[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A00XES10W2ZP5KFYBQDFK7":3,"skill-same:01M7A00XES10W2ZP5KFYBQDFK7":57},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7A00XES10W2ZP5KFYBQDFK7","dispatch-panel-review",null,"Dispatch the four dimensional PR reviewers in parallel. Use when review_orchestrator starts or repeats a panel review, or when the user says dispatch panel review or \u002Fdispatch_panel_review. Do not review the diff yourself.","sazlin\u002Floadout","sazlin","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7120031?v=4","01M79ZSNX5RMXATQTSH5NGHN51","Sean Azlin","01M79ZSNXQ5HCTYC1RE7J5CAPF",0,"MIT","https:\u002F\u002Fgithub.com\u002Fsazlin\u002Floadout\u002Fblob\u002Fmain\u002Fskills\u002Fdispatch-panel-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dispatch-panel-review\ndescription: >-\n  Dispatch the four dimensional PR reviewers in parallel. Use when\n  review_orchestrator starts or repeats a panel review, or when the user\n  says dispatch panel review or \u002Fdispatch_panel_review. Do not review the\n  diff yourself.\n---\n\n# Dispatch panel review\n\nLaunch `review_correctness`, `review_maintainability`, `review_scale`, and\n`review_security` **in one turn, in parallel**, on the same GitHub PR \u002F diff.\n\n## When to use\n\n- `review_orchestrator` is starting or repeating the Review phase\n- The user asks for `\u002Fdispatch_panel_review` or a panel review\n\n**Do not use** to fix code, judge `VERIFIERS.md`, or merge.\n\n## Steps\n\n1. Resolve the change set. Loop 1 is the full PR diff (`gh pr view` \u002F\n   `gh pr diff` or the git range in the brief). Loop 2+ uses the\n   two-dot resolver-commit range the orchestrator named\n   (`git diff \u003Cleft-sha>..HEAD` for `issue_resolver` commits since the\n   previous panel), not the full PR vs base. Use that range as written.\n   Do not recompute the left SHA. Every reviewer gets the **same**\n   summary, paths, PR id, and range.\n2. Issue **four** isolated subagent calls in a **single** response. One call\n   per response is a protocol failure. Loops 2+ still dispatch **all four**\n   reviewers. Never skip a reviewer.\n3. Each brief:\n   - \"You are the `\u003Cagent>` reviewer. Follow `.claude\u002Fagents\u002F\u003Cagent>.md`.\"\n   - \"Return only your JSON issue schema. Do not edit files. Do not review other dimensions.\"\n   - Enough diff\u002Fpath context that the reviewer does not need this chat.\n   - On loop 2+: \"Review only that range. File regressions those\n     resolver commits introduced.\"\n4. Wait for all four JSON reports. If a report is missing the issue schema,\n   one retry, then record that reviewer as `missing`.\n5. Do **not** review in-process. Do **not** write `TASKS_TO_RESOLVE.md` or\n   `TASKS_TO_RESOLVE-\u003Cshort-sha>.md` here (`dedupe-and-write-tasks` is next).\n\n## Harness\n\n- Cursor: four `Task` calls in one message (named agent type if available).\n  Do not pass inherit or a Fast model; reviewers are pinned to Grok 4.6\n  medium, not Fast (`grok-4.6[effort=medium,fast=false]`).\n- Claude Code: four Agent calls using the custom agent names.\n\n## Guardrails\n\n- Never become a single combined reviewer\n- Never drop a reviewer's issues\n- Never skip a reviewer on loop 2 or 3\n- Never edit source, `VERIFIERS.md`, or history in this skill\n","# Dispatch panel review\n\nLaunch `review_correctness`, `review_maintainability`, `review_scale`, and\n`review_security` **in one turn, in parallel**, on the same GitHub PR \u002F diff.\n\n## When to use\n\n- `review_orchestrator` is starting or repeating the Review phase\n- The user asks for `\u002Fdispatch_panel_review` or a panel review\n\n**Do not use** to fix code, judge `VERIFIERS.md`, or merge.\n\n## Steps\n\n1. Resolve the change set. Loop 1 is the full PR diff (`gh pr view` \u002F\n   `gh pr diff` or the git range in the brief). Loop 2+ uses the\n   two-dot resolver-commit range the orchestrator named\n   (`git diff \u003Cleft-sha>..HEAD` for `issue_resolver` commits since the\n   previous panel), not the full PR vs base. Use that range as written.