[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CAR953HFW3069060C7GRFE":3,"skill-same:01M6CAR953HFW3069060C7GRFE":66},{"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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":47,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M6CAR953HFW3069060C7GRFE","add-agent",null,"Scaffold a new agent definition file inside an existing addon or framework","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\u002Fplugins\u002Futils\u002Fskills\u002Fadd-agent\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],"add agent","add","scaffold","framework","file","new agent","agent definition","Existing","definition","new","2026-11-10 10:12:30",false,"---\nnamespace: aiwg\nname: add-agent\nplatforms: [all]\ndescription: Scaffold a new agent definition file inside an existing addon or framework\n---\n\n# Add Agent\n\nScaffold a new agent definition file inside an existing addon or framework.\n\n## Triggers\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"I need a new agent\" → scaffold agent in specified target\n- \"build me an agent\" → scaffold agent with interactive guidance\n- \"write an agent for X\" → scaffold agent named after the described role\n- \"agent for \u003Crole>\" → derive name from role, prompt for target\n\n## Trigger Patterns Reference\n\n| Pattern | Example | Action |\n|---------|---------|--------|\n| Named add | \"add agent security-auditor --to sdlc-complete\" | Scaffold directly |\n| Role description | \"create an agent that reviews PRs\" | Derive name, scaffold |\n| Interactive | \"add agent --interactive\" | Guided mode, ask for name\u002Ftarget\u002Ftemplate |\n| Target omitted | \"add agent code-reviewer\" | Ask which addon or framework |\n\n## Process\n\n### 1. Parse Arguments\n\nExtract from `$ARGUMENTS`:\n- `\u003Cname>` — kebab-case agent name (required)\n- `--to \u003Ctarget>` — addon or framework directory name (required)\n- `--template \u003Ctype>` — one of `simple` (default), `complex`, `orchestrator`, `validator`\n- `--interactive` — enable guided design questions\n\nIf either `\u003Cname>` or `--to` is missing, ask before proceeding.\n\n### 2. Validate Target\n\nConfirm the target addon or framework exists:\n\n```bash\n# Check addons\nls agentic\u002Fcode\u002Faddons\u002F\u003Ctarget>\u002F\n\n# Check frameworks\nls agentic\u002Fcode\u002Fframeworks\u002F\u003Ctarget>\u002F\n```\n\nIf not found, report available targets and stop.\n\n### 3. Interactive Design (if --interactive)\n\nAsk the following before generating:\n\n1. **Role**: What is this agent's primary role?\n2. **Expertise**: What domains or technologies does it specialize in?\n3. **Responsibilities**: What are its 3-5 key responsibilities?\n4. **Tools needed**: Which tools does it require? (Read, Write, Bash, Grep, WebFetch, Task)\n5. **Model tier**: haiku (fast\u002Futility), sonnet (balanced), opus (reasoning-heavy)\n6. **Output format**: What structured output should it produce?\n\n### 4. Select Template\n\n| Template | Use When | Default Model | Tools |\n|----------|----------|---------------|-------|\n| `simple` | Single-purpose utility agent | haiku | Read, Write |\n| `complex` | Domain expert, reviewer, analyst | sonnet | Read, Write, Grep |\n| `orchestrator` | Coordinates other agents | opus | Task |\n| `validator` | Read-only quality\u002Fcompliance gate | haiku | Read, Grep |\n\n### 5. Run Scaffolding\n\n```bash\naiwg add-agent \u003Cname> --to \u003Ctarget> --template \u003Ctype>\n```\n\nThis generates `\u003Ctarget>\u002Fagents\u002F\u003Cname>.md` with the appropriate frontmatter and section stubs.\n\n### 6. Customize the Generated File\n\nThe generated agent file requires population of these sections:\n\n```markdown\n---\nname: \u003Cname>\ndescription: \u003Cone-sentence purpose>\nmodel: \u003Cclaude-haiku-4-5|claude-sonnet-5|claude-opus-5>  # Pin specific variant; bare aliases (`sonnet`) inherit the parent session's 1M-context attributes and hit the usage-credit gate on subagent dispatch. See #1442.