[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M786HHHC5PEVENCDZ3YM8MJ7":3,"skill-same:01M786HHHC5PEVENCDZ3YM8MJ7":48},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M786HHHC5PEVENCDZ3YM8MJ7","dispatching-parallel-agents",null,"Use when facing 2+ independent test failures, bugs, research questions, map lanes, or implementation tasks that can run without shared write state. Dispatch native subagents through the owning sp-* workflow.","chenziyang110\u002Flaunchdeck","chenziyang110","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43693913?v=4","01M7863EBWK1D0P6A29YGEMAS4","Robin11","01M7863ECM1VB6RXDMHTW90D2T",0,"MIT","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fdispatching-parallel-agents\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"dispatching-parallel-agents\"\ndescription: \"Use when facing 2+ independent test failures, bugs, research questions, map lanes, or implementation tasks that can run without shared write state. Dispatch native subagents through the owning sp-* workflow.\"\ncompatibility: \"Requires spec-kit project structure with .specify\u002F directory\"\nmetadata:\n  author: \"github-spec-kit\"\n  source: \"templates\u002Fpassive-skills\u002Fdispatching-parallel-agents\u002FSKILL.md\"\n---\n\n\n# Dispatching Parallel Agents (Spec Kit Plus)\n\nUse this skill when there are 2+ independent lanes: unrelated failing tests,\nseparate bugs, distinct modules, read-only evidence lanes, testing-system build\nlanes, map scan\u002Fbuild lanes, or implementation tasks with non-overlapping\nwrite-sets.\n\nThe stable default is current-runtime dispatch. Do not turn parallel work into a\nuser coordination problem when native subagents are available.\n\nCurrent routing vocabulary:\n\n- Use parallel subagents only after the owning workflow selects delegation and\n  confirms that parallelism materially improves the critical path or evidence quality.\n- Dispatch `one-subagent` when one safe lane is ready.\n- Dispatch `parallel-subagents` when two or more independent lanes can run\n  concurrently.\n- If delegation becomes unsafe or unavailable, re-evaluate the owning workflow's\n  route instead of treating parallelism as mandatory.\n- Do not use old strategy labels as routing choices.\n\n## When to Use\n\n- 2+ independent lanes can be understood or changed without waiting on each\n  other.\n- Each lane has a clear owner, scope, and verification target.\n- Write-set overlap is absent or can be explicitly sequenced at a join point.\n- Running the lanes in parallel materially improves throughput, evidence quality,\n  or verification confidence.\n\n## Process\n\n1. **Route first**: Select the owning `sp-*` workflow before dispatch. Common\n   canonical routes are `sp-quick`, `sp-debug`, `sp-map-scan`, `sp-map-build`,\n   and `sp-implement`. When telling the user what to type, use placeholders such\n   as `$sp-quick`, `$sp-debug`, `$sp-map-scan`,\n   `$sp-map-build`, or `$sp-implement`.\n2. **Split lanes**: Name each lane, purpose, read context, write-set, forbidden\n   paths, shared surfaces, and verification target.\n   `sp-debug` dispatches parallel agents only when the investigation exposes\n   independent evidence lanes; small focused investigations may stay\n   leader-inline under the debug session contract.\n3. **Check conflicts**: Do not dispatch two writers to the same file or shared\n   state unless one lane is explicitly read-only or the workflow defines a safe\n   join point.\n4. **Packetize just in time**: Compile validated packets only for the selected\n   current lanes. Raw task text is not enough and future batches stay unexpanded.\n5. **Dispatch native subagents**: Use `parallel-subagents` on the\n   `native-subagents` surface first, such as Codex `spawn_agent`\u002F`wait_agent`,\n   Claude Task, or the active CLI's equivalent. Keep the leader focused on\n   integration and conflict resolution.\n6. **Join on structured handoff**: Each worker must report changed files,\n   verification run, failures, open risks, and whether its acceptance target is\n   met. Integrate only after the handoff is specific enough to review.\n\n## Fallbacks\n\n- Use `sp-teams` only when Codex work needs durable team state, result files,\n  explicit join tracking, or lifecycle control beyond one in-session burst.\n- Use a separate terminal only when the current runtime has no native subagents\n  and no managed-team path can safely represent the lanes.