[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71GHDSFS3Y4D9DXCSEBK7XB":3,"skill-same:01M71GHDSFS3Y4D9DXCSEBK7XB":96},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":61,"install":62,"resources":75},"01M71GHDSFS3Y4D9DXCSEBK7XB","intelligent-router",null,"Analyzes user questions and automatically dispatches optimal agents\u002Fskills\u002Fplugins","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Primadetaautomation--intelligent-router\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"intelligent router","router","user","plugins","questions","logic","detect","testing tools","routing","examples","complete","framework","Tools","matrix","scripts","auto","auto-detect","decision","testing","2026-11-10 10:12:30",false,"---\nname: intelligent-router\ndescription: Analyzes user questions and automatically dispatches optimal agents\u002Fskills\u002Fplugins\ntriggers: []\nversion: 1.0.0\nagents: []\nactivation: smart-auto-detect\ncontext_levels:\n  minimal: Router logic and decision framework\n  detailed: Complete routing matrix and examples\n  full: Scripts and testing tools\n---\n\n# 🎯 Intelligent Router - Smart Agent\u002FSkill\u002FPlugin Dispatch\n\n## Overview\n\nThe Intelligent Router is an **automatic orchestration system** that analyzes user questions and intelligently selects the optimal combination of:\n- 🤖 **Agents** (specialized subagents)\n- 🎯 **Skills** (knowledge bundles)\n- 🔌 **Plugins** (global tools)\n- 📚 **Docs** (project documentation)\n- 🛠️ **Tools** (native Claude tools)\n\n**Design Philosophy: B - Medium Router**\n- ✅ Auto-loads relevant skills\n- ✅ Auto-dispatches primary agent\n- 💡 Suggests optional agents (you choose)\n- 📊 Transparent reporting (you see everything)\n\n## When This Skill Activates\n\n**Smart Auto-Detect** triggers on:\n- ✅ Questions with 5+ words\n- ✅ Action verbs: \"maak\", \"bouw\", \"fix\", \"deploy\", \"test\", etc.\n- ✅ Complex requests (multiple domains)\n\n**Skips on:**\n- ❌ Simple questions: \"Wat is X?\", \"Hoe werkt Y?\"\n- ❌ Short queries (\u003C 5 words)\n- ❌ Informational requests\n\n## How It Works\n\n### Phase 1: Analysis\n```\nUser Question\n    ↓\nIntent Detection (analyze-intent.js)\n    ↓\nMatch Against Routing Matrix\n    ↓\nCalculate Match Scores\n    ↓\nIdentify Domains & Complexity\n```\n\n### Phase 2: Resource Collection\n```\nCollect ALL Matched Routes\n    ↓\nPrimary Route = Highest Score\n    ↓\nGather:\n  - Skills from all matches\n  - Plugins from all matches\n  - Docs from all matches\n  - Tools from primary route\n  - Optional agents from secondary matches\n```\n\n### Phase 3: Dispatch\n```\nAuto-Load:\n  ✅ Skills (via skill-loader.js)\n  ✅ Docs (loaded into context)\n  ✅ Plugins (activated)\n\nAuto-Dispatch:\n  ✅ Primary Agent (Task tool)\n\nSuggest:\n  💡 Optional Agents (you choose to dispatch)\n  💡 Additional tools\n  💡 Memory check (episodic-memory)\n```\n\n### Phase 4: Transparent Reporting\n```\nDisplay Formatted Analysis:\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n🎯 INTELLIGENT ROUTER ANALYSIS\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n📊 Detected Intent: [...]\n📁 Complexity: [SIMPLE|MEDIUM|HIGH|COMPLEX]\n🎯 Domains: [...]\n\n✅ AUTO-LOADED SKILLS: [...]\n✅ AUTO-DISPATCHED: [agent] → [reason]\n💡 OPTIONAL DISPATCH: [suggestions]\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n```\n\n## Routing Matrix\n\nThe router uses `routing-matrix.json` with 20+ predefined routes:\n\n### Critical Routes (Always Priority)\n- **memory_recall** - Episodic memory search\n- **security_review** - OWASP compliance, vulnerability scanning\n- **authentication** - User auth, login systems\n- **complex_feature** - Multi-domain features → master-orchestrator\n\n### High Priority Routes\n- **backend_api** - REST\u002FGraphQL API development\n- **backend_database** - SQL, schema design, queries\n- **frontend_ui** - React\u002FVue components, UI work\n- **testing_unit** - TDD, unit\u002Fintegration tests\n- **architecture** - System