[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DC1GWKJSGZ83Z68B8HTQYY":3,"skill-same:01M6DC1GWKJSGZ83Z68B8HTQYY":51},{"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":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":14,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M6DC1GWKJSGZ83Z68B8HTQYY","team-builder",null,"Interactive agent picker for composing and dispatching parallel teams","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\u002Fteam-builder\u002FSKILL.md",[],[19,20,21,22,23,24,25],"team","builder","team builder","teams","parallel","interactive","community","2026-11-10 10:12:30",false,"---\nname: team-builder\ndescription: Interactive agent picker for composing and dispatching parallel teams\norigin: community\n---\n\n# Team Builder\n\nInteractive menu for browsing and composing agent teams on demand. Works with flat or domain-subdirectory agent collections.\n\n## When to Use\n\n- You have multiple agent personas (markdown files) and want to pick which ones to use for a task\n- You want to compose an ad-hoc team from different domains (e.g., Security + SEO + Architecture)\n- You want to browse what agents are available before deciding\n\n## Prerequisites\n\nAgent files must be markdown files containing a persona prompt (identity, rules, workflow, deliverables). The first `# Heading` is used as the agent name and the first paragraph as the description.\n\nBoth flat and subdirectory layouts are supported:\n\n**Subdirectory layout** — domain is inferred from the folder name:\n\n```\nagents\u002F\n├── engineering\u002F\n│   ├── security-engineer.md\n│   └── software-architect.md\n├── marketing\u002F\n│   └── seo-specialist.md\n└── sales\u002F\n    └── discovery-coach.md\n```\n\n**Flat layout** — domain inferred from shared filename prefixes. A prefix counts as a domain when 2+ files share it. Files with unique prefixes go to \"General\". Note: the algorithm splits at the first `-`, so multi-word domains (e.g., `product-management`) should use the subdirectory layout instead:\n\n```\nagents\u002F\n├── engineering-security-engineer.md\n├── engineering-software-architect.md\n├── marketing-seo-specialist.md\n├── marketing-content-strategist.md\n├── sales-discovery-coach.md\n└── sales-outbound-strategist.md\n```\n\n## Configuration\n\nAgent directories are probed in order and results are merged:\n\n1. `.\u002Fagents\u002F**\u002F*.md` + `.\u002Fagents\u002F*.md` — project-local agents (both depths)\n2. `~\u002F.claude\u002Fagents\u002F**\u002F*.md` + `~\u002F.claude\u002Fagents\u002F*.md` — global agents (both depths)\n\nResults from all locations are merged and deduplicated by agent name. Project-local agents take precedence over global agents with the same name. A custom path can be used instead if the user specifies one.\n\n## How It Works\n\n### Step 1: Discover Available Agents\n\nGlob agent directories using the probe order above. Exclude README files. For each file found:\n- **Subdirectory layout:** extract the domain from the parent folder name\n- **Flat layout:** collect all filename prefixes (text before the first `-`). A prefix qualifies as a domain only if it appears in 2 or more filenames (e.g., `engineering-security-engineer.md` and `engineering-software-architect.md` both start with `engineering` → Engineering domain). Files with unique prefixes (e.g., `code-reviewer.md`, `tdd-guide.md`) are grouped under \"General\"\n- Extract the agent name from the first `# Heading`. If no heading is found, derive the name from the filename (strip `.md`, replace hyphens with spaces, title-case)\n- Extract a one-line summary from the first paragraph after the heading\n\nIf no agent files are found after probing all locations, inform the user: \"No agent files found. Checked: [list paths probed]. Expected: markdown files in one of those directories.\" Then stop.\n\n### Step 2: Present Domain Menu\n\n```\nAvailable agent domains:\n1. Engineering — Software Architect, Security Engineer\n2. Marketing — SEO Specialist\n3. Sales — Discovery Coach, Outbound Strategist\n\nPick domains or name specific agents (e.g., \"1,3\" or \"security + seo\"):\n```\n\n- Skip domains with zero agents (empty directories)\n- Show agent count per domain\n\n### Step 3: Handle Selection\n\nAccept flexible input:\n- Numbers: \"1,3\" selects all agents from Engineering and Sales\n- Names: \"security + seo\" fuzzy-matches against discovered agents\n- \"all from engineering\" selects every agent in that domain\n\nIf more than 5 agents are selected, list them alphabetically and ask the user to narrow down: \"You selected N agents (max 5). Pick which to keep, or say 'first 5' to use the first five alphabetically.\"\n\nConfirm selection:\n```\nSelected: Security Engineer + SEO Specialist\nWhat should they work on? (describe the task):\n```\n\n### Step 4: Spawn Agents in Parallel\n\n1. Read each selected agent's markdown file\n2. Prompt for the task description if not already provided\n3. Spawn all agents in parallel using the Agent tool:\n   - `subagent_type: \"general-purpose\"`\n   - `prompt: \"{agent file content}\\n\\nTask: {task description}\"`\n   - Each agent runs independently — no inter-agent communication needed\n4. If an agent fails (error, timeout, or empty output), note the failure inline (e.g., \"Security Engineer: failed — [reason]\") and continue with results from agents that succeeded\n\n### Step 5: Synthesize Results\n\nCollect all outputs and present a unified report:\n- Results grouped by agent\n- Synthesis section highlighting:\n  - Agreements across agents\n  - Conflicts or tensions between recommendations\n  - Recommended next steps\n\nIf only 1 agent was selected, skip synthesis and present the output directly.