\n- If lanes share write state or one fix may resolve the others, keep the work in\n  one sequential workflow run until the dependency is clarified.\n\n## Behavioral Rules\n\n- Do not fix unrelated systems in one leader-inline pass when current-runtime\n  native subagents can handle independent bounded lanes.\n- Do not dispatch agents that will modify the same write-set concurrently.\n- Do not ask the user to manually coordinate parallel terminals as the first\n  option.\n- Do not mark a lane complete from silence, idle status, or a vague summary.\n- If the first split reveals hidden coupling, stop parallel execution and move\n  the coupled work behind one owner or join point.\n\n## Red Flags\n\n- \"Fix all failing tests\" with failures spread across unrelated modules.\n- Multiple implementation tasks touch different write-sets, but the leader is\n  about to execute them serially without checking native subagents.\n- A worker prompt does not include a write-set, forbidden paths, or verification\n  target.\n- A handoff says \"done\" without file paths and command output summary.\n- The fallback plan starts with \"open another separate terminal\" even though the\n  current runtime supports native subagents.\n","# Dispatching Parallel Agents (Spec Kit Plus)\n\nUse this skill when there are 2+ independent lanes: unrelated failing tests,\nseparate bugs, distinct modules, read-only evidence lanes, testing-system build\nlanes, map scan\u002Fbuild lanes, or implementation tasks with non-overlapping\nwrite-sets.\n\nThe stable default is current-runtime dispatch. Do not turn parallel work into a\nuser coordination problem when native subagents are available.\n\nCurrent routing vocabulary:\n\n- Use parallel subagents only after the owning workflow selects delegation and\n  confirms that parallelism materially improves the critical path or evidence quality.\n- Dispatch `one-subagent` when one safe lane is ready.\n- Dispatch `parallel-subagents` when two or more independent lanes can run\n  concurrently.\n- If delegation becomes unsafe or unavailable, re-evaluate the owning workflow's\n  route instead of treating parallelism as mandatory.\n- Do not use old strategy labels as routing choices.\n\n## When to Use\n\n- 2+ independent lanes can be understood or changed without waiting on each\n  other.\n- Each lane has a clear owner, scope, and verification target.\n- Write-set overlap is absent or can be explicitly sequenced at a join point.\n- Running the lanes in parallel materially improves throughput, evidence quality,\n  or verification confidence.\n\n## Process\n\n1. **Route first**: Select the owning `sp-*` workflow before dispatch. Common\n   canonical routes are `sp-quick`, `sp-debug`, `sp-map-scan`, `sp-map-build`,\n   and `sp-implement`. When telling the user what to type, use placeholders such\n   as `$sp-quick`, `$sp-debug`, `$sp-map-scan`,\n   `$sp-map-build`, or `$sp-implement`.\n2. **Split lanes**: Name each lane, purpose, read context, write-set, forbidden\n   paths, shared surfaces, and verification target.\n   `sp-debug` dispatches parallel agents only when the investigation exposes\n   independent evidence lanes; small focused investigations may stay\n   leader-inline under the debug session contract.\n3. **Check conflicts**: Do not dispatch two writers to the same file or shared\n   state unless one lane is explicitly read-only or the workflow defines a safe\n   join point.\n4. **Packetize just in time**: Compile validated packets only for the selected\n   current lanes. Raw task text is not enough and future batches stay unexpanded.\n5. **Dispatch native subagents**: Use `parallel-subagents` on the\n   `native-subagents` surface first, such as Codex `spawn_agent`\u002F`wait_agent`,\n   Claude Task, or the active CLI's equivalent. Keep the leader focused on\n   integration and conflict resolution.\n6. **Join on structured handoff**: Each worker must report changed files,\n   verification run, failures, open risks, and whether its acceptance target is\n   met. Integrate only after the handoff is specific enough to review.\n\n## Fallbacks\n\n- Use `sp-teams` only when Codex work needs durable team state, result files,\n  explicit join tracking, or lifecycle control beyond one in-session burst.\n- Use a separate terminal only when the current runtime has no native subagents\n  and no managed-team path can safely represent the lanes.\n- If lanes share write state or one fix may resolve the others, keep the work in\n  one sequential workflow run until the dependency is clarified.