\n   Do not recompute the left SHA. Every reviewer gets the **same**\n   summary, paths, PR id, and range.\n2. Issue **four** isolated subagent calls in a **single** response. One call\n   per response is a protocol failure. Loops 2+ still dispatch **all four**\n   reviewers. Never skip a reviewer.\n3. Each brief:\n   - \"You are the `\u003Cagent>` reviewer. Follow `.claude\u002Fagents\u002F\u003Cagent>.md`.\"\n   - \"Return only your JSON issue schema. Do not edit files. Do not review other dimensions.\"\n   - Enough diff\u002Fpath context that the reviewer does not need this chat.\n   - On loop 2+: \"Review only that range. File regressions those\n     resolver commits introduced.\"\n4. Wait for all four JSON reports. If a report is missing the issue schema,\n   one retry, then record that reviewer as `missing`.\n5. Do **not** review in-process. Do **not** write `TASKS_TO_RESOLVE.md` or\n   `TASKS_TO_RESOLVE-\u003Cshort-sha>.md` here (`dedupe-and-write-tasks` is next).\n\n## Harness\n\n- Cursor: four `Task` calls in one message (named agent type if available).\n  Do not pass inherit or a Fast model; reviewers are pinned to Grok 4.6\n  medium, not Fast (`grok-4.6[effort=medium,fast=false]`).\n- Claude Code: four Agent calls using the custom agent names.\n\n## Guardrails\n\n- Never become a single combined reviewer\n- Never drop a reviewer's issues\n- Never skip a reviewer on loop 2 or 3\n- Never edit source, `VERIFIERS.md`, or history in this skill\n",{"name":5,"description":7},"main","f6497b6aafdead5bb7cf244894b930f699a53e46","skills\u002Fdispatch-panel-review",1,"https:\u002F\u002Fgithub.com\u002Fsazlin\u002Floadout","https:\u002F\u002Fgithub.com\u002Fsazlin","https:\u002F\u002Fseanazlin.com","Principal Engineer & Engineering Leader | AI Infrastructure & Marketplace Systems | Fractional CTO for 0-to-1 Startups","2026-11-14 20:13:46",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add sazlin\u002Floadout --skill dispatch-panel-review",{"tool":39,"command":40},"bunx","bunx skills add sazlin\u002Floadout --skill dispatch-panel-review",{"tool":42,"command":43},"pnpm","pnpm dlx skills add sazlin\u002Floadout --skill dispatch-panel-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsazlin\u002Floadout\u002Fblob\u002Fmain\u002Fskills\u002Fdispatch-panel-review\u002FSKILL.md",true,[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"evals\u002Fevals.json","REFERENCE","参考文档",645,"https:\u002F\u002Fgithub.com\u002Fsazlin\u002Floadout\u002Fblob\u002Fmain\u002Fskills\u002Fdispatch-panel-review\u002Fevals\u002Fevals.json",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"evals\u002Ffiles\u002Fbrief.md",60,"https:\u002F\u002Fgithub.com\u002Fsazlin\u002Floadout\u002Fblob\u002Fmain\u002Fskills\u002Fdispatch-panel-review\u002Fevals\u002Ffiles\u002Fbrief.md",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7A06GGYSGA1EA79WNMD8JHJ","demo","Demo skill","https:\u002F\u002Fgithub.com\u002Fsazlin\u002Floadout\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmini_loadout\u002Fskills\u002Fdemo\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7A06BTSB17JVWZ52Z3DQDYY","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fsazlin\u002Floadout\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7A069Y4ZJZBPP82QJ9KBHTV","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fsazlin\u002Floadout\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7A0676YNTT61WYZ7241T3RB","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\u002Fsazlin\u002Floadout\u002Fblob\u002Fmain\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7A065AY047VH6JBN19WFAZ9","using-superpowers","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Fsazlin\u002Floadout\u002Fblob\u002Fmain\u002Fskills\u002Fusing-superpowers\u002FSKILL.md",[],[],{"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":19},"01M7A062FBQ3VPWZT3BP8DWYKA","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002Fsazlin\u002Floadout\u002Fblob\u002Fmain\u002Fskills\u002Fusing-git-worktrees\u002FSKILL.md",[],[]]