[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71M5ZC93A644C54C65K2AVB":3,"skill-same:01M71M5ZC93A644C54C65K2AVB":87},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":64,"commitSha":65,"skillDirectory":66,"forksCount":67,"repositoryHtmlUrl":68,"repositoryHomepageUrl":69,"ownerHtmlUrl":70,"ownerBlogUrl":71,"ownerDescription":6,"updatedAt":72,"install":73,"resources":86},"01M71M5ZC93A644C54C65K2AVB","specialagent",null,"Find the single best specialized agent for a task — the [PICK] line or the shared pick index (mcp__monomind__pick \u002F monomind pick), with a two-stage domain→agent fallback over the installed agents","monoes\u002Fmonomind","monoes","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F276744696?v=4","01M71KWF37AJ2NJBP3KWBVSDGT","01M71KWF4CSF8ADH0M6HA09VD2",23,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspecialagent\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"MCP","line","find","with","two","specialized","task","Bash","stage","use","assign","single","handle","pick","swarm","for","domain","which","shared","2026-11-10 10:56:23",false,"---\nname: specialagent\ndescription: Find the single best specialized agent for a task — the [PICK] line or the shared pick index (mcp__monomind__pick \u002F monomind pick), with a two-stage domain→agent fallback over the installed agents\nversion: 2.0.0\ntriggers:\n  - \u002Fspecialagent\n  - find best agent\n  - which agent should i use\n  - best agent for\n  - recommend an agent\n  - pick an agent\n  - what agent\n  - who should handle this\n  - which specialist\n  - what specialist\n  - agent for this task\n  - assign an agent\n  - which swarm agent\ntools:\n  - Bash\npick: low\n---\n\n# \u002Fspecialagent — Best Agent for a Task\n\nFinds the best installed agent for a task. Never recommend from memory or from a hardcoded roster: the agent set differs per install, and a `subagent_type` that is not installed fails at spawn time.\n\n## Step 1: Use the pick index\n\nIn this order, stop at the first that answers:\n\n1. **`[PICK]` line** — if the prompt carries `[PICK] agent: \u003Cname> · skill: \u003Cinvoke>`, recommend that agent unless it is clearly wrong for the task.\n2. **`mcp__monomind__pick({ task: \"\u003Ctask>\", kind: \"agents\", top: 5 })`** — choose the best fit among `agents.ranked[]` (prefer the top entry unless another is clearly more specific). Each `name` is a spawnable `subagent_type`.\n3. **Local CLI** — `monomind pick -t \"\u003Ctask>\" --top 5 --json | jq -r '.agents.ranked[].name'` (local binary only, never npx; see `mastermind-agent-select\u002FSKILL.md` for the version-checked `mmpick` helper).\n\n## Step 2 (fallback): Two-stage domain → agent selection\n\nOnly when Step 1 returned nothing. Only names are passed at each stage — no descriptions, no keyword dumps.\n\n```\nStage 1: Give LLM the category names → LLM picks the best category\nStage 2: Give LLM the agent names installed in that category → LLM picks the best agent\n```\n\nCategories are the `.claude\u002Fagents\u002F` folder names: `architecture consensus core design engineering github goal marketing monoswarm optimization specialists specialized templates testing`.\n\nList the installed agent names in a category from the registry (or the definitions on disk):\n\n```bash\nCAT=\"engineering\"\njq -r --arg c \"$CAT\" '.agents[] | select(.category == $c and .deprecated != true) | .name' .monomind\u002Fregistry.json 2>\u002Fdev\u002Fnull \\\n  || grep -h -m1 \"^name:\" packages\u002F@monomind\u002Fcli\u002F.claude\u002Fagents\u002F$CAT\u002F*.md .claude\u002Fagents\u002F$CAT\u002F*.md 2>\u002Fdev\u002Fnull | sed 's\u002F^name: *\u002F\u002F'\n```\n\n**Stage 1 prompt to yourself:**\n> \"Given the task: `\u003Ctask>` — which single category from this list best fits: `\u003Ccategory names>`? Answer with just the category name.\"\n\n**Stage 2 prompt to yourself:**\n> \"Given the task: `\u003Ctask>` — which single agent from this category is the best fit: `\u003Cagent names listed above>`? Answer with just the agent name.\"\n\nIf both stages come up empty, fall back to a core agent: `coder`, `reviewer`, `tester`, `researcher`, `planner`.\n\n## Slug Mapping\n\nThe `subagent_type` is the agent's frontmatter `name:` — what the pick index returns as `name`, and what the registry lists as `.name`.\n\n## Output Format\n\n```\nTASK: \u003Cone-line task summary>\n\nPICKED BY: \u003C[PICK] line | mcp__monomind__pick | monomind pick | category fallback: \u003Ccategory>>\n\nRECOMMENDED AGENT: \u003CAgent Name>\nInvoke: Task({ subagent_type: \"\u003Cagent name>\", prompt: \"...\" })\n```\n\nThen ask: \"Should I spawn this agent now?