\n\n## Behavioral Rules\n\n- Do not fix unrelated systems in one leader-inline pass when current-runtime\n  native subagents can handle independent bounded lanes.\n- Do not dispatch agents that will modify the same write-set concurrently.\n- Do not ask the user to manually coordinate parallel terminals as the first\n  option.\n- Do not mark a lane complete from silence, idle status, or a vague summary.\n- If the first split reveals hidden coupling, stop parallel execution and move\n  the coupled work behind one owner or join point.\n\n## Red Flags\n\n- \"Fix all failing tests\" with failures spread across unrelated modules.\n- Multiple implementation tasks touch different write-sets, but the leader is\n  about to execute them serially without checking native subagents.\n- A worker prompt does not include a write-set, forbidden paths, or verification\n  target.\n- A handoff says \"done\" without file paths and command output summary.\n- The fallback plan starts with \"open another separate terminal\" even though the\n  current runtime supports native subagents.\n",{"name":5,"metadata":24,"description":7,"compatibility":27},{"author":25,"source":26},"github-spec-kit","templates\u002Fpassive-skills\u002Fdispatching-parallel-agents\u002FSKILL.md","Requires spec-kit project structure with .specify\u002F directory","main","021f5cbe02157229460a577e9a585f2da6d78cb0",".codex\u002Fskills\u002Fdispatching-parallel-agents","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck","https:\u002F\u002Fgithub.com\u002Fchenziyang110","2026-08-07 18:10:54",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add chenziyang110\u002Flaunchdeck --skill dispatching-parallel-agents",{"tool":40,"command":41},"bunx","bunx skills add chenziyang110\u002Flaunchdeck --skill dispatching-parallel-agents",{"tool":43,"command":44},"pnpm","pnpm dlx skills add chenziyang110\u002Flaunchdeck --skill dispatching-parallel-agents","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fdispatching-parallel-agents\u002FSKILL.md",true,[],[49,56,62,68,75,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7875F3HQ1GF5F6BR36KY3JE","launchdeck-agent","Codex host adapter contract fixture for Launchdeck.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fagent-hosts\u002Fcodex\u002Fskill\u002FSKILL.md",[],[],{"skillNo":57,"name":51,"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},"01M7875DV2DQR33K1NFJHKAMZP","Claude host adapter contract fixture for Launchdeck.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fagent-hosts\u002Fclaude\u002Fskill\u002FSKILL.md",[],[],{"skillNo":63,"name":51,"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":67,"publishedAt":19},"01M78759JQ7A6FQ8KDQTNYS3X9","Use this skill aggressively for local project lifecycle operations even when the user does not mention Launchdeck: start this project, run the dev server, dev, build, test, restart service, stop service, show logs, inspect ports, port is occupied, clean cache; and when the user explicitly asks to configure this local project for Launchdeck or create or generate a project-adapted `.launchdeck.yml`, including 为这个项目生成 Launchdeck 配置. Do not use for ordinary code edits, docs-only work, general explanations, API design discussion, or production deployment unless the user also asks to operate or configure a local project or service.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002Fagent\u002Finstaller-payload\u002Fskill\u002Flaunchdeck-agent\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M78753ZJQ7G2CZT1W1G8WRJV","zig-testing","Use ONLY when user explicitly requests Zig test code, built-in test runner configuration,\ntest failure diagnosis, or coverage for Zig projects.\n\nTriggers: \"write test zig\", \"zig test\", \"testing.allocator\", \"zig coverage\",\n\"comptime test\", \"zig expectError\", \"zig snapshot test\", \"zig fuzz\".\n\nDo NOT activate for: general Zig coding without test context, build.zig configuration\nfor non-test targets, Zig compiler errors, or Zig build system setup.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fzig-testing\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M78750JXY4Z5D5W1EX3PQ31Z","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"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},"01M7874X2T83EQQFRCEY5SJJVC","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fverification-before-completion\u002FSKILL.md",[],[]]