[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DHAC6B365WHP4Z10T7RCWM":3,"skill-same:01M6DHAC6B365WHP4Z10T7RCWM":84},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":13,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M6DHAC6B365WHP4Z10T7RCWM","patterns",null,"Shared workflow patterns referenced across orchestrator skills — multi-explorer deployment, the discovery\u002Ffriction signal vocabulary, the outcome interview, and state-chain file formats. Load on-demand when a skill points to a section.","JAuto-Corp\u002Fjustinventit","JAuto-Corp","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F254009312?v=4","01M6DH85D43FJAXD8RPBY6A91C","01M6DH85M60CDJBZ9W2CAFCPXE",0,"MIT","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fpatterns\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"workflow","deployment","state","file","discovery","interview","orchestrator","outcome","friction","explorer","vocabulary","workflow patterns","across","shared","2026-11-10 10:12:30",false,"---\nname: patterns\ndescription: \"Shared workflow patterns referenced across orchestrator skills — multi-explorer deployment, the discovery\u002Ffriction signal vocabulary, the outcome interview, and state-chain file formats. Load on-demand when a skill points to a section.\"\n---\n\n# Shared Patterns\n\nReusable patterns extracted from the orchestrator skills so they live in one place. Load the specific pattern a skill points you to — don't preload.\n\n## Available Patterns\n\n| Pattern | Depth file | Referenced by |\n|-|-|-|\n| Multi-Explorer | `explorer.md` | work, verify |\n| Discovery Signals | `discovery.md` | verify, capture |\n| Friction Signals | `discovery.md` | verify, capture |\n| Interview Protocol | `interview.md` | work |\n| State Files | `state-files.md` | work, verify, capture |\n\n## When to Load\n\nA skill says \"see the `patterns` skill § X\" or \"see `patterns\u002Fexplorer.md`\". Read the matching file only when you hit that reference. The sections below are the quick reference; the depth files carry formats, examples, and edge cases.\n\n---\n\n## Multi-Explorer Pattern\n\nDeploy read-only `Explore` sub-agents to gather context before acting. Each gets one viewpoint over a fixed scope and returns bounded, evidence-backed findings; you cross-reference them and verify the cited lines before trusting anything.\n\n```\nTask(subagent_type=\"Explore\", prompt=\"[Viewpoint] for [SCOPE]:\n- \u003Cfocused questions for this viewpoint>\nReturn findings under 2000 characters, each with file:line and (for audits) a severity.\")\n```\n\nExplorers cannot load skills — after they report, YOU invoke any matching best-practices skill and reconcile. Full deployment guidance, the viewpoint menu, and the validation checklist: `explorer.md`.\n\n---\n\n## Discovery Signals\n\nEmit when you find something **outside the current scope** and want it tracked without derailing. The stop action `stop\u002Factions\u002Fdiscovery-extraction.sh` scans session output for `[DISCOVERY:*]` and appends each to `context\u002FDISCOVERIES.md`; the `capture` skill later turns those into issues.\n\n| Signal | Meaning | Action |\n|-|-|-|\n| `[DISCOVERY:BLOCKER]` | Security\u002Frequirements wrong; blocks current work | STOP, escalate |\n| `[DISCOVERY:DEFECT]` | Bug in existing code | Log, continue |\n| `[DISCOVERY:ADJACENT]` | Related to this epic, a different phase | Log for later phase |\n| `[DISCOVERY:DISTANT]` | Unrelated to current work | Log for backlog |\n\nFormat, examples, and the triage matrix: `discovery.md`.\n\n---\n\n## Friction Signals\n\nEmit when the **process itself** was wrong — a skill, hook, or workflow step got in the way. The stop action `stop\u002Factions\u002Ffriction-extraction.sh` scans for `[FRICTION:*]` and appends each to `context\u002FFRICTION_LOG.md`; `capture` classifies each PROJECT vs FRAMEWORK.\n\n| Signal | When |\n|-|-|\n| `[FRICTION:SKILL]` | A skill was wrong, outdated, or missing for this codebase |\n| `[FRICTION:HOOK]` | A hook blocked or fired when it shouldn't have |\n| `[FRICTION:WORKFLOW]` | A workflow step was unnecessary or in the wrong order |\n| `[FRICTION:CONTEXT]` | Missing context caused confusion or rework |\n\nFormat and the classification handoff: `discovery.md`.\n\n---\n\n## Interview Protocol\n\nUse the `AskUserQuestion` tool for iterative Q&A before writing a spec or making a UX\u002Farchitecture decision the code can't answer. Ask 1-4 structured questions per round, process answers, ask again — never dump a wall of text. Skip for single-file fixes and clear technical tasks. Categories, rhythm, and output: `interview.md`.\n\n---\n\n## State Files\n\nThe state chain carries work across sessions and context resets.