[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C12WDT7GM7XMTCVKVYWAY7":3,"skill-same:01M6C12WDT7GM7XMTCVKVYWAY7":68},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6C12WDT7GM7XMTCVKVYWAY7","devkit-create-agent",null,"Create a new agent with AI-guided expertise definition following the Agent Design Bible","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-dev\u002Fskills\u002Fdevkit-create-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",[24,25,26,27,28,29,30,31,32,33,34,35],"create agent","create","devkit create agent","devkit","design","agent design","bible","new agent","with","expertise","definition","new","2026-11-10 10:12:30",false,"---\nnamespace: aiwg\nname: devkit-create-agent\nplatforms: [all]\ndescription: Create a new agent with AI-guided expertise definition following the Agent Design Bible\n---\n\n# Create AIWG Agent\n\nCreate a new agent with AI assistance to define expertise, workflow, and capabilities.\n\n**Follows**: [Agent Design Bible]($AIWG_ROOT\u002Fdocs\u002Fframeworks\u002Fsdlc-complete\u002Fagent-design.md) - 10 Golden Rules for production-grade agents.\n\n**Research Foundation**: REF-001 (Bandara et al.), REF-002 (Roig 2025) failure archetype prevention.\n\n## Usage\n\n```\n\u002Fdevkit-create-agent \u003Cname> --to \u003Ctarget> [options]\n```\n\n## Arguments\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| name | Yes | Agent name (kebab-case recommended) |\n\n## Required Options\n\n| Option | Description |\n|--------|-------------|\n| --to | Target addon or framework |\n\n## Optional Options\n\n| Option | Description |\n|--------|-------------|\n| --template | Agent template: simple (default), complex, orchestrator |\n| --interactive | Enable interactive mode with guided questions |\n\n## Templates\n\nTemplates are in `~\u002F.local\u002Fshare\u002Fai-writing-guide\u002Ftemplates\u002Fagent-scaffolding\u002F`.\n\n### simple (default)\nSingle-purpose, focused agent with minimal structure (Rule 1: Single Responsibility).\n- Best for: Utility agents, single-task specialists\n- Model: haiku (efficiency tier)\n- Tools: Read, Write (Rule 2: Minimal Tools)\n\n### complex\nFull reasoning agent with all safeguards including failure archetype prevention.\n- Best for: Subject matter experts, reviewers, analysts\n- Model: sonnet\u002Fopus (based on complexity)\n- Tools: Read, Write, Grep (Rule 2: 0-3 tools)\n- Includes: Grounding, uncertainty handling, recovery protocol\n\n### orchestrator\nMulti-agent coordination with workflow patterns and agent assignment tables.\n- Best for: Workflow coordinators, phase managers\n- Model: opus (Rule 8: reasoning tier for coordination)\n- Tools: Task only (Rule 2: single tool for delegation)\n\n### validator\nRead-only validation agent that doesn't modify state.\n- Best for: Quality gates, compliance checks, code review\n- Model: haiku\u002Fsonnet\n- Tools: Read, Grep (read-only)\n\n## Interactive Mode\n\nWhen `--interactive` is specified, I will ask:\n\n1. **Role**: What is this agent's primary role?\n2. **Expertise**: What domains does it specialize in?\n3. **Responsibilities**: What are its key responsibilities?\n4. **Tools**: What tools does it need access to?\n5. **Workflow**: How should it approach tasks?\n6. **Output**: What format should its output take?\n\n## Examples\n\n```bash\n# Simple agent\n\u002Fdevkit-create-agent code-reviewer --to aiwg-utils\n\n# Complex domain expert\n\u002Fdevkit-create-agent security-auditor --to sdlc-complete --template complex\n\n# Orchestrator agent\n\u002Fdevkit-create-agent deployment-coordinator --to sdlc-complete --template orchestrator --interactive\n```\n\n## Execution\n\n1. **Validate inputs**: Check name and target\n2. **Verify target exists**: Ensure addon\u002Fframework is installed\n3. **Select template**: Use specified or default to simple\n4. **Gather expertise**: In interactive mode, ask about domain knowledge\n5. **Generate agent file**: Create with frontmatter and sections\n6. **Update manifest**: Add agent to manifest.json\n7. **Report success**: Show location and customization tips\n\n## Output Location\n\n```\n\u003Ctarget>\u002Fagents\u002F\u003Cname>.md\n```\n\n## Agent File Structure\n\n```markdown\n---\nname: agent-name\ndescription: Agent description\nmodel: claude-sonnet-5\ntools: Read, Write, MultiEdit, Bash, WebFetch\n---\n\n# Agent Title\n\n[Description]\n\n## Expertise\n[Domain knowledge]\n\n## Responsibilities\n[What the agent does]\n\n## Workflow\n[How it approaches tasks]\n\n## Output Format\n[Expected output structure]\n```\n\n## CLI Equivalent\n\n```bash\naiwg add-agent \u003Cname> --to \u003Ctarget> --template \u003Ctype>\n```\n\n## 10 Golden Rules Validation\n\nAfter creation, validate against the Agent Design Bible:\n\n```bash\naiwg lint agents \u003Ctarget>\u002Fagents\u002F\u003Cname>.md --verbose\n```\n\n| Rule | Check |\n|------|-------|\n| 1. Single