[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C4DPPA49XKASHCZMQ2BJR6":3,"skill-same:01M6C4DPPA49XKASHCZMQ2BJR6":51},{"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":23,"linkOnly":24,"markdownContent":25,"markdownBody":26,"frontMatter":27,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":50},"01M6C4DPPA49XKASHCZMQ2BJR6","arena",null,"Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for \u002Farena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.","mintuz\u002Fskills","mintuz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F447031?v=4","01M6BVWJYSVR4XQC9AQCEMWQRG","Adam Bulmer","01M6C4DCXKNYZB281YB3PZDJJG",35,"MIT","https:\u002F\u002Fgithub.com\u002Fmintuz\u002Fskills\u002Fblob\u002Fmain\u002Fevals\u002Farena\u002Fprechange\u002FSKILL.md",[],[5,19,20,21,22],"parallel","pick","spawn","use","2026-11-10 10:12:30",false,"---\nname: arena\ndescription: \"Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for \u002Farena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.\"\ndisable-model-invocation: true\n---\n\n# Arena\n\nOpen a todolist with one entry per phase (Frame, Fan out, Cross-judge, Pick, Graft, Verify) before launching anything.\n\n## Phase A: Frame\n\nEvery candidate gets the same prompt, so the prompt is the contract.\n\n1. State the artifact each candidate is producing.\n2. Derive the rubric, 3-6 concrete gradeable criteria for what success looks like on *this* task. It is the picker's tool in Phase D. Candidates only see the task.\n3. Pick the runners. Use the `arena runners` line in `~\u002F.cursor\u002Frules\u002Fpstack-models.mdc`. If the rule or that line is missing, default to one each on `claude-opus-5-5-xhigh` and `grok-4.7-xhigh-fast`. An `auto` or `inherit-parent` entry in this line or the cross-judge line means the parent model, so omit `model` for it. If the Task tool rejects a configured entry, run that seat on its family's default and say so. Families go by prefix: `claude-*` and `grok-*`. With no family match, use `claude-opus-5-5-xhigh`. If it rejects a default, use the closest valid slug of the same family from its error message. Spawn more runners when the arena covers multiple design directions. Use the same model N times when the work is generation-bound rather than judgment-sensitive.\n4. Give each candidate its own output location (a git worktree where possible, otherwise `\u002Ftmp\u002Farena-\u003Cslug>\u002Fcandidate-\u003Cn>\u002F`), per the **separate-before-serializing-shared-state** principle skill.\n\n## Phase B: Fan out\n\nSpawn all N subagents in one message with `run_in_background: true`, each with the task, the path to the shared grounding, its own output path, and instructions to produce the artifact and a short rationale naming the alternatives it considered and what it rejected.\n\nIf a candidate produces no output, proceed with N-1 and note the dropout.\n\n## Phase C: Cross-judge\n\nAfter all Phase B candidates complete, choose one model from the `arena cross-judge pool` line in `~\u002F.cursor\u002Frules\u002Fpstack-models.mdc`. If the rule or that line is missing, choose from `claude-opus-5-5-xhigh` and `grok-4.7-xhigh-fast`. Prefer a different model family from the parent's. Spawn one readonly judge subagent on that model. It sees the rubric and the candidates by path label, scores each criterion, and recommends a base with rationale. It runs in parallel with your reading in Phase D. Don't spawn it while candidates are still writing.\n\n## Phase D: Pick a base\n\nRead every candidate end to end before picking. Score each against the rubric criterion by criterion, not on holistic feel, and compare with the cross-judge. Agreement on the base confirms the pick. Disagreement means one of you is biased or the rubric was ambiguous. Read both rationales before deciding.\n\nPick the base a future maintainer can extend most easily without breaking invariants. When two feel tied, prefer the cleaner boundary or smaller API, per the Laziness Protocol.\n\n## Phase E: Graft\n\nWalk each losing candidate once more for what is worth porting into the base, usually one or two things per candidate, not most of it. Fold each graft in by hand, per the **redesign-from-first-principles** principle skill, so the result stays coherent under one mental model. Don't paste mechanically.\n\nIf the candidates converge on one shape, that is strong agreement. Note it and ship the consensus shape. No graft is needed. If they wildly diverge, Phase A was under-specified. Reframe and re-run rather than averaging the divergence.\n\n## Phase F: Verify\n\nVerify the synthesized artifact like any other output, per the **prove-it-works** principle skill. If verification finds a problem the arena missed, either Phase A was wrong (re-frame and re-run) or a candidate caught it and you missed the graft (go back to Phase E). Don't paper over it.