[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C1DVWC136WMYK69R2GG0P9":3,"skill-same:01M6C1DVWC136WMYK69R2GG0P9":73},{"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":28,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6C1DVWC136WMYK69R2GG0P9","team",null,"Orchestrate multi-agent teams across AIWG providers natively on Claude Code or emulated via Mission Control elsewhere","jmagly\u002Faiwg","jmagly","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1159087?v=4","01M6C10AK8N2WCSQN11FYGTJWN","Joseph Magly","01M6C10AQ8A2RMED1Y1BSVY7NF",229,"MIT","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Faddons\u002Faiwg-utils\u002Fskills\u002Fteam\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[5,29,30,31,32,33,34,35,36,37,38,39,40],"teams","code","orchestrate","Providers","multi-agent","mission control","agent teams","across","control","via","multi","mission","2026-11-10 10:12:30",false,"---\nnamespace: aiwg\nname: team\nplatforms: [all]\ndescription: Orchestrate multi-agent teams across AIWG providers natively on Claude Code or emulated via Mission Control elsewhere\n---\n\n# team\n\nYou orchestrate multi-agent teams across all AIWG providers. On Claude Code, teams run natively via the Task tool. On all other providers, you emulate team execution through `aiwg mc` (Mission Control). Team definitions live in `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fteams\u002F`.\n\n## Triggers\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"spin up a team\" → `team run` with named team\n- \"who's on the security review team\" → `team info`\n- \"what teams do I have\" → `team list`\n- \"run the greenfield team on this task\" → `team run greenfield \"\u003Ctask>\"`\n\n## Trigger Patterns Reference\n\n| Pattern | Example | Action |\n|---------|---------|--------|\n| Run a named team | \"run the sdlc-review team on the SAD\" | `aiwg team run sdlc-review \"\u003Ctask>\"` |\n| List available teams | \"what teams are available\" | `aiwg team list` |\n| Inspect team composition | \"who is on the security review team\" | `aiwg team info security-review` |\n| Task-inferred team | \"review this architecture for security\" | `aiwg team run security-review \"\u003Ctask>\"` |\n\n## Behavior\n\nWhen triggered:\n\n1. **Parse the subcommand**:\n   - `run \u003Cteam-name> \"\u003Ctask>\"` — execute team against a task\n   - `list` — list all available teams from the manifest\n   - `info \u003Cteam-name>` — show team composition and use cases\n\n2. **Detect provider**:\n   - Claude Code (`CLAUDE_CODE_VERSION` set) → native Task-tool dispatch\n   - All other providers → emulate via `aiwg mc dispatch`\n\n3. **Run the appropriate command**:\n\n   ```bash\n   # Run a team on a task\n   aiwg team run sdlc-review \"Review the SAD at .aiwg\u002Farchitecture\u002Fsad.md\"\n\n   # Run with provider override\n   aiwg team run security-review \"Audit auth module\" --provider cursor\n\n   # List all teams\n   aiwg team list\n\n   # Inspect a team\n   aiwg team info greenfield\n   ```\n\n4. **Report execution progress**:\n   - Native (Claude Code): reports inline as agents complete\n   - Emulated (mc): reports mission IDs and tracks via `aiwg mc status`\n\n## Team Definitions\n\nTeams are defined as JSON files in `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fteams\u002F`. Built-in teams:\n\n| Team | Use Cases |\n|------|-----------|\n| `sdlc-review` | Architecture, requirements, and test review |\n| `security-review` | Threat modeling, security audit, privacy review |\n| `api-development` | API design, documentation, test generation |\n| `full-stack` | Feature implementation across layers |\n| `greenfield` | New project inception and architecture |\n| `maintenance` | Refactoring, debt reduction, upgrades |\n| `migration` | Database or platform migration planning |\n\n## Team Definition Format\n\n```yaml\n# .aiwg\u002Fteams\u002Fmy-team.yaml  (project-local override)\nname: Custom Review Team\nslug: custom-review\ndescription: Tailored review for domain-specific concerns\nagents:\n  - agent: security-architect\n    role: lead\n    responsibilities:\n      - Security threat model\n      - Auth design review\n  - agent: test-architect\n    role: contributor\n    responsibilities:\n      - Test coverage gaps\n      - Integration risks\n  - agent: technical-writer\n    role: reviewer\n    responsibilities:\n      - Clarity and consistency\ndispatch: parallel\n```\n\n## Execution Modes\n\n### Native (Claude Code)\n\nAgents launch as parallel Task tool calls in a single message. Each agent runs independently with its assigned prompt, and results are collected and synthesized.