\"\n\n## Rules\n\n1. Prefer the pick index; in the fallback, only pass names at each stage — no descriptions, no keyword dumps, no scoring tables\n2. Recommend exactly one agent, and only a name that is installed\n3. For tasks that clearly need a specialized tool (e.g. accessibility audits → Accessibility Auditor, not tester), prefer the more specific agent\n4. Never recommend a generic role (coder, tester) when a specialized agent in the right domain exists\n","# \u002Fspecialagent — Best Agent for a Task\n\nFinds the best installed agent for a task. Never recommend from memory or from a hardcoded roster: the agent set differs per install, and a `subagent_type` that is not installed fails at spawn time.\n\n## Step 1: Use the pick index\n\nIn this order, stop at the first that answers:\n\n1. **`[PICK]` line** — if the prompt carries `[PICK] agent: \u003Cname> · skill: \u003Cinvoke>`, recommend that agent unless it is clearly wrong for the task.\n2. **`mcp__monomind__pick({ task: \"\u003Ctask>\", kind: \"agents\", top: 5 })`** — choose the best fit among `agents.ranked[]` (prefer the top entry unless another is clearly more specific). Each `name` is a spawnable `subagent_type`.\n3. **Local CLI** — `monomind pick -t \"\u003Ctask>\" --top 5 --json | jq -r '.agents.ranked[].name'` (local binary only, never npx; see `mastermind-agent-select\u002FSKILL.md` for the version-checked `mmpick` helper).\n\n## Step 2 (fallback): Two-stage domain → agent selection\n\nOnly when Step 1 returned nothing. Only names are passed at each stage — no descriptions, no keyword dumps.\n\n```\nStage 1: Give LLM the category names → LLM picks the best category\nStage 2: Give LLM the agent names installed in that category → LLM picks the best agent\n```\n\nCategories are the `.claude\u002Fagents\u002F` folder names: `architecture consensus core design engineering github goal marketing monoswarm optimization specialists specialized templates testing`.\n\nList the installed agent names in a category from the registry (or the definitions on disk):\n\n```bash\nCAT=\"engineering\"\njq -r --arg c \"$CAT\" '.agents[] | select(.category == $c and .deprecated != true) | .name' .monomind\u002Fregistry.json 2>\u002Fdev\u002Fnull \\\n  || grep -h -m1 \"^name:\" packages\u002F@monomind\u002Fcli\u002F.claude\u002Fagents\u002F$CAT\u002F*.md .claude\u002Fagents\u002F$CAT\u002F*.md 2>\u002Fdev\u002Fnull | sed 's\u002F^name: *\u002F\u002F'\n```\n\n**Stage 1 prompt to yourself:**\n> \"Given the task: `\u003Ctask>` — which single category from this list best fits: `\u003Ccategory names>`? Answer with just the category name.\"\n\n**Stage 2 prompt to yourself:**\n> \"Given the task: `\u003Ctask>` — which single agent from this category is the best fit: `\u003Cagent names listed above>`? Answer with just the agent name.\"\n\nIf both stages come up empty, fall back to a core agent: `coder`, `reviewer`, `tester`, `researcher`, `planner`.\n\n## Slug Mapping\n\nThe `subagent_type` is the agent's frontmatter `name:` — what the pick index returns as `name`, and what the registry lists as `.name`.\n\n## Output Format\n\n```\nTASK: \u003Cone-line task summary>\n\nPICKED BY: \u003C[PICK] line | mcp__monomind__pick | monomind pick | category fallback: \u003Ccategory>>\n\nRECOMMENDED AGENT: \u003CAgent Name>\nInvoke: Task({ subagent_type: \"\u003Cagent name>\", prompt: \"...\" })\n```\n\nThen ask: \"Should I spawn this agent now?\"\n\n## Rules\n\n1. Prefer the pick index; in the fallback, only pass names at each stage — no descriptions, no keyword dumps, no scoring tables\n2. Recommend exactly one agent, and only a name that is installed\n3. For tasks that clearly need a specialized tool (e.g. accessibility audits → Accessibility Auditor, not tester), prefer the more specific agent\n4. Never recommend a generic role (coder, tester) when a specialized agent in the right domain exists\n",{"name":5,"pick":47,"tools":48,"version":49,"triggers":50,"description":7},"low",[30],"2.0.0",[51,52,53,54,55,56,57,58,59,60,61,62,63],"\u002Fspecialagent","find best agent","which agent should i use","best agent for","recommend an agent","pick an agent","what agent","who should handle this","which specialist","what specialist","agent for this task","assign an agent","which swarm agent","main","f7cd4595d0f8959822163e14f9787117765c931a",".claude\u002Fskills\u002Fspecialagent",2,"https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind","https:\u002F\u002Fmonoes.github.io\u002Fmonomind\u002F","https:\u002F\u002Fgithub.com\u002Fmonoes","https:\u002F\u002Fmonoes.me","2026-11-10 01:53:48",{"source":8,"skillName":5,"commands":74,"prompt":84,"zipAvailable":85},[75,78,81],{"tool":76,"command":77},"npx","npx skills add monoes\u002Fmonomind --skill specialagent",{"tool":79,"command":80},"bunx","bunx skills add monoes\u002Fmonomind --skill specialagent",{"tool":82,"command":83},"pnpm","pnpm dlx skills add monoes\u002Fmonomind --skill specialagent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspecialagent\u002FSKILL.md",true,[],[88,116,151,177,200,225],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":115},"01M71PB3SHWKMNJM6MD65VX8D6","zk-steward","Org role guidance for a ZK steward: engineer zero-knowledge proof systems with circuit design, SNARK vs STARK choice and security review. This is zero-knowledge cryptography, not Zettelkasten note-taking.