[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBY99T6XSCVPD21QDX6330":3,"skill-same:01M6DBY99T6XSCVPD21QDX6330":59},{"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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":44,"install":45,"resources":58},"01M6DBY99T6XSCVPD21QDX6330","source-command-devfleet",null,"Orchestrate parallel Codex agents via Codex DevFleet — plan projects from natural language, dispatch agents in isolated worktrees, monitor progress, and read structured reports.","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\u002F.agents\u002Fskills\u002Fsource-command-devfleet\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"command","source command devfleet","codex","monitor","orchestrate","plan","projects","parallel","read","dispatch","reports","worktrees","language","natural language","structured","2026-11-10 10:12:30",false,"---\nname: \"source-command-devfleet\"\ndescription: \"Orchestrate parallel Codex agents via Codex DevFleet — plan projects from natural language, dispatch agents in isolated worktrees, monitor progress, and read structured reports.\"\n---\n\n# source-command-devfleet\n\nUse this skill when the user asks to run the migrated source command `devfleet`.\n\n## Command Template\n\n# DevFleet — Multi-Agent Orchestration\n\nOrchestrate parallel Codex agents via Codex DevFleet. Each agent runs in an isolated git worktree with full tooling.\n\nRequires the DevFleet MCP server: `Codex mcp add devfleet --transport http http:\u002F\u002Flocalhost:18801\u002Fmcp`\n\n## Flow\n\n```\nUser describes project\n  → plan_project(prompt) → mission DAG with dependencies\n  → Show plan, get approval\n  → dispatch_mission(M1) → Agent spawns in worktree\n  → M1 completes → auto-merge → M2 auto-dispatches (depends_on M1)\n  → M2 completes → auto-merge\n  → get_report(M2) → files_changed, what_done, errors, next_steps\n  → Report summary to user\n```\n\n## Workflow\n\n1. **Plan the project** from the user's description:\n\n```\nmcp__devfleet__plan_project(prompt=\"\u003Cuser's description>\")\n```\n\nThis returns a project with chained missions. Show the user:\n- Project name and ID\n- Each mission: title, type, dependencies\n- The dependency DAG (which missions block which)\n\n2. **Wait for user approval** before dispatching. Show the plan clearly.\n\n3. **Dispatch the first mission** (the one with empty `depends_on`):\n\n```\nmcp__devfleet__dispatch_mission(mission_id=\"\u003Cfirst_mission_id>\")\n```\n\nThe remaining missions auto-dispatch as their dependencies complete (because `plan_project` creates them with `auto_dispatch=true`). When manually creating missions with `create_mission`, you must explicitly set `auto_dispatch=true` for this behavior.\n\n4. **Monitor progress** — check what's running:\n\n```\nmcp__devfleet__get_dashboard()\n```\n\nOr check a specific mission:\n\n```\nmcp__devfleet__get_mission_status(mission_id=\"\u003Cid>\")\n```\n\nPrefer polling with `get_mission_status` over `wait_for_mission` for long-running missions, so the user sees progress updates.\n\n5. **Read the report** for each completed mission:\n\n```\nmcp__devfleet__get_report(mission_id=\"\u003Cmission_id>\")\n```\n\nCall this for every mission that reached a terminal state. Reports contain: files_changed, what_done, what_open, what_tested, what_untested, next_steps, errors_encountered.\n\n## All Available Tools\n\n| Tool | Purpose |\n|------|---------|\n| `plan_project(prompt)` | AI breaks description into chained missions with `auto_dispatch=true` |\n| `create_project(name, path?, description?)` | Create a project manually, returns `project_id` |\n| `create_mission(project_id, title, prompt, depends_on?, auto_dispatch?)` | Add a mission. `depends_on` is a list of mission ID strings. |\n| `dispatch_mission(mission_id, model?, max_turns?)` | Start an agent |\n| `cancel_mission(mission_id)` | Stop a running agent |\n| `wait_for_mission(mission_id, timeout_seconds?)` | Block until done (prefer polling for long tasks) |\n| `get_mission_status(mission_id)` | Check progress without blocking |\n| `get_report(mission_id)` | Read structured report |\n| `get_dashboard()` | System overview |\n| `list_projects()` | Browse projects |\n| `list_missions(project_id, status?)` | List missions |\n\n## Guidelines\n\n- Always confirm the plan before dispatching unless the user said \"go ahead\"\n- Include mission titles and IDs when reporting status\n- If a mission fails, read its report to understand errors before retrying\n- Agent concurrency is configurable (default: 3). Excess missions queue and auto-dispatch as slots free up. Check `get_dashboard()` for slot availability.\n- Dependencies form a DAG — never create circular dependencies\n- Each agent auto-merges its worktree on completion. If a merge conflict occurs, the changes remain on the worktree branch for manual resolution.\n","# source-command-devfleet\n\nUse this skill when the user asks to run the migrated source command `devfleet`.\n\n## Command Template\n\n# DevFleet — Multi-Agent Orchestration\n\nOrchestrate parallel Codex agents via Codex DevFleet. Each agent runs in an isolated git worktree with full tooling.