\n\n### Emulated (All Other Providers)\n\n```bash\n# Steward emulates by dispatching via Mission Control\nSESSION=$(aiwg mc start --name \"team-run-$(date +%s)\")\naiwg mc dispatch $SESSION \"security-architect: \u003Ctask>\" --completion \"Review complete\"\naiwg mc dispatch $SESSION \"test-architect: \u003Ctask>\" --completion \"Review complete\"\naiwg mc watch $SESSION\n```\n\n## Examples\n\n### Example 1: Run a review team\n\n**User**: \"Run the security review team on the auth module\"\n\n**Extraction**: `team run security-review` on the auth module\n\n**Action**:\n```bash\naiwg team run security-review \"Review src\u002Fauth\u002F for security vulnerabilities, focusing on token handling and session management\"\n```\n\n**Response** (Claude Code, native):\n```\nLaunching security-review team (3 agents, parallel)...\n  security-architect: reviewing...\n  security-auditor:   reviewing...\n  privacy-officer:    reviewing...\n\nResults collected. 2 critical findings, 4 recommendations.\nFull report: .aiwg\u002Fworking\u002Fteam-runs\u002Fsecurity-review-20260401-143022.md\n```\n\n### Example 2: List teams\n\n**User**: \"What teams do I have available?\"\n\n**Action**:\n```bash\naiwg team list\n```\n\n**Response**:\n```\nAvailable teams (7):\n  api-development   API design, documentation, test generation\n  full-stack        Feature implementation across layers\n  greenfield        New project inception and architecture\n  maintenance       Refactoring, debt reduction, upgrades\n  migration         Database or platform migration planning\n  sdlc-review       Architecture, requirements, and test review\n  security-review   Threat modeling, security audit, privacy review\n```\n\n### Example 3: Inspect team composition\n\n**User**: \"Who is on the sdlc-review team?\"\n\n**Action**:\n```bash\naiwg team info sdlc-review\n```\n\n**Response**:\n```\nTeam: sdlc-review\nDescription: Architecture, requirements, and test review\nDispatch: parallel\n\nAgents:\n  architecture-designer  [lead]        Architecture quality and pattern review\n  requirements-analyst   [contributor] Requirements traceability and completeness\n  test-architect         [contributor] Testability and coverage gaps\n  technical-writer       [reviewer]    Clarity and documentation quality\n\nUse cases:\n  - SAD review before Architecture Baseline Milestone\n  - Elaboration phase gate check\n  - ADR peer review\n```\n\n## Clarification Prompts\n\nIf the user names a task without a team:\n\n- \"Which team should I run? Available: sdlc-review, security-review, api-development, full-stack, greenfield, maintenance, migration\"\n\nIf the team name is ambiguous:\n\n- \"Did you mean `security-review` or `sdlc-review`?\"\n\n## References\n\n- @$AIWG_ROOT\u002Fsrc\u002Fcli\u002Fhandlers\u002Fteam.ts — Team command handler\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fteams\u002F — Built-in team definitions\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fteams\u002Fmanifest.json — Team manifest\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fteams\u002Fschema.json — Team definition schema\n- @$AIWG_ROOT\u002Fdocs\u002Fcli-reference.md — CLI reference\n","# team\n\nYou orchestrate multi-agent teams across all AIWG providers. On Claude Code, teams run natively via the Task tool. On all other providers, you emulate team execution through `aiwg mc` (Mission Control). Team definitions live in `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fteams\u002F`.\n\n## Triggers\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"spin up a team\" → `team run` with named team\n- \"who's on the security review team\" → `team info`\n- \"what teams do I have\" → `team list`\n- \"run the greenfield team on this task\" → `team run greenfield \"\u003Ctask>\"`\n\n## Trigger Patterns Reference\n\n| Pattern | Example | Action |\n|---------|---------|--------|\n| Run a named team | \"run the sdlc-review team on the SAD\" | `aiwg team run sdlc-review \"\u003Ctask>\"` |\n| List available teams | \"what teams are available\" | `aiwg team list` |\n| Inspect team composition | \"who is on the security review team\" | `aiwg team info security-review` |\n| Task-inferred team | \"review this architecture for security\" | `aiwg team run security-review \"\u003Ctask>\"` |\n\n## Behavior\n\nWhen triggered:\n\n1. **Parse the subcommand**:\n   - `run \u003Cteam-name> \"\u003Ctask>\"` — execute team against a task\n   - `list` — list all available teams from the manifest\n   - `info \u003Cteam-name>` — show team composition and use