[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CV8AMD6XJEV7V6V8QFAMR2":3,"skill-same:01M7CV8AMD6XJEV7V6V8QFAMR2":55},{"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":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7CV8AMD6XJEV7V6V8QFAMR2","craft-arena",null,"Parallel design bakeoff: N candidates on one brief, cross-judge, pick a base, graft the best parts. Use when one attempt would lock in the wrong shape.","TudeOrangBiasa\u002Fskills-for-agents","TudeOrangBiasa","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F125188681?v=4","01M7CV804RMMCVN5M0D4ZCQ6D8","TudeStillLearning!","01M7CV805CRFTQY48WZ6JK57YK",1,"MIT","https:\u002F\u002Fgithub.com\u002FTudeOrangBiasa\u002Fskills-for-agents\u002Fblob\u002Fmain\u002Fskills\u002Fmodel-invoked\u002Fcraft-arena\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Parallel design bakeoff: N candidates on one brief, cross-judge, pick a base, graft the best parts. Use when one attempt would lock in the wrong shape.\"\nname: craft-arena\n---\n# Arena\n\nRun N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use when one attempt at a non-trivial artifact would lock in the wrong shape. Companion to `craft-swarm` (coverage and races) and `review-adversary` (adversarial review of one change).\n\nOpen a todo with one entry per phase before launching anything.\n\n## A. Frame\n\nEvery candidate gets the same prompt, so the prompt is the contract: the artifact each produces, and a rubric of 3 to 6 concrete gradeable criteria for this task (the picker's tool; candidates only see the task). Runners follow the repo model map; keep at least two runners, dropping to one only when the map lists one. Use the same model N times when the work is generation-bound rather than judgment-sensitive, more runners when covering multiple design directions. A rejected slug falls back to the closest valid one in the harness error message, else the map's default or your own model; a dropped seat is refilled on a remaining runner's model, else your own model. Either way, say so. Each candidate gets its own output location (a git worktree where possible, otherwise a separate directory) per rule 15.\n\n## B. Fan out\n\nSpawn all N in one round, each with the task, the path to the shared grounding, its own output path, and instructions to produce the artifact plus a short rationale naming the alternatives it considered and rejected. A candidate with no output means proceeding with N-1, dropout noted.\n\n## C. Cross-judge\n\nAfter all candidates complete, one readonly judge (a different model family, from the map's judge entry, never your own model when it is an `auto` or `inherit-parent` entry) sees the rubric and the candidates by path label, scores each rubric criterion per candidate, and recommends a base with rationale. It runs in parallel with your reading in Phase D. Never judge while candidates are still writing. When no other-family model runs, pick the base alone and say Phase C skipped the judge.\n\n## D. Pick a base\n\nRead every candidate end to end before picking, score criterion by criterion against the rubric (not holistic feel), and compare with the cross-judge when Phase C ran one. Agreement confirms the pick; disagreement means bias or an ambiguous rubric, so read both rationales before deciding. Pick the base a future maintainer extends most easily without breaking invariants; ties break toward the cleaner boundary or smaller API (rule 1).\n\n## E. Graft\n\nWalk each loser once more for the one or two things worth porting (not most of it), and fold each in by hand (rule 17) so the result stays coherent under one mental model. Convergence on one shape means shipping the consensus, no graft needed. Wild divergence means Phase A was under-specified: reframe and re-run, never average the divergence.\n\n## F. Verify\n\nVerify the synthesized artifact like any other output (rule 3). A problem the arena missed means Phase A was wrong (re-run) or a graft was missed (back to Phase E); never paper over it.\n\n## Outputs\n\nOne synthesized artifact with a short note: the base and why, the cross-judge verdict (or that Phase C skipped the judge), each graft with its source, what was rejected and why, convergence or dropouts, and the verification result.\n","# Arena\n\nRun N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use when one attempt at a non-trivial artifact would lock in the wrong shape. Companion to `craft-swarm` (coverage and races) and `review-adversary` (adversarial review of one change).\n\nOpen a todo with one entry per phase before launching anything.\n\n## A. Frame\n\nEvery candidate gets the same prompt, so the prompt is the contract: the artifact each produces, and a rubric of 3 to 6 concrete gradeable criteria for this task (the picker's tool; candidates only see the task). Runners follow the repo model map; keep at least two runners, dropping to one only when the map lists one. Use the same model N times when the work is generation-bound rather than judgment-sensitive, more runners when covering multiple design directions. A rejected slug falls back to the closest valid one in the harness error message, else the map's default or your own model; a dropped seat is refilled on a remaining runner's model, else your own model. Either way, say so. Each candidate gets its own output location (a git worktree where possible, otherwise a separate directory) per rule 15.\n\n## B. Fan out\n\nSpawn all N in one round, each with the task, the path to the shared grounding, its own output path, and instructions to produce the artifact plus a short rationale naming the alternatives it considered and rejected. A candidate with no output means proceeding with N-1, dropout noted.