Responsibility | One clear purpose, no \"and\" overload |\n| 2. Minimal Tools | 0-3 tools, justified |\n| 3. Explicit I\u002FO | Inputs and outputs defined |\n| 4. Grounding | Verify before acting (Archetype 1) |\n| 5. Uncertainty | Escalate ambiguity (Archetype 2) |\n| 6. Context Scope | Filter distractors (Archetype 3) |\n| 7. Recovery | Handle errors (Archetype 4) |\n| 8. Model Tier | Match task complexity |\n| 9. Parallel Ready | Concurrent execution safe |\n| 10. Observable | Traceable output |\n\n## Related Commands\n\n- `\u002Fdevkit-create-command` - Create a slash command\n- `\u002Fdevkit-create-skill` - Create an auto-triggered skill\n- `\u002Fdevkit-validate` - Validate agent structure\n- `aiwg lint agents` - Validate against 10 Golden Rules\n\n## References\n\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Faddons\u002Faiwg-dev\u002FREADME.md — aiwg-dev addon overview\n- @$AIWG_ROOT\u002Fdocs\u002Fextensions\u002Fextension-types.md — Extension types including agent type\n- @$AIWG_ROOT\u002Fdocs\u002Fcli-reference.md — CLI reference including add-agent command\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Faddons\u002Faiwg-utils\u002Frules\u002Fgod-session.md — Single-responsibility rules for agents\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Faddons\u002Faiwg-utils\u002Frules\u002Fagent-deployment.md — Agent metadata structure and multi-provider deployment\n","# Create AIWG Agent\n\nCreate a new agent with AI assistance to define expertise, workflow, and capabilities.\n\n**Follows**: [Agent Design Bible]($AIWG_ROOT\u002Fdocs\u002Fframeworks\u002Fsdlc-complete\u002Fagent-design.md) - 10 Golden Rules for production-grade agents.\n\n**Research Foundation**: REF-001 (Bandara et al.), REF-002 (Roig 2025) failure archetype prevention.\n\n## Usage\n\n```\n\u002Fdevkit-create-agent \u003Cname> --to \u003Ctarget> [options]\n```\n\n## Arguments\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| name | Yes | Agent name (kebab-case recommended) |\n\n## Required Options\n\n| Option | Description |\n|--------|-------------|\n| --to | Target addon or framework |\n\n## Optional Options\n\n| Option | Description |\n|--------|-------------|\n| --template | Agent template: simple (default), complex, orchestrator |\n| --interactive | Enable interactive mode with guided questions |\n\n## Templates\n\nTemplates are in `~\u002F.local\u002Fshare\u002Fai-writing-guide\u002Ftemplates\u002Fagent-scaffolding\u002F`.\n\n### simple (default)\nSingle-purpose, focused agent with minimal structure (Rule 1: Single Responsibility).\n- Best for: Utility agents, single-task specialists\n- Model: haiku (efficiency tier)\n- Tools: Read, Write (Rule 2: Minimal Tools)\n\n### complex\nFull reasoning agent with all safeguards including failure archetype prevention.\n- Best for: Subject matter experts, reviewers, analysts\n- Model: sonnet\u002Fopus (based on complexity)\n- Tools: Read, Write, Grep (Rule 2: 0-3 tools)\n- Includes: Grounding, uncertainty handling, recovery protocol\n\n### orchestrator\nMulti-agent coordination with workflow patterns and agent assignment tables.\n- Best for: Workflow coordinators, phase managers\n- Model: opus (Rule 8: reasoning tier for coordination)\n- Tools: Task only (Rule 2: single tool for delegation)\n\n### validator\nRead-only validation agent that doesn't modify state.\n- Best for: Quality gates, compliance checks, code review\n- Model: haiku\u002Fsonnet\n- Tools: Read, Grep (read-only)\n\n## Interactive Mode\n\nWhen `--interactive` is specified, I will ask:\n\n1. **Role**: What is this agent's primary role?\n2. **Expertise**: What domains does it specialize in?\n3. **Responsibilities**: What are its key responsibilities?\n4. **Tools**: What tools does it need access to?\n5. **Workflow**: How should it approach tasks?\n6. **Output**: What format should its output take?\n\n## Examples\n\n```bash\n# Simple agent\n\u002Fdevkit-create-agent code-reviewer --to aiwg-utils\n\n# Complex domain expert\n\u002Fdevkit-create-agent security-auditor --to sdlc-complete --template complex\n\n# Orchestrator agent\n\u002Fdevkit-create-agent deployment-coordinator --to sdlc-complete --template orchestrator --interactive\n```\n\n## Execution\n\n1. **Validate inputs**: Check name and target\n2. **Verify target exists**: Ensure addon\u002Fframework is installed\n3. **Select template**: Use specified or default to simple\n4. **Gather expertise**: In interactive mode, ask about domain knowledge\n5. **Generate agent file**: Create with frontmatter and sections\n6. **Update manifest**: Add agent to manifest.json\n7. **Report success**: Show location and customization tips\n\n## Output Location\n\n```\n\u003Ctarget>\u002Fagents\u002F\u003Cname>.md\n```\n\n## Agent File Structure\n\n```markdown\n---\nname: agent-name\ndescription: Agent description\nmodel: claude-sonnet-5\ntools: Read, Write, MultiEdit, Bash, WebFetch\n---\n\n# Agent