\ntools: \u003Ccomma-separated tool list>\ncategory: \u003Cphase or domain>\n---\n\n# Agent Title\n\n[Role description]\n\n## Expertise\n\n[Domain knowledge and skills]\n\n## Responsibilities\n\n[Numbered list of what this agent does]\n\n## Workflow\n\n[How it approaches tasks — research, draft, validate, output]\n\n## Output Format\n\n[Expected structure of deliverables]\n```\n\n### 7. Validate Against 10 Golden Rules\n\nAfter creation, run the agent linter:\n\n```bash\naiwg lint agents \u003Ctarget>\u002Fagents\u002F\u003Cname>.md --verbose\n```\n\nKey checks:\n- Single responsibility (no \"and\" overload in description)\n- Minimal tools (0-3 tools, each justified)\n- Explicit I\u002FO contract defined\n- Model tier matches task complexity\n\n### 8. Update Manifest\n\nThe CLI tool updates `\u003Ctarget>\u002Fmanifest.json` automatically. Verify:\n\n```json\n{\n  \"agents\": [\"existing-agent\", \"\u003Cname>\"]\n}\n```\n\n## Generated Structure\n\n```\n\u003Ctarget>\u002Fagents\u002F\u003Cname>.md\n```\n\nManifest updated: `\u003Ctarget>\u002Fmanifest.json`\n\n## Output Format\n\n```\nAgent Created: \u003Cname>\n─────────────────────\nLocation: \u003Ctarget>\u002Fagents\u002F\u003Cname>.md\nTemplate:  \u003Ctype>\nModel:     \u003Cmodel>\n\nCreated:\n  ✓ \u003Ctarget>\u002Fagents\u002F\u003Cname>.md\n  ✓ manifest.json updated\n\nValidation:\n  ✓ Single responsibility\n  ✓ Tool count within limit\n  ✓ I\u002FO contract defined\n\nNext Steps:\n  1. Edit Expertise section with domain knowledge\n  2. Define Responsibilities (3-5 items)\n  3. Specify Output Format structure\n  4. Run: aiwg lint agents \u003Ctarget>\u002Fagents\u002F\u003Cname>.md\n```\n\n## Examples\n\n### Example 1: Simple utility agent\n\n**User**: \"add agent dependency-auditor --to aiwg-utils\"\n\n**Action**:\n```bash\naiwg add-agent dependency-auditor --to aiwg-utils\n```\n\n**Result**: `agentic\u002Fcode\u002Faddons\u002Faiwg-utils\u002Fagents\u002Fdependency-auditor.md` scaffolded with simple template (haiku, Read + Grep tools).\n\n### Example 2: Complex domain expert\n\n**User**: \"create a threat modeling agent for sdlc-complete\"\n\n**Extraction**: name=`threat-modeler`, target=`sdlc-complete`, template=`complex`\n\n**Action**:\n```bash\naiwg add-agent threat-modeler --to sdlc-complete --template complex\n```\n\n**Result**: `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fagents\u002Fthreat-modeler.md` scaffolded with sonnet model, Read\u002FWrite\u002FGrep tools.\n\n### Example 3: Interactive guided creation\n\n**User**: \"add agent --interactive --to sdlc-complete\"\n\n**Process**: Guided questions gather role, expertise, responsibilities, tools, and model tier before scaffolding.\n\n## References\n\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Faddons\u002Faiwg-utils\u002Fskills\u002Fdevkit-create-agent\u002FSKILL.md — Devkit equivalent (interactive design)\n- @$AIWG_ROOT\u002Fsrc\u002Fcli\u002Fhandlers\u002Fscaffolding.ts — CLI handler implementation\n- @$AIWG_ROOT\u002Fdocs\u002Fcli-reference.md — Full CLI reference\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fagents\u002F — Example agent definitions\n","# Add Agent\n\nScaffold a new agent definition file inside an existing addon or framework.\n\n## Triggers\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"I need a new agent\" → scaffold agent in specified target\n- \"build me an agent\" → scaffold agent with interactive guidance\n- \"write an agent for X\" → scaffold agent named after the described role\n- \"agent for \u003Crole>\" → derive name from role, prompt for target\n\n## Trigger Patterns Reference\n\n| Pattern | Example | Action |\n|---------|---------|--------|\n| Named add | \"add agent security-auditor --to sdlc-complete\" | Scaffold directly |\n| Role description | \"create an agent that reviews PRs\" | Derive name, scaffold |\n| Interactive | \"add agent --interactive\" | Guided mode, ask for name\u002Ftarget\u002Ftemplate |\n| Target omitted | \"add agent code-reviewer\" | Ask which addon or framework |\n\n## Process\n\n### 1. Parse Arguments\n\nExtract from `$ARGUMENTS`:\n- `\u003Cname>` — kebab-case agent name (required)\n- `--to \u003Ctarget>` — addon or framework directory name (required)\n- `--template \u003Ctype>` — one of `simple` (default), `complex`, `orchestrator`, `validator`\n- `--interactive` — enable guided design questions\n\nIf either `\u003Cname>` or `--to` is missing, ask before proceeding.