[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EZ7MB8R2G68DF086S6C6G7":3,"skill-same:01M7EZ7MB8R2G68DF086S6C6G7":45},{"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":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":44},"01M7EZ7MB8R2G68DF086S6C6G7","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.","SenCha930511\u002Fomp-desktop","SenCha930511","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F69847839?v=4","01M7EZ7DZM6X416N39DB35SDDB","SenChaaa","01M7EZ7E0JQGT4PZ95XA7S77RZ",1,"MIT","https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpstack\u002Farena\u002FSKILL.md",[],[],"2026-11-16 10:05:34",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\nFan out N parallel attempts at the same task. Read every candidate end to end. Pick the strongest as the base. Graft the best ideas from the others into it. Verify the synthesized result.\n\n## Start\n\nOpen a todolist with one entry per phase before launching anything. The arena runs autonomously and the list keeps phases from silently disappearing.\n\n1. Frame\n2. Fan out\n3. Cross-judge\n4. Pick\n5. Graft\n6. Verify\n\n## Phase A: Frame\n\nThe N candidates will receive the same prompt, so the prompt is the contract. Get it right before spawning anything.\n\n1. State the artifact each candidate is producing.\n2. Derive the rubric. State what success looks like for *this* task, then turn it into 3-6 concrete gradeable criteria. Concrete: `Adds a --dry-run flag that skips writes`. Vague: `code is correct`. The rubric is the picker's tool in Phase D; candidates only see the task.\n3. Pick the runners. Use `arena runners` from `~\u002F.cursor\u002Frules\u002Fpstack-models.mdc` when present. Otherwise default to one each on `claude-fable-5-thinking-max`, `gpt-5.6-sol-max`, `grok-4.6-fast-xhigh`, `claude-opus-5-thinking-xhigh`. Spawn more when the arena covers multiple design directions. Same model N times when the work is generation-bound rather than judgment-sensitive.\n4. Assign output paths. Each candidate writes to its own location (a git worktree where possible, otherwise `\u002Ftmp\u002Farena-\u003Cslug>\u002Fcandidate-\u003Cn>\u002F`). N candidates writing to the same path is shared mutable state and fails the the **separate-before-serializing-shared-state** principle skill test.\n\n## Phase B: Fan out\n\nSpawn all N subagents in one message with `run_in_background: true`, each with the task, the path to the shared grounding, its own output path, and instructions to produce both the artifact and a short rationale.\n\nThe rationale is mandatory. Without it, the parent cannot tell whether a candidate's structure is principled or accidental, which makes Phase E grafting unreliable. Each rationale names the alternatives the candidate considered and what it rejected.\n\nIf a candidate fails to produce output, proceed with N-1 and note the dropout in the synthesis record.\n\n## Phase C: Cross-judge\n\nAfter all Phase B candidates complete, choose one model from the `arena cross-judge pool` in `~\u002F.cursor\u002Frules\u002Fpstack-models.mdc` when present. Otherwise use `claude-fable-5-thinking-max`, `gpt-5.6-sol-max`, `grok-4.6-fast-xhigh`, `claude-opus-5-thinking-xhigh`. Prefer a different model family from the parent's. Spawn one readonly judge subagent on that model. It sees the rubric and the candidates by path label, scores each criterion, and recommends a base with rationale. It runs in parallel with the parent's reading in Phase D, not with the candidates themselves. Spawning while candidates are still writing means the judge sees partial or empty outputs and reports them as dropouts.\n\n## Phase D: Pick a base\n\nRead every candidate end to end before picking. Skimming N candidates surfaces only the candidate whose surface looks most familiar.\n\nScore each candidate against the rubric criterion by criterion, not on holistic feel. Compare against 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 on which candidate a future maintainer can extend most easily without breaking invariants. Prefer the cleaner boundary or smaller surface area when two feel tied, per the Laziness Protocol.\n\nRecord the pick and the reason in a short synthesis note alongside the base artifact, including the cross-judge's verdict.\n\n## Phase E: Graft\n\nWalk each losing candidate once more and identify what is worth porting into the base. The signal is usually one or two things per candidate, not most of it.