\n\n| File | Purpose |\n|-|-|\n| `docs\u002FCURRENT_WORK.md` | Active epic\u002Fsprint\u002Fphase pointer |\n| `context\u002FWORKING.md` | Append-only session observation blocks |\n| Phase `PROGRESS.md` | Implementation checklist |\n\nRead order and templates: `state-files.md`.\n","# Shared Patterns\n\nReusable patterns extracted from the orchestrator skills so they live in one place. Load the specific pattern a skill points you to — don't preload.\n\n## Available Patterns\n\n| Pattern | Depth file | Referenced by |\n|-|-|-|\n| Multi-Explorer | `explorer.md` | work, verify |\n| Discovery Signals | `discovery.md` | verify, capture |\n| Friction Signals | `discovery.md` | verify, capture |\n| Interview Protocol | `interview.md` | work |\n| State Files | `state-files.md` | work, verify, capture |\n\n## When to Load\n\nA skill says \"see the `patterns` skill § X\" or \"see `patterns\u002Fexplorer.md`\". Read the matching file only when you hit that reference. The sections below are the quick reference; the depth files carry formats, examples, and edge cases.\n\n---\n\n## Multi-Explorer Pattern\n\nDeploy read-only `Explore` sub-agents to gather context before acting. Each gets one viewpoint over a fixed scope and returns bounded, evidence-backed findings; you cross-reference them and verify the cited lines before trusting anything.\n\n```\nTask(subagent_type=\"Explore\", prompt=\"[Viewpoint] for [SCOPE]:\n- \u003Cfocused questions for this viewpoint>\nReturn findings under 2000 characters, each with file:line and (for audits) a severity.\")\n```\n\nExplorers cannot load skills — after they report, YOU invoke any matching best-practices skill and reconcile. Full deployment guidance, the viewpoint menu, and the validation checklist: `explorer.md`.\n\n---\n\n## Discovery Signals\n\nEmit when you find something **outside the current scope** and want it tracked without derailing. The stop action `stop\u002Factions\u002Fdiscovery-extraction.sh` scans session output for `[DISCOVERY:*]` and appends each to `context\u002FDISCOVERIES.md`; the `capture` skill later turns those into issues.\n\n| Signal | Meaning | Action |\n|-|-|-|\n| `[DISCOVERY:BLOCKER]` | Security\u002Frequirements wrong; blocks current work | STOP, escalate |\n| `[DISCOVERY:DEFECT]` | Bug in existing code | Log, continue |\n| `[DISCOVERY:ADJACENT]` | Related to this epic, a different phase | Log for later phase |\n| `[DISCOVERY:DISTANT]` | Unrelated to current work | Log for backlog |\n\nFormat, examples, and the triage matrix: `discovery.md`.\n\n---\n\n## Friction Signals\n\nEmit when the **process itself** was wrong — a skill, hook, or workflow step got in the way. The stop action `stop\u002Factions\u002Ffriction-extraction.sh` scans for `[FRICTION:*]` and appends each to `context\u002FFRICTION_LOG.md`; `capture` classifies each PROJECT vs FRAMEWORK.\n\n| Signal | When |\n|-|-|\n| `[FRICTION:SKILL]` | A skill was wrong, outdated, or missing for this codebase |\n| `[FRICTION:HOOK]` | A hook blocked or fired when it shouldn't have |\n| `[FRICTION:WORKFLOW]` | A workflow step was unnecessary or in the wrong order |\n| `[FRICTION:CONTEXT]` | Missing context caused confusion or rework |\n\nFormat and the classification handoff: `discovery.md`.\n\n---\n\n## Interview Protocol\n\nUse the `AskUserQuestion` tool for iterative Q&A before writing a spec or making a UX\u002Farchitecture decision the code can't answer. Ask 1-4 structured questions per round, process answers, ask again — never dump a wall of text. Skip for single-file fixes and clear technical tasks. Categories, rhythm, and output: `interview.md`.\n\n---\n\n## State Files\n\nThe state chain carries work across sessions and context resets.\n\n| File | Purpose |\n|-|-|\n| `docs\u002FCURRENT_WORK.md` | Active epic\u002Fsprint\u002Fphase pointer |\n| `context\u002FWORKING.md` | Append-only session observation blocks |\n| Phase `PROGRESS.md` | Implementation checklist |\n\nRead order and templates: `state-files.md`.