\n\n### 2. Validate Target\n\nConfirm the target addon or framework exists:\n\n```bash\n# Check addons\nls agentic\u002Fcode\u002Faddons\u002F\u003Ctarget>\u002F\n\n# Check frameworks\nls agentic\u002Fcode\u002Fframeworks\u002F\u003Ctarget>\u002F\n```\n\nIf not found, report available targets and stop.\n\n### 3. Interactive Design (if --interactive)\n\nAsk the following before generating:\n\n1. **Role**: What is this agent's primary role?\n2. **Expertise**: What domains or technologies does it specialize in?\n3. **Responsibilities**: What are its 3-5 key responsibilities?\n4. **Tools needed**: Which tools does it require? (Read, Write, Bash, Grep, WebFetch, Task)\n5. **Model tier**: haiku (fast\u002Futility), sonnet (balanced), opus (reasoning-heavy)\n6. **Output format**: What structured output should it produce?\n\n### 4. Select Template\n\n| Template | Use When | Default Model | Tools |\n|----------|----------|---------------|-------|\n| `simple` | Single-purpose utility agent | haiku | Read, Write |\n| `complex` | Domain expert, reviewer, analyst | sonnet | Read, Write, Grep |\n| `orchestrator` | Coordinates other agents | opus | Task |\n| `validator` | Read-only quality\u002Fcompliance gate | haiku | Read, Grep |\n\n### 5. Run Scaffolding\n\n```bash\naiwg add-agent \u003Cname> --to \u003Ctarget> --template \u003Ctype>\n```\n\nThis generates `\u003Ctarget>\u002Fagents\u002F\u003Cname>.md` with the appropriate frontmatter and section stubs.\n\n### 6. Customize the Generated File\n\nThe generated agent file requires population of these sections:\n\n```markdown\n---\nname: \u003Cname>\ndescription: \u003Cone-sentence purpose>\nmodel: \u003Cclaude-haiku-4-5|claude-sonnet-5|claude-opus-5>  # Pin specific variant; bare aliases (`sonnet`) inherit the parent session's 1M-context attributes and hit the usage-credit gate on subagent dispatch. See #1442.\ntools: \u003Ccomma-separated tool list>\ncategory: \u003Cphase or domain>\n---\n\n# Agent Title\n\n[Role description]\n\n## Expertise\n\n[Domain knowledge and skills]\n\n## Responsibilities\n\n[Numbered list of what this agent does]\n\n## Workflow\n\n[How it approaches tasks — research, draft, validate, output]\n\n## Output Format\n\n[Expected structure of deliverables]\n```\n\n### 7. Validate Against 10 Golden Rules\n\nAfter creation, run the agent linter:\n\n```bash\naiwg lint agents \u003Ctarget>\u002Fagents\u002F\u003Cname>.md --verbose\n```\n\nKey checks:\n- Single responsibility (no \"and\" overload in description)\n- Minimal tools (0-3 tools, each justified)\n- Explicit I\u002FO contract defined\n- Model tier matches task complexity\n\n### 8. Update Manifest\n\nThe CLI tool updates `\u003Ctarget>\u002Fmanifest.json` automatically. Verify:\n\n```json\n{\n  \"agents\": [\"existing-agent\", \"\u003Cname>\"]\n}\n```\n\n## Generated Structure\n\n```\n\u003Ctarget>\u002Fagents\u002F\u003Cname>.md\n```\n\nManifest updated: `\u003Ctarget>\u002Fmanifest.json`\n\n## Output Format\n\n```\nAgent Created: \u003Cname>\n─────────────────────\nLocation: \u003Ctarget>\u002Fagents\u002F\u003Cname>.md\nTemplate:  \u003Ctype>\nModel:     \u003Cmodel>\n\nCreated:\n  ✓ \u003Ctarget>\u002Fagents\u002F\u003Cname>.md\n  ✓ manifest.json updated\n\nValidation:\n  ✓ Single responsibility\n  ✓ Tool count within limit\n  ✓ I\u002FO contract defined\n\nNext Steps:\n  1. Edit Expertise section with domain knowledge\n  2. Define Responsibilities (3-5 items)\n  3. Specify Output Format structure\n  4. Run: aiwg lint agents \u003Ctarget>\u002Fagents\u002F\u003Cname>.md\n```\n\n## Examples\n\n### Example 1: Simple utility agent\n\n**User**: \"add agent dependency-auditor --to aiwg-utils\"\n\n**Action**:\n```bash\naiwg add-agent dependency-auditor --to aiwg-utils\n```\n\n**Result**: `agentic\u002Fcode\u002Faddons\u002Faiwg-utils\u002Fagents\u002Fdependency-auditor.md` scaffolded with simple template (haiku, Read + Grep tools).