\n\nFold each graft in by hand, per the **redesign-from-first-principles** principle skill. Don't paste mechanically. The result has to remain coherent under one mental model.\n\nRecord what was grafted, from which candidate, and what was rejected and why. The rejection notes are the highest-signal part of the record. Future readers learn from what you considered and dropped, not just what you kept.\n\nWhen N candidates converge on the same shape, that is a strong agreement signal. Note the convergence in the record and ship the consensus shape. No graft is needed. When N candidates wildly diverge, Phase A was under-specified. Reframe and re-run rather than averaging the divergence.\n\n## Phase F: Verify\n\nThe synthesized artifact has to hold up under the same scrutiny as any other output, per the **prove-it-works** principle skill. The arena does not earn you a pass.\n\nIf verification surfaces a problem the arena did not catch, either Phase A was wrong (re-frame and re-run) or one candidate caught it and you missed the graft (go back to Phase E). Don't paper over.\n\n## Outputs\n\nOne synthesized artifact. One short synthesis note alongside, naming the base, the grafts (with source candidate), the rejections, the dropouts if any, and the verification result.\n","# Arena\n\nFan out N parallel attempts at the same task. Read every candidate end to end. Pick the strongest as the base. Graft the best ideas from the others into it. Verify the synthesized result.\n\n## Start\n\nOpen a todolist with one entry per phase before launching anything. The arena runs autonomously and the list keeps phases from silently disappearing.\n\n1. Frame\n2. Fan out\n3. Cross-judge\n4. Pick\n5. Graft\n6. Verify\n\n## Phase A: Frame\n\nThe N candidates will receive the same prompt, so the prompt is the contract. Get it right before spawning anything.\n\n1. State the artifact each candidate is producing.\n2. Derive the rubric. State what success looks like for *this* task, then turn it into 3-6 concrete gradeable criteria. Concrete: `Adds a --dry-run flag that skips writes`. Vague: `code is correct`. The rubric is the picker's tool in Phase D; candidates only see the task.\n3. Pick the runners. Use `arena runners` from `~\u002F.cursor\u002Frules\u002Fpstack-models.mdc` when present. Otherwise default to one each on `claude-fable-5-thinking-max`, `gpt-5.6-sol-max`, `grok-4.6-fast-xhigh`, `claude-opus-5-thinking-xhigh`. Spawn more when the arena covers multiple design directions. Same model N times when the work is generation-bound rather than judgment-sensitive.\n4. Assign output paths. Each candidate writes to its own location (a git worktree where possible, otherwise `\u002Ftmp\u002Farena-\u003Cslug>\u002Fcandidate-\u003Cn>\u002F`). N candidates writing to the same path is shared mutable state and fails the the **separate-before-serializing-shared-state** principle skill test.\n\n## Phase B: Fan out\n\nSpawn all N subagents in one message with `run_in_background: true`, each with the task, the path to the shared grounding, its own output path, and instructions to produce both the artifact and a short rationale.\n\nThe rationale is mandatory. Without it, the parent cannot tell whether a candidate's structure is principled or accidental, which makes Phase E grafting unreliable. Each rationale names the alternatives the candidate considered and what it rejected.\n\nIf a candidate fails to produce output, proceed with N-1 and note the dropout in the synthesis record.\n\n## Phase C: Cross-judge\n\nAfter all Phase B candidates complete, choose one model from the `arena cross-judge pool` in `~\u002F.cursor\u002Frules\u002Fpstack-models.mdc` when present. Otherwise use `claude-fable-5-thinking-max`, `gpt-5.6-sol-max`, `grok-4.6-fast-xhigh`, `claude-opus-5-thinking-xhigh`. Prefer a different model family from the parent's. Spawn one readonly judge subagent on that model. It sees the rubric and the candidates by path label, scores each criterion, and recommends a base with rationale. It runs in parallel with the parent's reading in Phase D, not with the candidates themselves. Spawning while candidates are still writing means the judge sees partial or empty outputs and reports them as dropouts.\n\n## Phase D: Pick a base\n\nRead every candidate end to end before picking. Skimming N candidates surfaces only the candidate whose surface looks most familiar.