[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72Y1FVWMPAM9C5JKDME0AC1":3,"skill-same:01M72Y1FVWMPAM9C5JKDME0AC1":82},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":45},"01M72Y1FVWMPAM9C5JKDME0AC1","arena",null,"Put several agents on one task. The default arena mode runs parallel candidates and grafts the best parts into one result, and benchmark ranks models or skills with a blind judge. Runs only when the user types \u002Farena.","h00mankind\u002Fworkflow","h00mankind","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F105175148?v=4","01M72XXA2JP2H3BBK5GP9AP4P6","h00man","01M72XXA3824K52XFYWJDBFJ06",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fh00man\u002Fskills\u002Farena\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: arena\ndescription: Put several agents on one task. The default arena mode runs parallel candidates and grafts the best parts into one result, and benchmark ranks models or skills with a blind judge. Runs only when the user types \u002Farena.\ndisable-model-invocation: true\nmetadata:\n  opencode\u002Fautoinvoke: false\n---\n\n# arena\n\nUse several agents where one attempt or one opinion is not enough.\n\n## Pick the mode\n\nThe first word of the argument picks the mode. The rest of the argument is the task.\n\n- **arena** (the default): several candidates make the same artifact in parallel. You pick a base and graft the best parts of the others into it. Use it to make one thing when a single attempt could commit to the wrong design.\n- **benchmark**: contenders do the same task, a blind judge scores them, and an HTML report ranks them. Use it to compare models or skills. It does not make a deliverable.\n\nWith no mode word, choose from the request. A comparison of models or skills runs benchmark. Anything else runs arena. Name the mode in your first line.\n\nA review or a second opinion on existing work is not an arena task. Tell the user to type `\u002Fcouncil`.\n\n## Models and harness\n\nThese rules apply in every mode.\n\n- Read role lines from `agent-models.md` in `${CLAUDE_CONFIG_DIR:-$HOME\u002F.claude}\u002F` when that file exists. Without it, use the defaults in the mode's file.\n- Route every seat with the Routing rules in the Models section of `..\u002Fbuild\u002FSKILL.md`: the `|` fallback choices, the route for each harness, and the effort field. In T3 Code, load `delegate_task` and `orchestrator_capabilities` first if they are deferred tools.\n- Set each agent's reasoning effort for its job. Go higher for hard design or review work. Go lower for work that is mostly generation.\n\n## arena mode\n\nFollow `references\u002Fpstack-arena.md`. It names pstack files and skills. h00man is standalone, so use these in their place:\n\n- Its platform-mapping links and the **poteto-mode** Subagents section: the rules under Models and harness above.\n- **separate-before-serializing-shared-state**: `references\u002Fpstack-principle-separate-before-serializing-shared-state.md`.\n- **redesign-from-first-principles**: `references\u002Fpstack-principle-redesign-from-first-principles.md`.\n- **prove-it-works**: `references\u002Fpstack-principle-prove-it-works.md`. The **show-me-your-work** skill it names: `..\u002Fbuild\u002Freferences\u002Fshow-me-your-work\u002FSKILL.ref.md` when `build` is installed. Either way, keep the proof as a local file next to the artifact.\n- The Laziness Protocol: `references\u002Fpstack-principle-laziness-protocol.md`.\n- `\u002Fsetup-pstack` in its Models section: not in the stack. Edit the role lines in `agent-models.md` by hand.\n\nRead each principle file at the phase that names it.\n\n## benchmark mode\n\nFollow `modes\u002Fbenchmark.md`. It is the user's own method. The words after `benchmark` are the argument its setup step parses, for example `\u002Farena benchmark skill deep`.\n\n## Sources\n\n- h00man, by h00man23 (https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow, Apache-2.0): the earlier `h00man:benchmark` skill, now `modes\u002Fbenchmark.md`. It gives the benchmark mode: calibrated tasks, hermetic runs, the blind judge, and the report.\n- pstack, by Lauren Tan (https:\u002F\u002Fgithub.com\u002Fcursor\u002Fplugins\u002Ftree\u002Fmain\u002Fpstack, ported at https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fpstack, MIT): the `arena` skill, copied to `references\u002Fpstack-arena.md`, for the arena mode. The principle skills it names, copied to `references\u002Fpstack-principle-*.md`.\n","# arena\n\nUse several agents where one attempt or one opinion is not enough.\n\n## Pick the mode\n\nThe first word of the argument picks the mode. The rest of the argument is the task.\n\n- **arena** (the default): several candidates make the same artifact in parallel. You pick a base and graft the best parts of the others into it. Use it to make one thing when a single attempt could commit to the wrong design.\n- **benchmark**: contenders do the same task, a blind judge scores them, and an HTML report ranks them. Use it to compare models or skills. It does not make a deliverable.\n\nWith no mode word, choose from the request. A comparison of models or skills runs benchmark. Anything else runs arena. Name the mode in your first line.\n\nA review or a second opinion on existing work is not an arena task. Tell the user to type `\u002Fcouncil`.\n\n## Models and harness\n\nThese rules apply in every mode.\n\n- Read role lines from `agent-models.md` in `${CLAUDE_CONFIG_DIR:-$HOME\u002F.claude}\u002F` when that file exists. Without it, use the defaults in the mode's file.\n- Route every seat with the Routing rules in the Models section of `..\u002Fbuild\u002FSKILL.md`: the `|` fallback choices, the route for each harness, and the effort field. In T3 Code, load `delegate_task` and `orchestrator_capabilities` first if they are deferred tools.\n- Set each agent's reasoning effort for its job. Go higher for hard design or review work. Go lower for work that is mostly generation.\n\n## arena mode\n\nFollow `references\u002Fpstack-arena.md`. It names pstack files and skills. h00man is standalone, so use these in their place:\n\n- Its platform-mapping links and the **poteto-mode** Subagents section: the rules under Models and harness above.\n- **separate-before-serializing-shared-state**: `references\u002Fpstack-principle-separate-before-serializing-shared-state.md`.