[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NJ2CYY8JAMNRF6EHDFHQ0P":3,"skill-same:01M6NJ2CYY8JAMNRF6EHDFHQ0P":75},{"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":28,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6NJ2CYY8JAMNRF6EHDFHQ0P","arena",null,"Design bakeoff: sub-agents build one artifact several ways, a rubric picks the base, the best parts of the rest are grafted on. Use when the right design is unclear.","tinhtute\u002Fmonoharness","tinhtute","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F51282340?v=4","01M6NHYENXPR3K033S3YDA62FW","TINHTUTE","01M6NHYETDANVFY82EPKRC4JFS",5,"MIT","https:\u002F\u002Fgithub.com\u002Ftinhtute\u002Fmonoharness\u002Fblob\u002Fmaster\u002Fskills\u002Freason\u002Farena\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[5,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"design is","for","runners","design","use","code","REST","artifact","build","models","rubric","parts","base","when","2026-11-10 10:12:30",false,"---\nname: arena\nversion: \"1.1.0\"\ndescription: \"Design bakeoff: sub-agents build one artifact several ways, a rubric picks the base, the best parts of the rest are grafted on. Use when the right design is unclear.\"\nargument-hint: \"[artifact to design] [runners and models]\"\ncompatibility: Designed for Claude Code\n---\n\n# Arena: Build It Several Ways, Keep the Best\n\n## Outcome Contract\n\n- Outcome: one artifact built from the strongest candidate, improved with the best parts of the others.\n- Done when: every candidate is scored on the same rubric, the base and each graft are named with the rubric point they win, and the merged artifact passes its check.\n- Evidence: each candidate's output path, the score table, the judge's pick, and the final check output.\n- Writes: candidates go to scratch paths outside the repo; only the merged artifact lands in the repo.\n\n## Process\n\n1. **Frame.** Name the artifact, a 3–6 point rubric, the runners (2–4) and each runner's model, and one output location per runner. Mixing model families widens the spread.\n2. **Fan out.** Spawn every runner in one message, in the background, on an identical brief built per `work` [work-swarm.md](..\u002F..\u002Fstages\u002Fwork\u002Freferences\u002Fwork-swarm.md); only the output path differs.\n3. **Cross-judge.** Score each candidate yourself, then ask a judge for its pick and reasons; a judge on a different model family from the runners is recommended.\n4. **Pick a base.** The highest rubric total wins; on a tie, the simpler candidate.\n5. **Graft by hand.** Copy the best part of each loser into the base, one rubric point at a time; never merge whole candidates. Candidates that converge on one shape are strong agreement: note it and ship that shape with no graft.\n6. **Verify.** Run the artifact's check on the merged result. A problem the check finds that every candidate missed means the frame was wrong: reframe and re-run. One a candidate caught means a missed graft: return to step 5. Never patch over it.\n\nCandidates that diverge wildly mean the brief was under-specified: reframe the rubric or the brief and re-run; never average them.\n\n## Output\n\n```\nBase:     [runner, model, total score]\nGrafts:   [from runner → part, rubric point it wins]\nScores:   [table: runner × rubric point]\nJudge:    [pick, model, one-line reason]\nCheck:    [command and result]\n```\n\nDefer to: `work` (fan-out core and integration), `think` (when the question is a decision, not an artifact), `check` (gating the merged result).\n","# Arena: Build It Several Ways, Keep the Best\n\n## Outcome Contract\n\n- Outcome: one artifact built from the strongest candidate, improved with the best parts of the others.\n- Done when: every candidate is scored on the same rubric, the base and each graft are named with the rubric point they win, and the merged artifact passes its check.\n- Evidence: each candidate's output path, the score table, the judge's pick, and the final check output.\n- Writes: candidates go to scratch paths outside the repo; only the merged artifact lands in the repo.\n\n## Process\n\n1. **Frame.** Name the artifact, a 3–6 point rubric, the runners (2–4) and each runner's model, and one output location per runner. Mixing model families widens the spread.\n2. **Fan out.** Spawn every runner in one message, in the background, on an identical brief built per `work` [work-swarm.md](..\u002F..\u002Fstages\u002Fwork\u002Freferences\u002Fwork-swarm.md); only the output path differs.\n3. **Cross-judge.** Score each candidate yourself, then ask a judge for its pick and reasons; a judge on a different model family from the runners is recommended.\n4. **Pick a base.** The highest rubric total wins; on a tie, the simpler candidate.\n5. **Graft by hand.** Copy the best part of each loser into the base, one rubric point at a time; never merge whole candidates. Candidates that converge on one shape are strong agreement: note it and ship that shape with no graft.\n6. **Verify.** Run the artifact's check on the merged result. A problem the check finds that every candidate missed means the frame was wrong: reframe and re-run. One a candidate caught means a missed graft: return to step 5. Never patch over it.\n\nCandidates that diverge wildly mean the brief was under-specified: reframe the rubric or the brief and re-run; never average them.