\n\nScore each candidate against the rubric criterion by criterion, not on holistic feel. Compare against 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 on which candidate a future maintainer can extend most easily without breaking invariants. Prefer the cleaner boundary or smaller surface area when two feel tied, per the Laziness Protocol.\n\nRecord the pick and the reason in a short synthesis note alongside the base artifact, including the cross-judge's verdict.\n\n## Phase E: Graft\n\nWalk each losing candidate once more and identify what is worth porting into the base. The signal is usually one or two things per candidate, not most of it.\n\nFold each graft in by hand, per the **redesign-from-first-principles** principle skill. Don't paste mechanically. The result has to remain coherent under one mental model.\n\nRecord what was grafted, from which candidate, and what was rejected and why. The rejection notes are the highest-signal part of the record. Future readers learn from what you considered and dropped, not just what you kept.\n\nWhen N candidates converge on the same shape, that is a strong agreement signal. Note the convergence in the record and ship the consensus shape. No graft is needed. When N candidates wildly diverge, Phase A was under-specified. Reframe and re-run rather than averaging the divergence.\n\n## Phase F: Verify\n\nThe synthesized artifact has to hold up under the same scrutiny as any other output, per the **prove-it-works** principle skill. The arena does not earn you a pass.\n\nIf verification surfaces a problem the arena did not catch, either Phase A was wrong (re-frame and re-run) or one candidate caught it and you missed the graft (go back to Phase E). Don't paper over.\n\n## Outputs\n\nOne synthesized artifact. One short synthesis note alongside, naming the base, the grafts (with source candidate), the rejections, the dropouts if any, and the verification result.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","32794f82cde37d7beb6bd5a3ec6b2627df6343e1",".agents\u002Fskills\u002Fpstack\u002Farena",0,"https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop","https:\u002F\u002Fgithub.com\u002FSenCha930511","2026-10-29 14:13:50",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":24},[34,37,40],{"tool":35,"command":36},"npx","npx skills add SenCha930511\u002Fomp-desktop --skill arena",{"tool":38,"command":39},"bunx","bunx skills add SenCha930511\u002Fomp-desktop --skill arena",{"tool":41,"command":42},"pnpm","pnpm dlx skills add SenCha930511\u002Fomp-desktop --skill arena","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpstack\u002Farena\u002FSKILL.md",[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7EZCQMYWW2DTGD2S0DDFH70","gui-automation","Use when you need to visually interact with a GUI — test buttons, fill forms, verify visual layouts, fuzz web pages, automate user flows, take screenshots, or perform end-to-end QA on any application. Works on cloud VMs, Docker containers, local machines, and sandboxes. Install: pip install cua.","https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fgui-automation\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7EZCNGTT0C0T7MT3AZ4S1H5","gooeypi-computer-use","Drive native applications on macOS, Windows, or Linux through the separately installed TryCUA driver CLI.","https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fgooeypi-computer-use\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7EZCGWBSA4YMNJWZNE1THZM","verify-omp-desktop","Launch and drive the OMP Desktop desktop (Electron) app to prove user-facing behavior — sidebar navigation, Settings, and Capabilities — capturing screenshots and ARIA snapshots. Reach for this when verifying a OMP Desktop UI change or confirming the app still works end to end.","https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fverify-omp-desktop\u002FSKILL.md",[],[],{"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":19},"01M7EZCEEK5702GNYQQ74J8XAR","review-pr-viability","Review a pull request or issue for value, implementation quality, maintainability, regression risk, and reliance on upstream changes.","https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freview-pr-viability\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7EZC8CEFJ14446XSEMV807Q","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\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpstack\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7EZC61F3RFAV186YZT6R9ZM","unslop","Cut AI tells from any writing. Must always apply.","https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpstack\u002Funslop\u002FSKILL.md",[],[]]