cases\n\n2. **Detect provider**:\n   - Claude Code (`CLAUDE_CODE_VERSION` set) → native Task-tool dispatch\n   - All other providers → emulate via `aiwg mc dispatch`\n\n3. **Run the appropriate command**:\n\n   ```bash\n   # Run a team on a task\n   aiwg team run sdlc-review \"Review the SAD at .aiwg\u002Farchitecture\u002Fsad.md\"\n\n   # Run with provider override\n   aiwg team run security-review \"Audit auth module\" --provider cursor\n\n   # List all teams\n   aiwg team list\n\n   # Inspect a team\n   aiwg team info greenfield\n   ```\n\n4. **Report execution progress**:\n   - Native (Claude Code): reports inline as agents complete\n   - Emulated (mc): reports mission IDs and tracks via `aiwg mc status`\n\n## Team Definitions\n\nTeams are defined as JSON files in `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fteams\u002F`. Built-in teams:\n\n| Team | Use Cases |\n|------|-----------|\n| `sdlc-review` | Architecture, requirements, and test review |\n| `security-review` | Threat modeling, security audit, privacy review |\n| `api-development` | API design, documentation, test generation |\n| `full-stack` | Feature implementation across layers |\n| `greenfield` | New project inception and architecture |\n| `maintenance` | Refactoring, debt reduction, upgrades |\n| `migration` | Database or platform migration planning |\n\n## Team Definition Format\n\n```yaml\n# .aiwg\u002Fteams\u002Fmy-team.yaml  (project-local override)\nname: Custom Review Team\nslug: custom-review\ndescription: Tailored review for domain-specific concerns\nagents:\n  - agent: security-architect\n    role: lead\n    responsibilities:\n      - Security threat model\n      - Auth design review\n  - agent: test-architect\n    role: contributor\n    responsibilities:\n      - Test coverage gaps\n      - Integration risks\n  - agent: technical-writer\n    role: reviewer\n    responsibilities:\n      - Clarity and consistency\ndispatch: parallel\n```\n\n## Execution Modes\n\n### Native (Claude Code)\n\nAgents launch as parallel Task tool calls in a single message. Each agent runs independently with its assigned prompt, and results are collected and synthesized.\n\n### Emulated (All Other Providers)\n\n```bash\n# Steward emulates by dispatching via Mission Control\nSESSION=$(aiwg mc start --name \"team-run-$(date +%s)\")\naiwg mc dispatch $SESSION \"security-architect: \u003Ctask>\" --completion \"Review complete\"\naiwg mc dispatch $SESSION \"test-architect: \u003Ctask>\" --completion \"Review complete\"\naiwg mc watch $SESSION\n```\n\n## Examples\n\n### Example 1: Run a review team\n\n**User**: \"Run the security review team on the auth module\"\n\n**Extraction**: `team run security-review` on the auth module\n\n**Action**:\n```bash\naiwg team run security-review \"Review src\u002Fauth\u002F for security vulnerabilities, focusing on token handling and session management\"\n```\n\n**Response** (Claude Code, native):\n```\nLaunching security-review team (3 agents, parallel)...\n  security-architect: reviewing...\n  security-auditor:   reviewing...\n  privacy-officer:    reviewing...\n\nResults collected. 2 critical findings, 4 recommendations.\nFull report: .aiwg\u002Fworking\u002Fteam-runs\u002Fsecurity-review-20260401-143022.md\n```\n\n### Example 2: List teams\n\n**User**: \"What teams do I have available?\"\n\n**Action**:\n```bash\naiwg team list\n```\n\n**Response**:\n```\nAvailable teams (7):\n  api-development   API design, documentation, test generation\n  full-stack        Feature implementation across layers\n  greenfield        New project inception and architecture\n  maintenance       Refactoring, debt reduction, upgrades\n  migration         Database or platform migration planning\n  sdlc-review       Architecture, requirements, and test review\n  security-review   Threat modeling, security audit, privacy review\n```\n\n### Example 3: Inspect team composition\n\n**User**: \"Who is on the sdlc-review team?\"\n\n**Action**:\n```bash\naiwg team info sdlc-review\n```\n\n**Response**:\n```\nTeam: sdlc-review\nDescription: Architecture, requirements, and test review\nDispatch: parallel\n\nAgents:\n  architecture-designer  [lead]        Architecture quality and pattern review\n  requirements-analyst   [contributor] Requirements traceability and completeness\n  test-architect         [contributor] Testability and coverage gaps\n  technical-writer       [reviewer]    Clarity and documentation quality\n\nUse cases:\n  - SAD review before Architecture Baseline Milestone\n  - Elaboration phase gate check\n  - ADR peer review\n```\n\n## Clarification Prompts\n\nIf the user names a task without a team:\n\n- \"Which team should I run? Available: sdlc-review, security-review, api-development, full-stack, greenfield, maintenance, migration\"\n\nIf the team name is ambiguous:\n\n- \"Did you mean `security-review` or `sdlc-review`?