\n\n## Output\n\n```\nBase:     [runner, model, total score]\nGrafts:   [from runner → part, rubric point it wins]\nScores:   [table: runner × rubric point]\nJudge:    [pick, model, one-line reason]\nCheck:    [command and result]\n```\n\nDefer to: `work` (fan-out core and integration), `think` (when the question is a decision, not an artifact), `check` (gating the merged result).\n",{"name":5,"version":48,"description":7,"argument-hint":49,"compatibility":50},"1.1.0","[artifact to design] [runners and models]","Designed for Claude Code","master","aaac9fcb3d40fa124478cd66a58e99ce02e7cf6d","skills\u002Freason\u002Farena",0,"https:\u002F\u002Fgithub.com\u002Ftinhtute\u002Fmonoharness","https:\u002F\u002Fharness.tinhtute.me","https:\u002F\u002Fgithub.com\u002Ftinhtute","tinhtute.me","𝙻 𝙾 𝚂 𝙴 𝚁 ✨🚀","2026-11-14 12:10:57",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add tinhtute\u002Fmonoharness --skill arena",{"tool":67,"command":68},"bunx","bunx skills add tinhtute\u002Fmonoharness --skill arena",{"tool":70,"command":71},"pnpm","pnpm dlx skills add tinhtute\u002Fmonoharness --skill arena","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftinhtute\u002Fmonoharness\u002Fblob\u002Fmaster\u002Fskills\u002Freason\u002Farena\u002FSKILL.md",true,[],[76,84,111,137,165,187],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":83},"01M7667MMEAHTJPMWFJPD6ZMVK","poteto","Entry router: match a task to one of seventeen playbooks (feature, bug-fix, refactoring, perf, research, ship, ...) and run its skill steps as a todo list. Use when the route is unclear.","https:\u002F\u002Fgithub.com\u002Ftinhtute\u002Fmonoharness\u002Fblob\u002Fmaster\u002Fskills\u002Fpoteto\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"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":93,"publishedAt":43},"01M6NJ7YY1Q5V2JYZ401YHKJVK","read","Search the web and fetch URLs or PDFs as clean Markdown via a privacy-first cascade (local, gh, TinyFish\u002FFirecrawl\u002FExa, opt-in proxy). Use to read, cite or save a URL. Not for repo files.","https:\u002F\u002Fgithub.com\u002Ftinhtute\u002Fmonoharness\u002Fblob\u002Fmaster\u002Fskills\u002Ftools\u002Fread\u002FSKILL.md",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",[86,94,95,96,97,30,98,99,100,101,102,103,104,33,105,106,107,34,108,109,110],"as","fetch","PDF","proxy","repo","search","local","clean","tinyfish","gh","files","URL","exa","query","first","web","opt",{"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":117,"publishedAt":43},"01M6WWM7Y4Q4C1NN9DRC33J6F8","mono-write","Polish a research or learn draft (EN\u002FVI) so it reads naturally, and write CHANGELOG entries and release notes from a commit list. Not for UI copy, marketing or tone changes.","https:\u002F\u002Fgithub.com\u002Ftinhtute\u002Fmonoharness\u002Fblob\u002Fmaster\u002Fskills\u002Ftools\u002Fmono-write\u002FSKILL.md",[],[118,119,120,30,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136],"mono write","mono","write","en","entries","release notes","learn","commit","write changelog","tone","draft","notes","changelog","research","changes","release","polish","list","marketing",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":149,"publishedAt":43},"01M6NJ76P0AMQBPZSZQB38P0TT","librarian","GitHub code research via gh CLI, no cloning. Use to investigate external repos, find where a symbol is defined, or gather cited evidence and usage examples from GitHub.","https:\u002F\u002Fgithub.com\u002Ftinhtute\u002Fmonoharness\u002Fblob\u002Fmaster\u002Fskills\u002Ftools\u002Flibrarian\u002FSKILL.md",[143,146],{"categoryNo":144,"categoryName":145,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":147,"categoryName":148,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师",[139,150,151,30,98,99,152,153,103,33,107,154,34,155,156,157,131,158,159,160,161,86,162,163,164],"usage","evidence","gh-cli","github code","Bash","examples","investigate","haiku","cli","code research","github","cloning","repos","gh cli","gather",{"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":43},"01M6NJ72XJYEV4VDYBZVT69E5T","git","Git operations with conventional commits. Use for staging, committing, pushing, PRs, merges. Auto-splits commits by type\u002Fscope. Security scans for secrets.","https:\u002F\u002Fgithub.com\u002Ftinhtute\u002Fmonoharness\u002Fblob\u002Fmaster\u002Fskills\u002Ftools\u002Fgit\u002FSKILL.md",[],[167,172,173,174,30,175,176,177,178,33,179,180,34,181,182,157,183,184,185,186],"pr","scope","commits","cm","git operations","prs","auto","conventional commits","splits","type","with","cp","operations","merge","secrets",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":193,"publishedAt":43},"01M6NJ6BBWY0ZTGKE4TNA6W3KF","work","Execution orchestrator after `brainstorm` (and `to-plan` for high-risk). Runs phases wave-by-wave from locked artifacts, verifies each task, and hands off to `check`, `git`, or `handoff`.","https:\u002F\u002Fgithub.com\u002Ftinhtute\u002Fmonoharness\u002Fblob\u002Fmaster\u002Fskills\u002Fstages\u002Fwork\u002FSKILL.md",[],[189,194,30,195,196,197,178,198,34,199,200,129,201,202,203,204,205,167,206,207,208],"risk","mode","brainstorm","execution","artifacts","task","check","plan","simple","high","orchestrator","name","full","handoff","phase"]