\n\n## Outputs\n\nOne synthesized artifact, with a short synthesis note alongside naming the base and why, the cross-judge's verdict, each graft with its source candidate, what was rejected and why, any convergence or dropouts, and the verification result.\n","# Arena\n\nOpen a todolist with one entry per phase (Frame, Fan out, Cross-judge, Pick, Graft, Verify) before launching anything.\n\n## Phase A: Frame\n\nEvery candidate gets the same prompt, so the prompt is the contract.\n\n1. State the artifact each candidate is producing.\n2. Derive the rubric, 3-6 concrete gradeable criteria for what success looks like on *this* task. It is the picker's tool in Phase D. Candidates only see the task.\n3. Pick the runners. Use the `arena runners` line in `~\u002F.cursor\u002Frules\u002Fpstack-models.mdc`. If the rule or that line is missing, default to one each on `claude-opus-5-5-xhigh` and `grok-4.7-xhigh-fast`. An `auto` or `inherit-parent` entry in this line or the cross-judge line means the parent model, so omit `model` for it. If the Task tool rejects a configured entry, run that seat on its family's default and say so. Families go by prefix: `claude-*` and `grok-*`. With no family match, use `claude-opus-5-5-xhigh`. If it rejects a default, use the closest valid slug of the same family from its error message. Spawn more runners when the arena covers multiple design directions. Use the same model N times when the work is generation-bound rather than judgment-sensitive.\n4. Give each candidate its own output location (a git worktree where possible, otherwise `\u002Ftmp\u002Farena-\u003Cslug>\u002Fcandidate-\u003Cn>\u002F`), per the **separate-before-serializing-shared-state** principle skill.\n\n## Phase B: Fan out\n\nSpawn all N subagents in one message with `run_in_background: true`, each with the task, the path to the shared grounding, its own output path, and instructions to produce the artifact and a short rationale naming the alternatives it considered and what it rejected.\n\nIf a candidate produces no output, proceed with N-1 and note the dropout.\n\n## Phase C: Cross-judge\n\nAfter all Phase B candidates complete, choose one model from the `arena cross-judge pool` line in `~\u002F.cursor\u002Frules\u002Fpstack-models.mdc`. If the rule or that line is missing, choose from `claude-opus-5-5-xhigh` and `grok-4.7-xhigh-fast`. Prefer a different model family from the parent's. Spawn one readonly judge subagent on that model. It sees the rubric and the candidates by path label, scores each criterion, and recommends a base with rationale. It runs in parallel with your reading in Phase D. Don't spawn it while candidates are still writing.\n\n## Phase D: Pick a base\n\nRead every candidate end to end before picking. Score each against the rubric criterion by criterion, not on holistic feel, and compare with the cross-judge. Agreement on the base confirms the pick. Disagreement means one of you is biased or the rubric was ambiguous. Read both rationales before deciding.\n\nPick the base a future maintainer can extend most easily without breaking invariants. When two feel tied, prefer the cleaner boundary or smaller API, per the Laziness Protocol.\n\n## Phase E: Graft\n\nWalk each losing candidate once more for what is worth porting into the base, usually one or two things per candidate, not most of it. Fold each graft in by hand, per the **redesign-from-first-principles** principle skill, so the result stays coherent under one mental model. Don't paste mechanically.\n\nIf the candidates converge on one shape, that is strong agreement. Note it and ship the consensus shape. No graft is needed. If they wildly diverge, Phase A was under-specified. Reframe and re-run rather than averaging the divergence.\n\n## Phase F: Verify\n\nVerify the synthesized artifact like any other output, per the **prove-it-works** principle skill. If verification finds a problem the arena missed, either Phase A was wrong (re-frame and re-run) or a candidate caught it and you missed the graft (go back to Phase E). Don't paper over it.\n\n## Outputs\n\nOne synthesized artifact, with a short synthesis note alongside naming the base and why, the cross-judge's verdict, each graft with its source candidate, what was rejected and why, any convergence or dropouts, and the verification result.