\n\nRequires the DevFleet MCP server: `Codex mcp add devfleet --transport http http:\u002F\u002Flocalhost:18801\u002Fmcp`\n\n## Flow\n\n```\nUser describes project\n  → plan_project(prompt) → mission DAG with dependencies\n  → Show plan, get approval\n  → dispatch_mission(M1) → Agent spawns in worktree\n  → M1 completes → auto-merge → M2 auto-dispatches (depends_on M1)\n  → M2 completes → auto-merge\n  → get_report(M2) → files_changed, what_done, errors, next_steps\n  → Report summary to user\n```\n\n## Workflow\n\n1. **Plan the project** from the user's description:\n\n```\nmcp__devfleet__plan_project(prompt=\"\u003Cuser's description>\")\n```\n\nThis returns a project with chained missions. Show the user:\n- Project name and ID\n- Each mission: title, type, dependencies\n- The dependency DAG (which missions block which)\n\n2. **Wait for user approval** before dispatching. Show the plan clearly.\n\n3. **Dispatch the first mission** (the one with empty `depends_on`):\n\n```\nmcp__devfleet__dispatch_mission(mission_id=\"\u003Cfirst_mission_id>\")\n```\n\nThe remaining missions auto-dispatch as their dependencies complete (because `plan_project` creates them with `auto_dispatch=true`). When manually creating missions with `create_mission`, you must explicitly set `auto_dispatch=true` for this behavior.\n\n4. **Monitor progress** — check what's running:\n\n```\nmcp__devfleet__get_dashboard()\n```\n\nOr check a specific mission:\n\n```\nmcp__devfleet__get_mission_status(mission_id=\"\u003Cid>\")\n```\n\nPrefer polling with `get_mission_status` over `wait_for_mission` for long-running missions, so the user sees progress updates.\n\n5. **Read the report** for each completed mission:\n\n```\nmcp__devfleet__get_report(mission_id=\"\u003Cmission_id>\")\n```\n\nCall this for every mission that reached a terminal state. Reports contain: files_changed, what_done, what_open, what_tested, what_untested, next_steps, errors_encountered.\n\n## All Available Tools\n\n| Tool | Purpose |\n|------|---------|\n| `plan_project(prompt)` | AI breaks description into chained missions with `auto_dispatch=true` |\n| `create_project(name, path?, description?)` | Create a project manually, returns `project_id` |\n| `create_mission(project_id, title, prompt, depends_on?, auto_dispatch?)` | Add a mission. `depends_on` is a list of mission ID strings. |\n| `dispatch_mission(mission_id, model?, max_turns?)` | Start an agent |\n| `cancel_mission(mission_id)` | Stop a running agent |\n| `wait_for_mission(mission_id, timeout_seconds?)` | Block until done (prefer polling for long tasks) |\n| `get_mission_status(mission_id)` | Check progress without blocking |\n| `get_report(mission_id)` | Read structured report |\n| `get_dashboard()` | System overview |\n| `list_projects()` | Browse projects |\n| `list_missions(project_id, status?)` | List missions |\n\n## Guidelines\n\n- Always confirm the plan before dispatching unless the user said \"go ahead\"\n- Include mission titles and IDs when reporting status\n- If a mission fails, read its report to understand errors before retrying\n- Agent concurrency is configurable (default: 3). Excess missions queue and auto-dispatch as slots free up. Check `get_dashboard()` for slot availability.\n- Dependencies form a DAG — never create circular dependencies\n- Each agent auto-merges its worktree on completion. If a merge conflict occurs, the changes remain on the worktree branch for manual resolution.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fsource-command-devfleet","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill source-command-devfleet",{"tool":51,"command":52},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill source-command-devfleet",{"tool":54,"command":55},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill source-command-devfleet","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsource-command-devfleet\u002FSKILL.md",true,[],[60,82,113,140,154,170],{"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":34},"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",[],[67,68,69,70,71,72,73,74,75,76,77,78,79,80,81],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","use","context","repo","injection","execution","file",{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":93,"publishedAt":34},"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",[88],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[94,95,96,97,98,99,100,101,102,103,104,105,106,107,76,108,109,110,111,112],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":125,"publishedAt":34},"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",[119,122],{"categoryNo":120,"categoryName":121,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":123,"categoryName":124,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000008","测试与质量",[126,127,128,129,130,131,132,133,134,135,95,136,137,138,139],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":34},"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",[],[142,147,148,149,150,151,152,153],"setup","report","project","installation","project setup","issues","state",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":161,"publishedAt":34},"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",[160],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},[156,162,72,163,164,165,76,166,167,168,169],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":171,"name":147,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":34},"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",[],[147,149,110,176,151,177],"files","interactive"]