Title\n\n[Description]\n\n## Expertise\n[Domain knowledge]\n\n## Responsibilities\n[What the agent does]\n\n## Workflow\n[How it approaches tasks]\n\n## Output Format\n[Expected output structure]\n```\n\n## CLI Equivalent\n\n```bash\naiwg add-agent \u003Cname> --to \u003Ctarget> --template \u003Ctype>\n```\n\n## 10 Golden Rules Validation\n\nAfter creation, validate against the Agent Design Bible:\n\n```bash\naiwg lint agents \u003Ctarget>\u002Fagents\u002F\u003Cname>.md --verbose\n```\n\n| Rule | Check |\n|------|-------|\n| 1. Single Responsibility | One clear purpose, no \"and\" overload |\n| 2. Minimal Tools | 0-3 tools, justified |\n| 3. Explicit I\u002FO | Inputs and outputs defined |\n| 4. Grounding | Verify before acting (Archetype 1) |\n| 5. Uncertainty | Escalate ambiguity (Archetype 2) |\n| 6. Context Scope | Filter distractors (Archetype 3) |\n| 7. Recovery | Handle errors (Archetype 4) |\n| 8. Model Tier | Match task complexity |\n| 9. Parallel Ready | Concurrent execution safe |\n| 10. Observable | Traceable output |\n\n## Related Commands\n\n- `\u002Fdevkit-create-command` - Create a slash command\n- `\u002Fdevkit-create-skill` - Create an auto-triggered skill\n- `\u002Fdevkit-validate` - Validate agent structure\n- `aiwg lint agents` - Validate against 10 Golden Rules\n\n## References\n\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Faddons\u002Faiwg-dev\u002FREADME.md — aiwg-dev addon overview\n- @$AIWG_ROOT\u002Fdocs\u002Fextensions\u002Fextension-types.md — Extension types including agent type\n- @$AIWG_ROOT\u002Fdocs\u002Fcli-reference.md — CLI reference including add-agent command\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Faddons\u002Faiwg-utils\u002Frules\u002Fgod-session.md — Single-responsibility rules for agents\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Faddons\u002Faiwg-utils\u002Frules\u002Fagent-deployment.md — Agent metadata structure and multi-provider deployment\n",{"name":5,"namespace":41,"platforms":42,"description":7},"aiwg",[43],"all","main","6754967c344ccb087a8de06972f55a41067b291b","agentic\u002Fcode\u002Faddons\u002Faiwg-dev\u002Fskills\u002Fdevkit-create-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 00:33:10",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add jmagly\u002Faiwg --skill devkit-create-agent",{"tool":60,"command":61},"bunx","bunx skills add jmagly\u002Faiwg --skill devkit-create-agent",{"tool":63,"command":64},"pnpm","pnpm dlx skills add jmagly\u002Faiwg --skill devkit-create-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Faddons\u002Faiwg-dev\u002Fskills\u002Fdevkit-create-agent\u002FSKILL.md",true,[],[69,97,121,127,134,148],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":76,"publishedAt":36},"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",[75],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96],"host","host hardening","hardening","read","re","recommendations","remediation","plan","port","verification","Bash","access","only","retention","audit","never","firewall","bind","secrets","request",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":107,"publishedAt":36},"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",[103,106],{"categoryNo":104,"categoryName":105,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[108,109,110,80,111,85,112,113,87,114,77,115,89,116,117,92,93,118,119,120],"exposure analysis","analysis","unknown","credentials","collection","ufw","ports","internet","local","scope","reconstruction","operator","write",{"skillNo":122,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":126,"publishedAt":36},"01M70P8QATMPKA78E4FT5D2TNA","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[125],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[79,77,78,88,80,96,83,82,91,84,85,86,87,95,89,90,81,92,93,94],{"skillNo":128,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":133,"publishedAt":36},"01M70NMPVJ5H0JH131P60FW4R8","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fforensics-complete\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[131,132],{"categoryNo":104,"categoryName":105,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[109,108,92,111,85,112,87,110,77,115,89,116,117,80,93,114,113,118,119,120],{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":141,"publishedAt":36},"01M6CB4DDR0B4NNCFK7ZK7449H","fixture-skill","Exercise rule delivery.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Frule-delivery\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[140],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[142,143,144,145,146,147],"fixture skill","fixture","rule","delivery","true","exercise",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":155,"publishedAt":36},"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",[154],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[156,157,116,158,143],"pi","pi local","duplicate"]