[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EV63WAFME8RHD1BGYMZHCZ":3,"skill-same:01M7EV63WAFME8RHD1BGYMZHCZ":46},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":45},"01M7EV63WAFME8RHD1BGYMZHCZ","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.","shreshthkapai\u002Fagent-workflows","shreshthkapai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F73650860?v=4","01M7EV5VN4GMWQ8R39WQ7KYFZQ","Shreshth","01M7EV5VNTDGPW78K42W4TYBAJ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fshreshthkapai\u002Fagent-workflows\u002Fblob\u002Fmain\u002Fskills\u002Farena\u002FSKILL.md",[],[],"2026-11-15 14:19:17",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` role in `~\u002F.config\u002Fagent-workflows\u002Fmodels.toml`, resolved with `aw-run --resolve arena_runners`, one runner per entry. An `inherit` entry in this role or the cross-judge role means the parent model. Families are providers, `claude` and `codex`. If the spawn or `aw-run` rejects a seat's model or its provider is unavailable, run that seat on its model's `fallback` and say so. 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. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the **workflow** skill.\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, in the background, per the Subagents section of the **workflow** 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, resolved with `aw-run --resolve arena_cross_judge_pool`. Prefer an entry whose provider differs from the current CLI's. Spawn one read-only judge subagent on that model (`aw-run arena_cross_judge_pool --index \u003Cn> --read-only` when it runs on the other provider). 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 `~\u002F.config\u002Fagent-workflows\u002Fmodels.toml`, resolved with `aw-run --resolve arena_runners`, one runner per entry. An `inherit` entry in this role or the cross-judge role means the parent model. Families are providers, `claude` and `codex`. If the spawn or `aw-run` rejects a seat's model or its provider is unavailable, run that seat on its model's `fallback` and say so. 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. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the **workflow** skill.\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, in the background, per the Subagents section of the **workflow** 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, resolved with `aw-run --resolve arena_cross_judge_pool`. Prefer an entry whose provider differs from the current CLI's. Spawn one read-only judge subagent on that model (`aw-run arena_cross_judge_pool --index \u003Cn> --read-only` when it runs on the other provider). 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":24},true,"main","cafd398384400c1a0ce1da059a134394f28a690e","skills\u002Farena","https:\u002F\u002Fgithub.com\u002Fshreshthkapai\u002Fagent-workflows","https:\u002F\u002Fgithub.com\u002Fshreshthkapai","https:\u002F\u002Fshreshth-personal-website.vercel.app\u002F","Lost....in neural networks","2026-10-30 08:24:11",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":24},[35,38,41],{"tool":36,"command":37},"npx","npx skills add shreshthkapai\u002Fagent-workflows --skill arena",{"tool":39,"command":40},"bunx","bunx skills add shreshthkapai\u002Fagent-workflows --skill arena",{"tool":42,"command":43},"pnpm","pnpm dlx skills add shreshthkapai\u002Fagent-workflows --skill arena","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshreshthkapai\u002Fagent-workflows\u002Fblob\u002Fmain\u002Fskills\u002Farena\u002FSKILL.md",[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7EVBMVS4ZXTSPK19XNMYNT5","workflow","Concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work, with each task routed to a playbook. Use for \u002Fworkflow, or for requests to work in this style. `aw skills always workflow` loads it into every session.","https:\u002F\u002Fgithub.com\u002Fshreshthkapai\u002Fagent-workflows\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7EVBEEEVNYKRCGBH6V5SSFA","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fshreshthkapai\u002Fagent-workflows\u002Fblob\u002Fmain\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"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},"01M7EVBBK5G5QKHXWVYHTRKJ0B","unslop","Cut AI tells from any writing.","https:\u002F\u002Fgithub.com\u002Fshreshthkapai\u002Fagent-workflows\u002Fblob\u002Fmain\u002Fskills\u002Funslop\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},"01M7EVB9ED5F0RVKN70D2ZKV9W","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Fshreshthkapai\u002Fagent-workflows\u002Fblob\u002Fmain\u002Fskills\u002Ftypescript-best-practices\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":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7EVB568STK9X05C00C83KBD","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for \u002Ftechnical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002Fshreshthkapai\u002Fagent-workflows\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-writing\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7EVB0H4V10C6GQHXX4599Y2","teach","Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.","https:\u002F\u002Fgithub.com\u002Fshreshthkapai\u002Fagent-workflows\u002Fblob\u002Fmain\u002Fskills\u002Fteach\u002FSKILL.md",[],[]]