[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GW9E3VSNFXHHEEBABZXM69":3,"skill-same:01M6GW9E3VSNFXHHEEBABZXM69":61},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M6GW9E3VSNFXHHEEBABZXM69","planning",null,"peteromallet\u002FArnold","peteromallet","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4647941?v=4","01M6GW770S4CG20MPXS5PZWNF8","POM","01M6GW774TYWCS83WGXD72E15V",98,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Farnold_pipelines\u002Fmegaplan\u002Fpipelines\u002Fplanning\u002FSKILL.md",[],[5],"2026-11-10 10:12:30",false,"> **Authority status (M11):** Zero-authority history. All repair, audit, and deployment authority has been migrated to canonical delegation. This document is retained for reference only — it must not be used to materialize commands, grant authority, or drive automated actions.\n\n# Planning Pipeline — Skill Reference\n\n## Overview\n\nThe `megaplan` pipeline (packaged at `megaplan\u002Fpipelines\u002Fplanning\u002F`) is the built-in megaplan plan-production substrate.\nIts canonical registry identity is `megaplan` with the legacy alias `planning → megaplan`.\nIt orchestrates the full prepare → plan → critique\u002Fgate\u002Frevise loop →\nfinalize → execute → review lifecycle.\n\n---\n\n## Gate verdict vocabulary\n\nThe gate stage emits a `PipelineVerdict` whose `recommendation` field is one\nof the following `GateRecommendation` literals:\n\n| Verdict | Meaning |\n|---|---|\n| `proceed` | Gate approved the plan; advance to finalize (and optionally execute). |\n| `iterate` | Gate rejected the plan; re-enter the critique → revise loop. |\n| `tiebreaker` | Evaluators are split; hand off to the tiebreaker stage for adjudication. |\n| `escalate` | Quality ceiling reached at current tier; escalate to a higher-complexity model. |\n\n---\n\n## Robustness levels\n\nRobustness controls the depth of the critique\u002Fgate loop and the number of\nevaluators engaged. Canonical names (accepted by `--robustness` \u002F config):\n\n| Level | Alias(es) | Behaviour |\n|---|---|---|\n| `bare` | `tiny` | Single-pass, no gate loop. Fastest; for quick drafts. |\n| `light` | — | One critique + revise round, minimal gate criteria. |\n| `full` | `standard` | Standard gate loop (default). Balanced quality\u002Fcost. |\n| `thorough` | `robust` | Extended gate loop, stricter criteria, more evaluators. |\n| `extreme` | `superrobust` | Maximum depth, all evaluators enabled. |\n\nThe default robustness when no `--robustness` flag is supplied is `full`.\n\n---\n\n## Stage topology\n\n```\nprep → plan → critique ──→ gate ──proceed──→ finalize [→ execute → review]\n                 ↑             │\n                 └──iterate────┘\n                               │\n                               └──tiebreaker──→ [adjudication] → finalize\n```\n\nDriver substrate: `subprocess_isolated` (execute\u002Freview) + `graph+loop-node`\n(critique→gate→revise subloop).\n\n`arnold_api_version`: `1.0`\n`capabilities`: `plan, execute, review`\n",{},"main","4815916805531030f062fc1c10bcc9f9cd10a40f","arnold_pipelines\u002Fmegaplan\u002Fpipelines\u002Fplanning",7,"https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold","https:\u002F\u002Fgithub.com\u002Fpeteromallet","2026-10-27 21:10:27",{"source":7,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add peteromallet\u002FArnold --skill planning",{"tool":35,"command":36},"bunx","bunx skills add peteromallet\u002FArnold --skill planning",{"tool":38,"command":39},"pnpm","pnpm dlx skills add peteromallet\u002FArnold --skill planning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Farnold_pipelines\u002Fmegaplan\u002Fpipelines\u002Fplanning\u002FSKILL.md",true,[43,49,53,57],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"__init__.py","SCRIPT","脚本",1085,"https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Farnold_pipelines\u002Fmegaplan\u002Fpipelines\u002Fplanning\u002F__init__.py",{"path":50,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":51,"sourceHtmlUrl":52},"prompts\u002F__init__.py",354,"https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Farnold_pipelines\u002Fmegaplan\u002Fpipelines\u002Fplanning\u002Fprompts\u002F__init__.py",{"path":54,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":55,"sourceHtmlUrl":56},"routing.py",639,"https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Farnold_pipelines\u002Fmegaplan\u002Fpipelines\u002Fplanning\u002Frouting.py",{"path":58,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":59,"sourceHtmlUrl":60},"steps.py",3294,"https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Farnold_pipelines\u002Fmegaplan\u002Fpipelines\u002Fplanning\u002Fsteps.py",[62,71,77,83,89,106],{"skillNo":63,"name":64,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M6GWC4WCKXPTH05M6D84CPC6","live_supervisor","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Fexamples\u002Fworkflow_authoring\u002Fshipped\u002Flive_supervisor\u002FSKILL.md",[],[68,69,70],"live supervisor","live","supervisor",{"skillNo":72,"name":73,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M6GWC25QW59XZMZF5A8QB1R2","jokes","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Fexamples\u002Fworkflow_authoring\u002Fshipped\u002Fjokes\u002FSKILL.md",[],[73],{"skillNo":78,"name":79,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M6GWBZ01NNK2NMGC4GSNK5EN","creative","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Fexamples\u002Fworkflow_authoring\u002Fshipped\u002Fcreative\u002FSKILL.md",[],[79],{"skillNo":84,"name":85,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M6GWBX6DPACH6GV2MD07Z1Q9","hello","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Fexamples\u002Fworkflow_authoring\u002Fhello\u002FSKILL.md",[],[85],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M6GWBRWZSK3C7459P1H2X2HZ","vibecomfy-executor","Arnold pipeline that classifies a user query, optionally researches via Hivemind\u002FBanodoco, optionally edits a ComfyUI workflow, and always emits a final reply.","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Fdocs\u002Farchive\u002Fm5\u002Fpipelines\u002Fvibecomfy_executor\u002FSKILL.md",[],[96,97,98,99,100,101,102,103,104,105],"vibecomfy executor","executor","comfyui","via","query","reply","hivemind","user","pipeline","workflow",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":122,"publishedAt":18},"01M6GWBPM62R2V1X5P81WWX1C3","simplify-writing","Fan out DeepSeek Pro critics and a Kimi editor to iteratively simplify a piece of writing.","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Fdocs\u002Farchive\u002Fm5\u002Fpipelines\u002Fsimplify_writing\u002Fskills\u002Fsimplify-writing\u002FSKILL.md",[112,117],{"categoryNo":113,"categoryName":114,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":118,"categoryName":119,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[123,124,125,126,127,128,129],"simplify","simplify writing","writing","pro","deepseek","kimi","editor"]