\n\n### Example 2: Complex domain expert\n\n**User**: \"create a threat modeling agent for sdlc-complete\"\n\n**Extraction**: name=`threat-modeler`, target=`sdlc-complete`, template=`complex`\n\n**Action**:\n```bash\naiwg add-agent threat-modeler --to sdlc-complete --template complex\n```\n\n**Result**: `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fagents\u002Fthreat-modeler.md` scaffolded with sonnet model, Read\u002FWrite\u002FGrep tools.\n\n### Example 3: Interactive guided creation\n\n**User**: \"add agent --interactive --to sdlc-complete\"\n\n**Process**: Guided questions gather role, expertise, responsibilities, tools, and model tier before scaffolding.\n\n## References\n\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Faddons\u002Faiwg-utils\u002Fskills\u002Fdevkit-create-agent\u002FSKILL.md — Devkit equivalent (interactive design)\n- @$AIWG_ROOT\u002Fsrc\u002Fcli\u002Fhandlers\u002Fscaffolding.ts — CLI handler implementation\n- @$AIWG_ROOT\u002Fdocs\u002Fcli-reference.md — Full CLI reference\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fagents\u002F — Example agent definitions\n",{"name":5,"namespace":39,"platforms":40,"description":7},"aiwg",[41],"all","main","6754967c344ccb087a8de06972f55a41067b291b","agentic\u002Fcode\u002Fplugins\u002Futils\u002Fskills\u002Fadd-agent",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":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add jmagly\u002Faiwg --skill add-agent",{"tool":58,"command":59},"bunx","bunx skills add jmagly\u002Faiwg --skill add-agent",{"tool":61,"command":62},"pnpm","pnpm dlx skills add jmagly\u002Faiwg --skill add-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Futils\u002Fskills\u002Fadd-agent\u002FSKILL.md",true,[],[67,95,119,125,132,146],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":74,"publishedAt":34},"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",[73],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94],"host","host hardening","hardening","read","re","recommendations","remediation","plan","port","verification","Bash","access","only","retention","audit","never","firewall","bind","secrets","request",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":105,"publishedAt":34},"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",[101,104],{"categoryNo":102,"categoryName":103,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[106,107,108,78,109,83,110,111,85,112,75,113,87,114,115,90,91,116,117,118],"exposure analysis","analysis","unknown","credentials","collection","ufw","ports","internet","local","scope","reconstruction","operator","write",{"skillNo":120,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":124,"publishedAt":34},"01M70P8QATMPKA78E4FT5D2TNA","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[123],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[77,75,76,86,78,94,81,80,89,82,83,84,85,93,87,88,79,90,91,92],{"skillNo":126,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":131,"publishedAt":34},"01M70NMPVJ5H0JH131P60FW4R8","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fforensics-complete\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[129,130],{"categoryNo":102,"categoryName":103,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[107,106,90,109,83,110,85,108,75,113,87,114,115,78,91,112,111,116,117,118],{"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":139,"publishedAt":34},"01M6CB4DDR0B4NNCFK7ZK7449H","fixture-skill","Exercise rule delivery.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Frule-delivery\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[138],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[140,141,142,143,144,145],"fixture skill","fixture","rule","delivery","true","exercise",{"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":34},"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",[152],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[154,155,114,156,141],"pi","pi local","duplicate"]