\n\n## C. Cross-judge\n\nAfter all candidates complete, one readonly judge (a different model family, from the map's judge entry, never your own model when it is an `auto` or `inherit-parent` entry) sees the rubric and the candidates by path label, scores each rubric criterion per candidate, and recommends a base with rationale. It runs in parallel with your reading in Phase D. Never judge while candidates are still writing. When no other-family model runs, pick the base alone and say Phase C skipped the judge.\n\n## D. Pick a base\n\nRead every candidate end to end before picking, score criterion by criterion against the rubric (not holistic feel), and compare with the cross-judge when Phase C ran one. Agreement confirms the pick; disagreement means bias or an ambiguous rubric, so read both rationales before deciding. Pick the base a future maintainer extends most easily without breaking invariants; ties break toward the cleaner boundary or smaller API (rule 1).\n\n## E. Graft\n\nWalk each loser once more for the one or two things worth porting (not most of it), and fold each in by hand (rule 17) so the result stays coherent under one mental model. Convergence on one shape means shipping the consensus, no graft needed. Wild divergence means Phase A was under-specified: reframe and re-run, never average the divergence.\n\n## F. Verify\n\nVerify the synthesized artifact like any other output (rule 3). A problem the arena missed means Phase A was wrong (re-run) or a graft was missed (back to Phase E); never paper over it.\n\n## Outputs\n\nOne synthesized artifact with a short note: the base and why, the cross-judge verdict (or that Phase C skipped the judge), each graft with its source, what was rejected and why, convergence or dropouts, and the verification result.\n",{"name":5,"description":7},"main","d26d63fb9a1a8091ba1d908b1b35738b60e8be79","skills\u002Fmodel-invoked\u002Fcraft-arena",0,"https:\u002F\u002Fgithub.com\u002FTudeOrangBiasa\u002Fskills-for-agents","https:\u002F\u002Fgithub.com\u002FTudeOrangBiasa","2026-11-05 23:44:38",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add TudeOrangBiasa\u002Fskills-for-agents --skill craft-arena",{"tool":37,"command":38},"bunx","bunx skills add TudeOrangBiasa\u002Fskills-for-agents --skill craft-arena",{"tool":40,"command":41},"pnpm","pnpm dlx skills add TudeOrangBiasa\u002Fskills-for-agents --skill craft-arena","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTudeOrangBiasa\u002Fskills-for-agents\u002Fblob\u002Fmain\u002Fskills\u002Fmodel-invoked\u002Fcraft-arena\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",82,"https:\u002F\u002Fgithub.com\u002FTudeOrangBiasa\u002Fskills-for-agents\u002Fblob\u002Fmain\u002Fskills\u002Fmodel-invoked\u002Fcraft-arena\u002Fagents\u002Fopenai.yaml",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"CREDITS.md",838,"https:\u002F\u002Fgithub.com\u002FTudeOrangBiasa\u002Fskills-for-agents\u002Fblob\u002Fmain\u002Fskills\u002Fmodel-invoked\u002Fcraft-arena\u002FCREDITS.md",[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7CVDKFYKNEY024TK36QAA2R","whips","Route any non-trivial task through one entry: match a playbook, drive HIT skills plus subagents, open a reviewed ready PR with ship-pr-shaped evidence.","https:\u002F\u002Fgithub.com\u002FTudeOrangBiasa\u002Fskills-for-agents\u002Fblob\u002Fmain\u002Fskills\u002Fuser-invoked\u002Fwhips\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7CVDFG46BBHV71Q5JVZ7XZT","verify-upkeep","Periodic upkeep for a project's verification skill: source wave plus live pass per feature, at most one PR of proven corrections. Use to audit the verify skill.","https:\u002F\u002Fgithub.com\u002FTudeOrangBiasa\u002Fskills-for-agents\u002Fblob\u002Fmain\u002Fskills\u002Fuser-invoked\u002Fverify-upkeep\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7CVDB20QNGAPR8T5YXDRNT9","verify-statechart","Check a TLA+ model of a system that moves between states, such as a product flow, a protocol, or a service, and draw it as a Mermaid statechart. The report gives the shortest path to each state that breaks a rule. Use to show a bug as a path through states.","https:\u002F\u002Fgithub.com\u002FTudeOrangBiasa\u002Fskills-for-agents\u002Fblob\u002Fmain\u002Fskills\u002Fuser-invoked\u002Fverify-statechart\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7CVD6Y3W2A12ZDEQBS39QPD","verify-new","Generate a project-local skill that drives the app like a user (launch, doctor, drive, evidence, feature map), proven once. Use when a project has no scripted proof.","https:\u002F\u002Fgithub.com\u002FTudeOrangBiasa\u002Fskills-for-agents\u002Fblob\u002Fmain\u002Fskills\u002Fuser-invoked\u002Fverify-new\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},"01M7CVD2WTQ83ETMQ82GWWZAAV","ship-triage","Move issues and external PRs through a state machine of triage roles, categorise, verify, interview if needed, and write agent-ready briefs.","https:\u002F\u002Fgithub.com\u002FTudeOrangBiasa\u002Fskills-for-agents\u002Fblob\u002Fmain\u002Fskills\u002Fuser-invoked\u002Fship-triage\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7CVCYS0S8S8XW68V819QKZ6","ship-runner","Run ready-for-agent issue queues on any schedule through \u002Fwhips intake, one fresh worktree each, landing per risk tier, with the agent and model you pick at setup.","https:\u002F\u002Fgithub.com\u002FTudeOrangBiasa\u002Fskills-for-agents\u002Fblob\u002Fmain\u002Fskills\u002Fuser-invoked\u002Fship-runner\u002FSKILL.md",[],[]]