\n\n## Rules\n\n- **Dynamic discovery only.** Never hardcode agent lists. New files in the directory auto-appear in the menu.\n- **Max 5 agents per team.** More than 5 produces diminishing returns and excessive token usage. Enforce at selection time.\n- **Parallel dispatch.** All agents run simultaneously — use the Agent tool's parallel invocation pattern.\n- **Parallel Agent calls, not TeamCreate.** This skill uses parallel Agent tool calls for independent work. TeamCreate (a Claude Code tool for multi-agent dialogue) is only needed when agents must debate or respond to each other.\n\n## Examples\n\n```\nUser: team builder\n\nClaude:\nAvailable agent domains:\n1. Engineering (2) — Software Architect, Security Engineer\n2. Marketing (1) — SEO Specialist\n3. Sales (4) — Discovery Coach, Outbound Strategist, Proposal Strategist, Sales Engineer\n4. Support (1) — Executive Summary\n\nPick domains or name specific agents:\n\nUser: security + seo\n\nClaude:\nSelected: Security Engineer + SEO Specialist\nWhat should they work on?\n\nUser: Review my Next.js e-commerce site before launch\n\n[Both agents spawn in parallel, each applying their specialty to the codebase]\n\nClaude:\n## Security Engineer Findings\n- [findings...]\n\n## SEO Specialist Findings\n- [findings...]\n\n## Synthesis\nBoth agents agree on: [...]\nTension: Security recommends CSP that blocks inline styles, SEO needs inline schema markup. Resolution: [...]\nNext steps: [...]\n```\n","# Team Builder\n\nInteractive menu for browsing and composing agent teams on demand. Works with flat or domain-subdirectory agent collections.\n\n## When to Use\n\n- You have multiple agent personas (markdown files) and want to pick which ones to use for a task\n- You want to compose an ad-hoc team from different domains (e.g., Security + SEO + Architecture)\n- You want to browse what agents are available before deciding\n\n## Prerequisites\n\nAgent files must be markdown files containing a persona prompt (identity, rules, workflow, deliverables). The first `# Heading` is used as the agent name and the first paragraph as the description.\n\nBoth flat and subdirectory layouts are supported:\n\n**Subdirectory layout** — domain is inferred from the folder name:\n\n```\nagents\u002F\n├── engineering\u002F\n│   ├── security-engineer.md\n│   └── software-architect.md\n├── marketing\u002F\n│   └── seo-specialist.md\n└── sales\u002F\n    └── discovery-coach.md\n```\n\n**Flat layout** — domain inferred from shared filename prefixes. A prefix counts as a domain when 2+ files share it. Files with unique prefixes go to \"General\". Note: the algorithm splits at the first `-`, so multi-word domains (e.g., `product-management`) should use the subdirectory layout instead:\n\n```\nagents\u002F\n├── engineering-security-engineer.md\n├── engineering-software-architect.md\n├── marketing-seo-specialist.md\n├── marketing-content-strategist.md\n├── sales-discovery-coach.md\n└── sales-outbound-strategist.md\n```\n\n## Configuration\n\nAgent directories are probed in order and results are merged:\n\n1. `.\u002Fagents\u002F**\u002F*.md` + `.\u002Fagents\u002F*.md` — project-local agents (both depths)\n2. `~\u002F.claude\u002Fagents\u002F**\u002F*.md` + `~\u002F.claude\u002Fagents\u002F*.md` — global agents (both depths)\n\nResults from all locations are merged and deduplicated by agent name. Project-local agents take precedence over global agents with the same name. A custom path can be used instead if the user specifies one.\n\n## How It Works\n\n### Step 1: Discover Available Agents\n\nGlob agent directories using the probe order above. Exclude README files. For each file found:\n- **Subdirectory layout:** extract the domain from the parent folder name\n- **Flat layout:** collect all filename prefixes (text before the first `-`). A prefix qualifies as a domain only if it appears in 2 or more filenames (e.g., `engineering-security-engineer.md` and `engineering-software-architect.md` both start with `engineering` → Engineering domain). Files with unique prefixes (e.g., `code-reviewer.md`, `tdd-guide.md`) are grouped under \"General\"\n- Extract the agent name from the first `# Heading`. If no heading is found, derive the name from the filename (strip `.md`, replace hyphens with spaces, title-case)\n- Extract a one-line summary from the first paragraph after the heading\n\nIf no agent files are found after probing all locations, inform the user: \"No agent files found. Checked: [list paths probed]. Expected: markdown files in one of those directories.\" Then stop.