\n- **redesign-from-first-principles**: `references\u002Fpstack-principle-redesign-from-first-principles.md`.\n- **prove-it-works**: `references\u002Fpstack-principle-prove-it-works.md`. The **show-me-your-work** skill it names: `..\u002Fbuild\u002Freferences\u002Fshow-me-your-work\u002FSKILL.ref.md` when `build` is installed. Either way, keep the proof as a local file next to the artifact.\n- The Laziness Protocol: `references\u002Fpstack-principle-laziness-protocol.md`.\n- `\u002Fsetup-pstack` in its Models section: not in the stack. Edit the role lines in `agent-models.md` by hand.\n\nRead each principle file at the phase that names it.\n\n## benchmark mode\n\nFollow `modes\u002Fbenchmark.md`. It is the user's own method. The words after `benchmark` are the argument its setup step parses, for example `\u002Farena benchmark skill deep`.\n\n## Sources\n\n- h00man, by h00man23 (https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow, Apache-2.0): the earlier `h00man:benchmark` skill, now `modes\u002Fbenchmark.md`. It gives the benchmark mode: calibrated tasks, hermetic runs, the blind judge, and the report.\n- pstack, by Lauren Tan (https:\u002F\u002Fgithub.com\u002Fcursor\u002Fplugins\u002Ftree\u002Fmain\u002Fpstack, ported at https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fpstack, MIT): the `arena` skill, copied to `references\u002Fpstack-arena.md`, for the arena mode. The principle skills it names, copied to `references\u002Fpstack-principle-*.md`.\n",{"name":5,"metadata":24,"description":7,"disable-model-invocation":25},{"opencode\u002Fautoinvoke":20},true,"main","642d17451b565c0f4407fb4aeffcd19cbfacc8f4","plugins\u002Fh00man\u002Fskills\u002Farena","https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow","https:\u002F\u002Fgithub.com\u002Fh00mankind","an ordinary mortal h00man","2026-11-13 01:29:34",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add h00mankind\u002Fworkflow --skill arena",{"tool":39,"command":40},"bunx","bunx skills add h00mankind\u002Fworkflow --skill arena",{"tool":42,"command":43},"pnpm","pnpm dlx skills add h00mankind\u002Fworkflow --skill arena","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fh00man\u002Fskills\u002Farena\u002FSKILL.md",[46,52,58,62,66,70,74,78],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",96,"https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fh00man\u002Fskills\u002Farena\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"includes.toml","OTHER","其他",724,"https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fh00man\u002Fskills\u002Farena\u002Fincludes.toml",{"path":59,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":60,"sourceHtmlUrl":61},"modes\u002Fbenchmark.md",7200,"https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fh00man\u002Fskills\u002Farena\u002Fmodes\u002Fbenchmark.md",{"path":63,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fpstack-arena.md",6973,"https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fh00man\u002Fskills\u002Farena\u002Freferences\u002Fpstack-arena.md",{"path":67,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fpstack-principle-laziness-protocol.md",543,"https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fh00man\u002Fskills\u002Farena\u002Freferences\u002Fpstack-principle-laziness-protocol.md",{"path":71,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fpstack-principle-prove-it-works.md",2435,"https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fh00man\u002Fskills\u002Farena\u002Freferences\u002Fpstack-principle-prove-it-works.md",{"path":75,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fpstack-principle-redesign-from-first-principles.md",749,"https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fh00man\u002Fskills\u002Farena\u002Freferences\u002Fpstack-principle-redesign-from-first-principles.md",{"path":79,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fpstack-principle-separate-before-serializing-shared-state.md",1556,"https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fh00man\u002Fskills\u002Farena\u002Freferences\u002Fpstack-principle-separate-before-serializing-shared-state.md",[83,91,98,106,113,120],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":90},"01M78R7TT830V3BYFNDX1EHF0V","teach","Teach the user a subject, in explain mode (one plain account of code, a change, or a concept, in chat) or course mode (a learning workspace with a mission, lessons, and records over many sessions). Runs only when the user types \u002Fteach.","https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fh00man\u002Fskills\u002Fteach\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"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":90},"01M78R7RSGFF5TFE0JBGY3WKEJ","council","Get a review or a second opinion on existing work from several strong models of different providers. Runs only when the user types \u002Fcouncil.","https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fh00man\u002Fskills\u002Fcouncil\u002FSKILL.md",[],[],{"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":104,"publishedAt":105},"01M74AAVCZZREXPZEE5HRN5WF5","variant","Builds multiple variants of a component you're working on and helps you iterate and pick one.","https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fjakub\u002Fskills\u002Fvariant\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":105},"01M74AAR3M07M86YX2CXPD79EX","teardown","Creates technical illustrations of physical objects and of how things work, such as display pixels or interface layers, with coherent views, fine linework and part fills.","https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fjakub\u002Fskills\u002Fteardown\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":105},"01M74AAMKJ8MKP9M99K37A82ZM","state-machine","Renders every state of a component you choose on a throwaway page, with mock data and a switcher, so you can work on each state.","https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fjakub\u002Fskills\u002Fstate-machine\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":105},"01M74AAHF2A498F7F2E74696KF","interface-review","Reviews a branch, pull request or uncommitted change for the interface problems it introduced or regressed, across accessibility, layout, writing, typography, color and UI.","https:\u002F\u002Fgithub.com\u002Fh00mankind\u002Fworkflow\u002Fblob\u002Fmain\u002Fplugins\u002Fjakub\u002Fskills\u002Finterface-review\u002FSKILL.md",[],[]]