66,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ferror-handling.md",8417,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fparallel-execution\u002Freferences\u002Ferror-handling.md",{"path":70,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Flean-dispatch-example.md",1497,"https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fparallel-execution\u002Freferences\u002Flean-dispatch-example.md",[74,106,131,145,172,193],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":88,"publishedAt":29},"01M6C48YMJVFHM7DVGG1WWW5RJ","webapp-testing","Playwright end-to-end testing guidance for web apps, with practical patterns and setup steps. Use when creating or improving browser-based E2E coverage, test stability, and CI execution. DO NOT USE FOR: React component tests (use ui-testing), canvas game interaction (use browser-canvas-testing), TDD workflow (use test-driven-development), debugging failures (use systematic-debugging), or randomized property tests (use property-based-testing).","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[80,85],{"categoryNo":81,"categoryName":82,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":86,"categoryName":87,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000009","前端开发",[89,90,91,92,93,94,95,23,96,97,98,99,100,101,102,18,103,104,105,28],"testing","webapp testing","webapp","canvas","tdd","workflow","playwright","web","react","component","debugging","development","browser","ci","e2e","game","coverage",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":29},"01M6C48TNNP2KCSQXV8YK7SK49","verification-before-completion","Evidence-based verification checklist before marking work complete. Use before PRs, releases, marking tickets done, or any \"I'm finished\" declaration; also when naming a baseline commit for a differential suite claim, when designing a mutation campaign or red-run evidence, when making an absence claim, a universal claim, or a one-time demonstration offered as a standing guarantee, when attributing a measurement or claiming a sweep or verification loop is complete, and when stating what a check or a CI suite will do about a change. DO NOT USE FOR: post-merge cleanup or archival (use post-pr-review) or processing GitHub review comments (use code-review-intake).","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[113,114,115,116,117,118,119,120,121,122,123,124,102,125,126,127,128,28,129,130],"verification","verification before completion","review","change","commit","merge","pr","cleanup","run","code","code-review","intake","loop","verification loop","work","check","evidence","campaign",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":29},"01M6C48QZWNTP7JGKD32QZAKKX","validation-methodology","Reusable validation and review methodology for staged validation, failure triage, and prosecution-depth setup. Use when running validation ladders, triaging failures, or executing adversarial review passes. DO NOT USE FOR: CE Gate orchestration, specialist dispatch ownership, or step execution flow (keep those in Code-Conductor).","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fvalidation-methodology\u002FSKILL.md",[],[138,139,140,115,21,22,141,142,122,143,18,28,144],"validation","methodology","validation methodology","setup","adversarial review","flow","dispatch",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":159,"publishedAt":29},"01M6C48MCAHG5Z79BJ369CRYRZ","upstream-onboarding","Shared opening-phase protocol for upstream agents (Experience-Owner, Solution-Designer, Issue-Planner) and Code-Conductor when invoked on an existing GitHub issue. Renders a scaled context brief and runs a standards check on inherited work at each phase boundary. Use when a user-invocable agent receives a request referencing an existing GitHub issue and must load solution-authoring and upstream-onboarding at the opening phase. DO NOT USE FOR: subagent dispatches (which already operate within an assessed session context); post-merge review (use post-pr-review); research or non-tree subagents.","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fupstream-onboarding\u002FSKILL.md",[151,154],{"categoryNo":152,"categoryName":153,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":155,"categoryName":156,"taxonomyType":157,"taxonomyTypeDesc":158},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[160,161,115,162,163,118,164,119,122,27,165,166,167,168,169,127,128,170,171,28],"onboarding","upstream onboarding","github","research","standards check","brief","boundary","designer","subagent","planner","user","session",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":186,"publishedAt":29},"01M6C48GPVE120TGPMD1CS365H","ui-testing","Resilient React component testing strategies focusing on user behavior. Use when writing or reviewing component-level React tests, fixing flaky component tests, or establishing React testing patterns. DO NOT USE FOR: Playwright E2E tests (use webapp-testing), canvas game interaction (use browser-canvas-testing), TDD workflow (use test-driven-development), debugging failures (use systematic-debugging), UI component design (use frontend-design), or randomized property tests (use property-based-testing).","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fui-testing\u002FSKILL.md",[178,179,180,183],{"categoryNo":81,"categoryName":82,"taxonomyType":83,"taxonomyTypeDesc":84},{"categoryNo":86,"categoryName":87,"taxonomyType":83,"taxonomyTypeDesc":84},{"categoryNo":181,"categoryName":182,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":184,"categoryName":185,"taxonomyType":157,"taxonomyTypeDesc":158},"01JBSEEDCAT000000000000032","设计师",[89,187,188,189,190,191,92,94,95,23,97,98,99,100,101,192,103,104,28,91],"ui","ui testing","frontend","design","writing","testing patterns",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":201,"publishedAt":29},"01M6C48DRJ9XBDR2FW0W37DY53","ui-iteration","Reusable screenshot-driven UI polish workflow for iterative visual refinement. Use when improving layout, hierarchy, spacing, feedback, or Tailwind-based presentation through repeated review-and-adjust passes. DO NOT USE FOR: functional bug fixing, accessibility-only audits, or major redesign strategy work (use Code-Smith or frontend-design).","https:\u002F\u002Fgithub.com\u002FGrimblaz\u002Fagent-orchestra\u002Fblob\u002Fmain\u002Fskills\u002Fui-iteration\u002FSKILL.md",[199,200],{"categoryNo":86,"categoryName":87,"taxonomyType":83,"taxonomyTypeDesc":84},{"categoryNo":184,"categoryName":185,"taxonomyType":157,"taxonomyTypeDesc":158},[187,202,189,190,115,94,203,122,204,205,206,207,208,127,209,210,28,211],"ui iteration","accessibility","screenshot","Tailwind","polish","ui polish","feedback","redesign","strategy","only"]