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fzk-steward\u002FSKILL.md",[],[95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114],"zk","zk steward","steward","zero-knowledge","engineer","choice","design","knowledge","impact","query","snark","review","monomind","security review","stark","zettelkasten","cryptography","security","org","blockchain","2026-11-10 13:02:02",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":120,"licenseFileUrl":121,"sourceHtmlUrl":122,"categories":123,"keywords":132,"publishedAt":115},"01M71PB18SDG28WBKPKJNB814K","writing-plans","Use when you have a spec or requirements for a multi-step coding task and must write an implementation plan before touching code. Produces bite-sized TDD tasks with exact file paths, code and commands for an engineer with zero context.","MIT","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwriting-plans\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwriting-plans\u002FSKILL.md",[124,127],{"categoryNo":125,"categoryName":126,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":128,"categoryName":129,"taxonomyType":130,"taxonomyTypeDesc":131},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[133,134,135,99,136,137,138,139,104,140,141,142,143,144,145,146,147,148,149,150],"writing","writing plans","plans","superpowers","implementation plan","when","you","code","tasks","plan","product","write","commands","paths","suggest","coding","context","ZeRO",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":155,"sourceHtmlUrl":156,"categories":157,"keywords":161,"publishedAt":115},"01M71PAXFM488X9ARXK0T04TF5","write-spec","Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request into a structured document, scoping a feature with goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into a phased spec.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwrite-spec\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwrite-spec\u002FSKILL.md",[158],{"categoryNo":159,"categoryName":160,"taxonomyType":130,"taxonomyTypeDesc":131},"01JBSEEDCAT000000000000031","产品经理",[144,162,163,164,165,102,166,138,167,168,169,143,170,171,172,173,174,175,32,176],"write spec","spec","user request","problem","acceptance","ask","vague","work","request","scoping","idea","metrics","feature","problem statement","document",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":181,"sourceHtmlUrl":182,"categories":183,"keywords":187,"publishedAt":115},"01M71PASSZY800C0RPEARBS918","write-query","Write optimized SQL for your dialect with best practices. Use when translating a natural-language data need into SQL, building a multi-CTE query with joins and aggregations, optimizing a query against a large partitioned table, or getting dialect-specific syntax for Snowflake, BigQuery, Postgres, etc.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwrite-query\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwrite-query\u002FSKILL.md",[184],{"categoryNo":185,"categoryName":186,"taxonomyType":130,"taxonomyTypeDesc":131},"01JBSEEDCAT000000000000033","数据分析师",[104,144,188,189,38,190,102,32,138,191,192,26,193,169,194,195,196,197,198,199],"write query","postgres","snowflake","best practices","natural-language","multi","github","sql","https","syntax","plugins","data",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":210,"publishedAt":115},"01M71PAPTX0T3PF6ETFVR96SJJ","workflow-automation","Org role guidance for workflow automation: build and maintain CI\u002FCD definitions in GitHub Actions or equivalent: triggers, jobs, matrices, caching. Covers path filters, dependency caching, parallel jobs, timeouts and fail-fast ordering.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fworkflow-automation\u002FSKILL.md",[206,209],{"categoryNo":207,"categoryName":208,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[211,212,213,214,38,215,216,217,218,103,219,220,221,104,107,194,222,223,224,196],"Workflow Automation","automation","workflow","parallel","actions","ci","triggers","github actions","maintain","filters","caching","build","dependency","devops",{"skillNo":226,"name":227,"nameZh":6,"description":228,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":229,"categories":230,"keywords":232,"publishedAt":115},"01M71PAM19Z1XTV9NPCFSE2MY8","workflow-architect","Org role guidance for a workflow architect: map full workflow trees for systems, user journeys and agents, covering every branch and failure. Covers discovering workflows from code, handoff contracts, timeouts, recovery paths and observable state.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fworkflow-architect\u002FSKILL.md",[231],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[213,233,234,235,236,237,238,38,239,240,140,241,242,243,107,194,244,245,196,246],"workflow architect","architect","trees","user journeys","branch","planning","map","workflows","architecture","state","leadership","recovery","operations","systems"]