\n",{"name":5,"description":7},"main","07fef474a459f2562dbae35a3baf6470c8ae530d","template\u002F.claude\u002Fskills\u002Forchestrators\u002Fpatterns","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit","https:\u002F\u002Fgithub.com\u002FJAuto-Corp","2026-11-10 13:45:22",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add JAuto-Corp\u002Fjustinventit --skill patterns",{"tool":54,"command":55},"bunx","bunx skills add JAuto-Corp\u002Fjustinventit --skill patterns",{"tool":57,"command":58},"pnpm","pnpm dlx skills add JAuto-Corp\u002Fjustinventit --skill patterns","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fpatterns\u002FSKILL.md",true,[62,68,72,76,80],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"agents\u002Fopenai.yaml","REFERENCE","参考文档",318,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fomero-django-docker-lab-infrastructure\u002Fselected-omero-reference\u002Fdeployment-patterns-omero-docker-extended\u002Fagents\u002Fopenai.yaml",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"discovery.md",2530,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fpatterns\u002Fdiscovery.md",{"path":73,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":74,"sourceHtmlUrl":75},"explorer.md",2978,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fpatterns\u002Fexplorer.md",{"path":77,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":78,"sourceHtmlUrl":79},"interview.md",2345,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fpatterns\u002Finterview.md",{"path":81,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":82,"sourceHtmlUrl":83},"state-files.md",2140,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fpatterns\u002Fstate-files.md",[85,112,131,152,171,187],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":89,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":37},"01M6DHBJE2P291DTXAW6DE6ZSR","ponytail","Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says \"ponytail\", \"be lazy\", \"lazy mode\", \"simplest solution\", \"minimal solution\", \"yagni\", \"do less\", or \"shortest path\", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Fponytail\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Fponytail\u002FSKILL.md",[],[87,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111],"writing","yagni","line","recipes","platform","dependencies","task","do","translation","default","general","minimal","use","question","refactoring","knowledge","dev","code","libraries",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":126,"publishedAt":37},"01M6DHB61PAWVGHF53A89MJ6SM","workflow\u002Fskill","Patterns for adding or editing a skill — frontmatter contract, router + sub-file split, line budgets.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002Fskill.md",[118,123],{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":124,"categoryName":125,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000037","律师与法务",[127,23,5,128,129,26,130,95],"workflow skill","router","editing","contract",{"skillNo":132,"name":23,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":137,"publishedAt":37},"01M6DHB1GD89RW71ZYZJZJH4ZG","Meta-skill for editing the framework itself — skills, hooks, commands, rules, CLAUDE.md. Use before changing anything under .claude\u002F or the routing docs, so the change keeps the system's shape (lazy-load, forge markers, hook auto-discovery, harness).","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002FSKILL.md",[136],{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},[23,138,139,140,141,142,105,129,143,144,27,145,146,147,148,149,150,151],"commands","meta-skill","shape","hooks","auto","Rules","system","Meta","forge","harness","change","routing","docs","framework",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":37},"01M6DHAX1NCV3HXK4M1RMBWGAV","work","Work lifecycle orchestration: start, continue, pause, handoff, done, plus epic\u002Fsprint planning. Context gathering + goal-focused state-chain transitions.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fwork\u002FSKILL.md",[],[154,159,160,161,162,163,164,165,166,167,25,168,169,170],"continue","chain","sprint planning","transitions","done","goal","context","lifecycle","start","planning","orchestration","handoff",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":37},"01M6DHASZYRB1ZZWVNQ6CN8FN3","verify","Verification and auditing. Validate acceptance scenarios, run multi-perspective audits, check type-check\u002Fbuild evidence, and gate phase\u002Fsprint completion.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fverify\u002FSKILL.md",[],[173,178,179,180,181,182,183,184,185,186],"check","verification","acceptance","run","validate","evidence","type","build","gate",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":193,"publishedAt":37},"01M6DHAP9JN9X7ZSWCWYTWN1KT","team-lead","Coordinate an Agent Team for parallelizable work — implementation, audit, research, or testing. Teaches the mechanical constraints (WAIT pattern, file ownership, model tiers) and lets you design the team. For orchestration_tier=cluster \u002F multi-agent runs.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fteam-lead\u002FSKILL.md",[],[194,195,196,197,198,199,200,201,154,202,203,204,205,26,169,206,207,208],"team","team lead","implementation","wait","mechanical","pattern","agent team","coordinate","multi-agent","model","constraints","audit","research","design","testing"]