\n",{"name":5,"description":7,"disable-model-invocation":28},true,"main","4e0a12b5048eac78a3ace4feee657873cdd530ef","evals\u002Farena\u002Fprechange",7,"https:\u002F\u002Fgithub.com\u002Fmintuz\u002Fskills","https:\u002F\u002Fgithub.com\u002Fmintuz","http:\u002F\u002Fwww.mintuz.com","Working at @monzo, Previously worked at Moonpig, @booking and @bbc","2026-11-11 15:50:19",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":28},[40,43,46],{"tool":41,"command":42},"npx","npx skills add mintuz\u002Fskills --skill arena",{"tool":44,"command":45},"bunx","bunx skills add mintuz\u002Fskills --skill arena",{"tool":47,"command":48},"pnpm","pnpm dlx skills add mintuz\u002Fskills --skill arena","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmintuz\u002Fskills\u002Fblob\u002Fmain\u002Fevals\u002Farena\u002Fprechange\u002FSKILL.md",[],[52,75,98,111,132,149],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":66,"publishedAt":23},"01M6C4PDGB6ZZWBS35N3DF7PZZ","xstate","WHEN React state changes in response to an external answer — async submit, in-flight or loading flags, retries, cancellation, polling, optimistic updates, stale responses — or to an interaction with an interruptible middle, such as a drag or a gesture; or WHEN building, reviewing, testing, or visualising XState 5 actors and @xstate\u002Freact integrations; NOT for a value one event sets completely, such as a text draft, a focus flag, or a plain open and closed toggle; models typed lifecycles and renders legal Mermaid stateDiagram-v2 charts.","https:\u002F\u002Fgithub.com\u002Fmintuz\u002Fskills\u002Fblob\u002Fmain\u002Fsrc\u002Fweb\u002Fskills\u002Fxstate\u002FSKILL.md",[58,63],{"categoryNo":59,"categoryName":60,"taxonomyType":61,"taxonomyTypeDesc":62},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":64,"categoryName":65,"taxonomyType":61,"taxonomyTypeDesc":62},"01JBSEEDCAT000000000000009","前端开发",[54,67,68,69,70,71,72,73,74],"integrations","react","text","open","Charts","state","mermaid","testing",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":89,"publishedAt":23},"01M6C4PB6VVC2X19B63B7YNH0T","web-design","WHEN refining UI layout, typography, color, or polish; NOT code implementation; provides concise principles for intentional, legible design.","https:\u002F\u002Fgithub.com\u002Fmintuz\u002Fskills\u002Fblob\u002Fmain\u002Fsrc\u002Fweb\u002Fskills\u002Fweb-design\u002FSKILL.md",[81,84],{"categoryNo":82,"categoryName":83,"taxonomyType":61,"taxonomyTypeDesc":62},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[90,91,92,93,94,95,96,97],"design","web","web design","code","code implementation","ui","polish","typography",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":105,"publishedAt":23},"01M6C4P8D92GJDA49V7X1CZXEV","tailwind","WHEN building design systems or component libraries with Tailwind CSS; covers design tokens, CVA patterns and dark mode.","https:\u002F\u002Fgithub.com\u002Fmintuz\u002Fskills\u002Fblob\u002Fmain\u002Fsrc\u002Fweb\u002Fskills\u002Ftailwind\u002FSKILL.md",[104],{"categoryNo":82,"categoryName":83,"taxonomyType":61,"taxonomyTypeDesc":62},[106,90,107,108,109,110],"Tailwind","css","component","libraries","design systems",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":120,"publishedAt":23},"01M6C4P5VWQ69Q32DA0634GDJY","refactoring","WHEN you need a plan to refactor, restructure, or clean up working code and the test result is known, either green or a recorded failing set; NOT for new feature delivery or any behavior change; reversible-baseline safety with prioritized improvements.","https:\u002F\u002Fgithub.com\u002Fmintuz\u002Fskills\u002Fblob\u002Fmain\u002Fsrc\u002Fweb\u002Fskills\u002Frefactoring\u002FSKILL.md",[117],{"categoryNo":118,"categoryName":119,"taxonomyType":61,"taxonomyTypeDesc":62},"01JBSEEDCAT000000000000007","代码审查",[113,121,122,123,124,125,126,127,128,129,130,93,131],"baseline","SET","plan","behavior","new feature","up","Safety","test","change","feature delivery","refactor",{"skillNo":133,"name":68,"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":139,"publishedAt":23},"01M6C4P345APEFEX00J8T7QMXQ","WHEN building or changing React components, pages, hooks, effects, or apps, including edits to existing components; NOT for test code (react-testing) or styling (css, tailwind); enforces scalable architecture, state management, API layer, performance patterns.","https:\u002F\u002Fgithub.com\u002Fmintuz\u002Fskills\u002Fblob\u002Fmain\u002Fsrc\u002Fweb\u002Fskills\u002Freact\u002FSKILL.md",[137,138],{"categoryNo":59,"categoryName":60,"taxonomyType":61,"taxonomyTypeDesc":62},{"categoryNo":64,"categoryName":65,"taxonomyType":61,"taxonomyTypeDesc":62},[68,140,74,107,141,128,142,143,144,93,72,145,106,146,147,148],"react components","performance","components","architecture","state management","api","management","hooks","styling",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":157,"publishedAt":23},"01M6C4P0DK385QBG3B3S86TQV2","react-testing","WHEN testing React components\u002Fhooks\u002Fcontext with React Testing Library; NOT e2e; covers renderHook, providers, forms, and anti-patterns.","https:\u002F\u002Fgithub.com\u002Fmintuz\u002Fskills\u002Fblob\u002Fmain\u002Fsrc\u002Fweb\u002Fskills\u002Freact-testing\u002FSKILL.md",[155,156],{"categoryNo":59,"categoryName":60,"taxonomyType":61,"taxonomyTypeDesc":62},{"categoryNo":64,"categoryName":65,"taxonomyType":61,"taxonomyTypeDesc":62},[74,158,68,142,140,159,160,161,162,163,164,147],"react testing","testing library","library","Providers","e2e","context","anti-patterns"]