\"\n\n## References\n\n- @$AIWG_ROOT\u002Fsrc\u002Fcli\u002Fhandlers\u002Fteam.ts — Team command handler\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fteams\u002F — Built-in team definitions\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fteams\u002Fmanifest.json — Team manifest\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fteams\u002Fschema.json — Team definition schema\n- @$AIWG_ROOT\u002Fdocs\u002Fcli-reference.md — CLI reference\n",{"name":5,"namespace":46,"platforms":47,"description":7},"aiwg",[48],"all","main","6754967c344ccb087a8de06972f55a41067b291b","agentic\u002Fcode\u002Faddons\u002Faiwg-utils\u002Fskills\u002Fteam",36,"https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg","https:\u002F\u002Faiwg.io","https:\u002F\u002Fgithub.com\u002Fjmagly","https:\u002F\u002Fintegrolabs.io","ml\u002Fai, industrial automation, safety\u002Fsecurity, ssi\r\n\r\nmagly.net\r\nintegrolabs.io\r\naiwg.io\r\nfortemi.com\r\npagenary.com\r\nbytecask.com","2026-11-12 21:57:33",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add jmagly\u002Faiwg --skill team",{"tool":65,"command":66},"bunx","bunx skills add jmagly\u002Faiwg --skill team",{"tool":68,"command":69},"pnpm","pnpm dlx skills add jmagly\u002Faiwg --skill team","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Faddons\u002Faiwg-utils\u002Fskills\u002Fteam\u002FSKILL.md",true,[],[74,102,126,132,139,153],{"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":81,"publishedAt":41},"01M70QA0BSYJ49EES9V4RE8QH1","host-hardening","Read-only system hardening baseline and plan-first host hardening recommendations for SSH, Docker bind addresses, firewall persistence, datastores, exporters and audit retention.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[80],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101],"host","host hardening","hardening","read","re","recommendations","remediation","plan","port","verification","Bash","access","only","retention","audit","never","firewall","bind","secrets","request",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":112,"publishedAt":41},"01M70PNT2Z4HMZPRBTAF6073NN","exposure-analysis","Read-only firewall analysis and effective host exposure reconstruction for Docker published ports, UFW bypass, stale rules, CDN scope, IPv6 asymmetry and external probe allowlists.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fforensics\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[108,111],{"categoryNo":109,"categoryName":110,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[113,114,115,85,116,90,117,118,92,119,82,120,94,121,122,97,98,123,124,125],"exposure analysis","analysis","unknown","credentials","collection","ufw","ports","internet","local","scope","reconstruction","operator","write",{"skillNo":127,"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":128,"categories":129,"keywords":131,"publishedAt":41},"01M70P8QATMPKA78E4FT5D2TNA","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[130],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[84,82,83,93,85,101,88,87,96,89,90,91,92,100,94,95,86,97,98,99],{"skillNo":133,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":138,"publishedAt":41},"01M70NMPVJ5H0JH131P60FW4R8","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fforensics-complete\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[136,137],{"categoryNo":109,"categoryName":110,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[114,113,97,116,90,117,92,115,82,120,94,121,122,85,98,119,118,123,124,125],{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":146,"publishedAt":41},"01M6CB4DDR0B4NNCFK7ZK7449H","fixture-skill","Exercise rule delivery.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Frule-delivery\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[145],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[147,148,149,150,151,152],"fixture skill","fixture","rule","delivery","true","exercise",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":160,"publishedAt":41},"01M6CB4AVK1W76MFMPP0JP32CJ","pi-local","Pi-local duplicate-precedence fixture.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fproviders\u002Fpi\u002Fproject\u002F.pi\u002Fskills\u002Fpi-local\u002FSKILL.md",[159],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[161,162,121,163,148],"pi","pi local","duplicate"]