[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71P0QR0E3WH6DHAHM6353VP":3,"skill-same:01M71P0QR0E3WH6DHAHM6353VP":66},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M71P0QR0E3WH6DHAHM6353VP","arena",null,"Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.","drsh4dow\u002Fpi-setup","drsh4dow","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F45247070?v=4","01M71P068NASGHSWS11VWW416N","Daniel Moretti","01M71P0698BH81N65NP04X9NVN",10,"MIT","https:\u002F\u002Fgithub.com\u002Fdrsh4dow\u002Fpi-setup\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Farena\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"lock","it","Wrong","base","parts","shape","at","spawn","artifact","candidates","task","one","when","false","use","graft","pick","for","parallel","2026-11-10 10:56:23",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 '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: false\nuser-invokable: false\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` role in the subagents skill. 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 per the subagents skill, 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` role in the subagents skill. Prefer a different model family from the parent's. Spawn one judge subagent on that model, with a write scope that changes nothing. 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` role in the subagents skill. 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 per the subagents skill, 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` role in the subagents skill. Prefer a different model family from the parent's. Spawn one judge subagent on that model, with a write scope that changes nothing. 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,"user-invokable":39,"disable-model-invocation":39},"main","f7936596c1ba2e1472dadccc3f111b9d517fa96c","agent\u002Fskills\u002Farena",2,"https:\u002F\u002Fgithub.com\u002Fdrsh4dow\u002Fpi-setup","https:\u002F\u002Fgithub.com\u002Fdrsh4dow","https:\u002F\u002Fdanielmoretti.com\u002F","Toss A Coin To Your Witcher :pirate_flag: ","2026-11-03 22:13:53",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add drsh4dow\u002Fpi-setup --skill arena",{"tool":58,"command":59},"bunx","bunx skills add drsh4dow\u002Fpi-setup --skill arena",{"tool":61,"command":62},"pnpm","pnpm dlx skills add drsh4dow\u002Fpi-setup --skill arena","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdrsh4dow\u002Fpi-setup\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Farena\u002FSKILL.md",true,[],[67,87,117,134,154,165],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":38},"01M71P4GPJMBK21BTZBKY9T8EE","changelog","Write the changelog entry for a pull request. Use when a PR changes behavior that users, operators, or integrators can notice.","https:\u002F\u002Fgithub.com\u002Fdrsh4dow\u002Fpi-setup\u002Fblob\u002Fmain\u002Fevals\u002Fharness-lessons\u002Ffixtures\u002Fchangelog-skill\u002FSKILL.md",[],[69,74,75,76,77,78,79,80,36,81,82,83,84,33,31,85,86],"users","pull","notice","changes","operators","pr","pull request","request","behavior","entry","write","can","changelog entry",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":103,"publishedAt":38},"01M71P4E9AZM56JBY227P2G1SC","writing-good-tickets","Write, file, or update an issue or ticket that an agent or a developer can take to one PR. Use when filing a bug or feature, updating an issue, or breaking a plan into tickets.","https:\u002F\u002Fgithub.com\u002Fdrsh4dow\u002Fpi-setup\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fwriting-good-tickets\u002FSKILL.md",[93,98],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[104,105,106,107,79,108,109,110,33,32,31,111,30,85,112,113,84,114,115,116],"good","writing","tickets","writing good tickets","feature","filing","ticket","file","plan","update","bug","take","issue",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":125,"publishedAt":38},"01M71P4C0B0DXTRRSG9RA6Y687","writing-good-prs","Write or update a pull request title and body that a reviewer can trust and own. Use when opening a PR or editing its description.","https:\u002F\u002Fgithub.com\u002Fdrsh4dow\u002Fpi-setup\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fwriting-good-prs\u002FSKILL.md",[123,124],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[104,126,105,127,75,128,79,129,33,32,31,85,130,131,80,81,113,84,132,133],"prs","writing good prs","trust","editing","reviewer","title","opening a pr","body",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":142,"publishedAt":38},"01M71P49D1AG2MR6AYNPMMT34Z","writing-good-commits","Write or reword a git commit message and size the commit it describes. Use when committing, or when reshaping commits during a rebase.","https:\u002F\u002Fgithub.com\u002Fdrsh4dow\u002Fpi-setup\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fwriting-good-commits\u002FSKILL.md",[140,141],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[143,104,105,144,145,146,84,147,148,149,33,32,150,151,31,152,153,20],"commits","writing good commits","message","size","git commit message","git","git commit","rebase","commit message","committing","commit",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":162,"publishedAt":38},"01M71P480BDE55JMPVVEBCFS7P","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fdrsh4dow\u002Fpi-setup\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[160,161],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[163,36,105,129,33,32,164,31],"writing for agents","documents",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":38},"01M71P45SNCD7DDSA6FRVCPA17","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fdrsh4dow\u002Fpi-setup\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fwizard\u002FSKILL.md",[],[167,172,173,36,174,175,176,177,33,178,32,31,179,30,180,85,181,182,183,184],"running","setting","up","ci","provisioning infrastructure","only","invoke","Bash","interactive","credentials","dashboard","generate","human"]