[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DEGHR0HTN4JF4H2P99BTG4":3,"skill-same:01M6DEGHR0HTN4JF4H2P99BTG4":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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":54,"install":55,"resources":68},"01M6DEGHR0HTN4JF4H2P99BTG4","multi-agent-quickstart",null,"Use when learning how to reach Codex from this Windows-first setup - the beginner mental model for the codex mcp-server rail (mcp__codex__codex \u002F mcp__codex__codex-reply), how the retired per-mode codex_* tools map onto prompt framings, when to fan out parallel calls instead, and how to choose an execution path after planning.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fmulti-agent-quickstart\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"multi agent","multi agent quickstart","quickstart","how","MCP","map","use","prompt","choose","parallel","model","learning","windows","first","execution","Tools","server","codex","planning","setup","2026-11-10 10:12:30",false,"---\nname: multi-agent-quickstart\ndescription: Use when learning how to reach Codex from this Windows-first setup - the beginner mental model for the codex mcp-server rail (mcp__codex__codex \u002F mcp__codex__codex-reply), how the retired per-mode codex_* tools map onto prompt framings, when to fan out parallel calls instead, and how to choose an execution path after planning.\n---\n\n# Multi-Agent Quickstart\n\n**Rewritten 2026-08-09.** The previous version taught six MCP tools (`codex_consult`,\n`codex_brainstorm`, `codex_review`, `codex_discuss`, `codex_coordinate`, `codex_curate`) plus\nan optional PromptBridge talk lane. All of them came from `tools\u002Fmcp\u002Fcodex-orchestrator\u002F` and\n`tools\u002Fweb\u002Fpromptbridge-talk-lane\u002F`, both deleted. These are not renames - the old tool names\nfail rather than degrade.\n\n## Mental model\n\nThere is **one rail**: the official `codex mcp-server`.\n\n- `mcp__codex__codex` - start a Codex thread.\n- `mcp__codex__codex-reply` - continue by `threadId` (hyphenated; the underscore form does\n  not resolve).\n\nThe old tool names are now prompt framings on that one rail:\n\n| Old tool | Now |\n|---|---|\n| `codex_consult` | one call asking for one strong answer |\n| `codex_brainstorm` | one call asking for N alternatives |\n| `codex_review` | one call handing over the plan\u002Fdiff, asking for a critic pass |\n| `codex_discuss` | two parallel calls with opposed framings, synthesized by you |\n| `codex_coordinate` | one call per role in parallel, consolidated by you |\n| `codex_curate` | one call handed the option set, asked to select and justify |\n\nFan-out replaces the orchestration server. Each call is single-threaded and fresh-context, so\nanything that must persist belongs in the prompt or in a file.\n\n## Beginner flow\n\n1. Make one `mcp__codex__codex` call and read the answer.\n2. Ask for alternatives in a second call if one answer is not enough.\n3. Ask for a critic pass before a risky implementation.\n4. Hand the option set back for selection when choosing among options.\n\n## Execution choice\n\n- After planning, prefer subagent-driven execution for complex work.\n- Use inline execution when the task is small or subagents would be overhead.\n- Do not silently force one path after the plan is written.\n\n## Failure behavior\n\nThere is no second lane to fall back to, and no `fallback_to_lane_a` flag. If the rail is\nunavailable, say so and stop - do not answer as though a Codex peer had been consulted.\nDiagnose with `codex --version` and `claude mcp get codex` (expect `Connected`).\n\n## Related skills\n\n`codex-orchestrate` (mode routing on this rail) · `codex-invoke` (exec rail, per-call\nscoping) · `codex-consult` (retired tombstone, redirects here).\n","# Multi-Agent Quickstart\n\n**Rewritten 2026-08-09.** The previous version taught six MCP tools (`codex_consult`,\n`codex_brainstorm`, `codex_review`, `codex_discuss`, `codex_coordinate`, `codex_curate`) plus\nan optional PromptBridge talk lane. All of them came from `tools\u002Fmcp\u002Fcodex-orchestrator\u002F` and\n`tools\u002Fweb\u002Fpromptbridge-talk-lane\u002F`, both deleted. These are not renames - the old tool names\nfail rather than degrade.\n\n## Mental model\n\nThere is **one rail**: the official `codex mcp-server`.\n\n- `mcp__codex__codex` - start a Codex thread.\n- `mcp__codex__codex-reply` - continue by `threadId` (hyphenated; the underscore form does\n  not resolve).\n\nThe old tool names are now prompt framings on that one rail:\n\n| Old tool | Now |\n|---|---|\n| `codex_consult` | one call asking for one strong answer |\n| `codex_brainstorm` | one call asking for N alternatives |\n| `codex_review` | one call handing over the plan\u002Fdiff, asking for a critic pass |\n| `codex_discuss` | two parallel calls with opposed framings, synthesized by you |\n| `codex_coordinate` | one call per role in parallel, consolidated by you |\n| `codex_curate` | one call handed the option set, asked to select and justify |\n\nFan-out replaces the orchestration server. Each call is single-threaded and fresh-context, so\nanything that must persist belongs in the prompt or in a file.\n\n## Beginner flow\n\n1. Make one `mcp__codex__codex` call and read the answer.\n2. Ask for alternatives in a second call if one answer is not enough.\n3. Ask for a critic pass before a risky implementation.\n4. Hand the option set back for selection when choosing among options.\n\n## Execution choice\n\n- After planning, prefer subagent-driven execution for complex work.\n- Use inline execution when the task is small or subagents would be overhead.\n- Do not silently force one path after the plan is written.\n\n## Failure behavior\n\nThere is no second lane to fall back to, and no `fallback_to_lane_a` flag. If the rail is\nunavailable, say so and stop - do not answer as though a Codex peer had been consulted.\nDiagnose with `codex --version` and `claude mcp get codex` (expect `Connected`).\n\n## Related skills\n\n`codex-orchestrate` (mode routing on this rail) · `codex-invoke` (exec rail, per-call\nscoping) · `codex-consult` (retired tombstone, redirects here).\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Fmulti-agent-quickstart","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill multi-agent-quickstart",{"tool":61,"command":62},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill multi-agent-quickstart",{"tool":64,"command":65},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill multi-agent-quickstart","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fmulti-agent-quickstart\u002FSKILL.md",true,[69],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"agents\u002Fopenai.yaml","REFERENCE","参考文档",179,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fmulti-agent-quickstart\u002Fagents\u002Fopenai.yaml",[76,96,120,147,160,176],{"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":44},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[83,84,85,86,87,88,89,90,91,30,92,93,94,38,95],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","file",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":103,"publishedAt":44},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[102],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[104,27,105,106,107,108,109,110,111,112,113,114,115,36,30,116,117,118,119,28],"openmm md","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","free","molecular dynamics","local","do",{"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":132,"publishedAt":44},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[126,129],{"categoryNo":127,"categoryName":128,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[133,134,135,136,137,138,139,140,141,142,27,143,144,145,146],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":44},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[149,43,154,155,156,157,158,159],"report","project","installation","project setup","issues","state",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":167,"publishedAt":44},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[166],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[162,168,88,169,170,171,30,172,173,174,175],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":177,"name":43,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":181,"publishedAt":44},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[43,155,118,182,157,183],"files","interactive"]