\n\n### Step 2: Present Domain Menu\n\n```\nAvailable agent domains:\n1. Engineering — Software Architect, Security Engineer\n2. Marketing — SEO Specialist\n3. Sales — Discovery Coach, Outbound Strategist\n\nPick domains or name specific agents (e.g., \"1,3\" or \"security + seo\"):\n```\n\n- Skip domains with zero agents (empty directories)\n- Show agent count per domain\n\n### Step 3: Handle Selection\n\nAccept flexible input:\n- Numbers: \"1,3\" selects all agents from Engineering and Sales\n- Names: \"security + seo\" fuzzy-matches against discovered agents\n- \"all from engineering\" selects every agent in that domain\n\nIf more than 5 agents are selected, list them alphabetically and ask the user to narrow down: \"You selected N agents (max 5). Pick which to keep, or say 'first 5' to use the first five alphabetically.\"\n\nConfirm selection:\n```\nSelected: Security Engineer + SEO Specialist\nWhat should they work on? (describe the task):\n```\n\n### Step 4: Spawn Agents in Parallel\n\n1. Read each selected agent's markdown file\n2. Prompt for the task description if not already provided\n3. Spawn all agents in parallel using the Agent tool:\n   - `subagent_type: \"general-purpose\"`\n   - `prompt: \"{agent file content}\\n\\nTask: {task description}\"`\n   - Each agent runs independently — no inter-agent communication needed\n4. If an agent fails (error, timeout, or empty output), note the failure inline (e.g., \"Security Engineer: failed — [reason]\") and continue with results from agents that succeeded\n\n### Step 5: Synthesize Results\n\nCollect all outputs and present a unified report:\n- Results grouped by agent\n- Synthesis section highlighting:\n  - Agreements across agents\n  - Conflicts or tensions between recommendations\n  - Recommended next steps\n\nIf only 1 agent was selected, skip synthesis and present the output directly.\n\n## Rules\n\n- **Dynamic discovery only.** Never hardcode agent lists. New files in the directory auto-appear in the menu.\n- **Max 5 agents per team.** More than 5 produces diminishing returns and excessive token usage. Enforce at selection time.\n- **Parallel dispatch.** All agents run simultaneously — use the Agent tool's parallel invocation pattern.\n- **Parallel Agent calls, not TeamCreate.** This skill uses parallel Agent tool calls for independent work. TeamCreate (a Claude Code tool for multi-agent dialogue) is only needed when agents must debate or respond to each other.\n\n## Examples\n\n```\nUser: team builder\n\nClaude:\nAvailable agent domains:\n1. Engineering (2) — Software Architect, Security Engineer\n2. Marketing (1) — SEO Specialist\n3. Sales (4) — Discovery Coach, Outbound Strategist, Proposal Strategist, Sales Engineer\n4. Support (1) — Executive Summary\n\nPick domains or name specific agents:\n\nUser: security + seo\n\nClaude:\nSelected: Security Engineer + SEO Specialist\nWhat should they work on?\n\nUser: Review my Next.js e-commerce site before launch\n\n[Both agents spawn in parallel, each applying their specialty to the codebase]\n\nClaude:\n## Security Engineer Findings\n- [findings...]\n\n## SEO Specialist Findings\n- [findings...]\n\n## Synthesis\nBoth agents agree on: [...]\nTension: Security recommends CSP that blocks inline styles, SEO needs inline schema markup. Resolution: [...]\nNext steps: [...]\n```\n",{"name":5,"origin":25,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fteam-builder","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill team-builder",{"tool":43,"command":44},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill team-builder",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill team-builder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fteam-builder\u002FSKILL.md",true,[],[52,74,105,132,146,162],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":26},"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",[],[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","use","context","repo","injection","execution","file",{"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":85,"publishedAt":26},"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",[80],{"categoryNo":81,"categoryName":82,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[86,87,88,89,90,91,92,93,94,95,96,97,98,99,68,100,101,102,103,104],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":117,"publishedAt":26},"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",[111,114],{"categoryNo":112,"categoryName":113,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":115,"categoryName":116,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000008","测试与质量",[118,119,120,121,122,123,124,125,126,127,87,128,129,130,131],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":26},"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",[],[134,139,140,141,142,143,144,145],"setup","report","project","installation","project setup","issues","state",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":153,"publishedAt":26},"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",[152],{"categoryNo":81,"categoryName":82,"taxonomyType":83,"taxonomyTypeDesc":84},[148,154,64,155,156,157,68,158,159,160,161],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":163,"name":139,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":26},"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",[],[139,141,102,168,143,24],"files"]