design, tech stack decisions\n- **debugging** - Bug fixes, error resolution\n\n### Medium Priority Routes\n- **ux_design** - UI\u002FUX, dashboards, premium interfaces\n- **testing_e2e** - Playwright, browser automation\n- **data_engineering** - ETL pipelines, data warehouses\n- **deployment** - CI\u002FCD, production deploys\n- **ai_ml_integration** - LLM, RAG, vector databases\n- **accessibility** - WCAG compliance, inclusive design\n\n### Specialized Routes\n- **code_search** - Finding code, codebase analysis\n- **browser_automation** - Web scraping, UI testing\n- **git_operations** - Worktrees, branching\n- **documentation** - Writing docs, README files\n\n## Complexity Assessment\n\nRouter automatically determines complexity:\n\n### Simple (1 domain, \u003C 10 words)\n- Single file edit\n- Small bug fix\n- Quick query\n→ **Auto-dispatch:** Direct to specialist agent\n\n### Medium (2 domains, 10-30 words)\n- New feature in one area\n- Moderate refactoring\n- Standard API endpoint\n→ **Auto-dispatch:** Primary agent + suggest related agents\n\n### High (3 domains, 30-50 words)\n- Cross-cutting feature\n- Security + functionality\n- Multiple file changes\n→ **Auto-dispatch:** Primary agent + optional specialists\n\n### Complex (3+ domains, complex requirements)\n- Complete new module\n- System redesign\n- Multi-domain integration\n→ **Requires:** master-orchestrator with sub-agents\n\n## Progressive Context Loading\n\nRouter uses 3 levels for skills:\n\n### Level 1: Always Load\n- Core principles (2-5KB)\n- Quick reference\n- Essential patterns\n\n### Level 2: Load on Request\n- Detailed patterns (10-15KB)\n- Complete examples\n- Architecture guidance\n\n### Level 3: Full Context\n- All scripts\n- Templates\n- Automation tools\n\n**Default:** Router loads Level 1 for all matched skills\n**Escalation:** Request Level 2\u002F3 if needed\n\n## Example Routing Scenarios\n\n### Example 1: Simple Bug Fix\n```\nUser: \"Fix deze error in login.ts\"\n\nRouter Analysis:\n  Intent: Bug fixing\n  Complexity: SIMPLE\n  Domains: debugging, backend\n\nAuto-Loaded:\n  - systematic-debugging skill\n  - testing-fundamentals skill\n\nAuto-Dispatched:\n  - senior-fullstack-developer\n\nOptional:\n  - qa-testing-engineer (regression tests)\n```\n\n### Example 2: Authentication System\n```\nUser: \"Maak een login systeem met registratie\"\n\nRouter Analysis:\n  Intent: User authentication\n  Complexity: HIGH\n  Domains: security, backend, frontend\n\nAuto-Loaded:\n  - security-essentials skill\n  - backend-development-patterns skill\n  - testing-fundamentals skill\n\nAuto-Dispatched:\n  - backend-specialist (primary)\n\nOptional:\n  - security-specialist (OWASP review)\n  - frontend-specialist (login UI)\n  - qa-testing-engineer (security tests)\n\nDocs Loaded:\n  - docs\u002Fsecurity.md\n  - docs\u002Fbackend.md\n```\n\n### Example 3: Complete Feature\n```\nUser: \"Bouw een dashboard met gebruikers, data visualisatie en export\"\n\nRouter Analysis:\n  Intent: Multi-domain feature\n  Complexity: COMPLEX\n  Domains: frontend, backend, data, ux\n\nAuto-Loaded:\n  - backend-development-patterns skill\n  - testing-fundamentals skill\n  - brainstorming skill\n\nAuto-Dispatched:\n  - master-orchestrator\n    Sub-agents (parallel):\n      - backend-specialist (API)\n      - frontend-specialist (Dashboard UI)\n      - data-engineer (Data pipeline)\n      - ux-design-expert (Charts\u002FUX)\n      - qa-testing-engineer (Test strategy)\n```\n\n### Example 4: Database Query\n```\nUser: \"Optimaliseer deze SQL query die te langzaam is\"\n\nRouter Analysis:\n  Intent: Database optimization\n  Complexity: MEDIUM\n  Domains: data-engineering, backend\n\nAuto-Loaded:\n  - backend-development-patterns skill\n\nAuto-Dispatched:\n  - data-engineer\n\nTools Activated:\n  - sql-universal-expert\n\nOptional:\n  - senior-fullstack-developer (code refactor)\n\nDocs Loaded:\n  - docs\u002Fbackend.md\n```\n\n## Usage\n\n### Automatic (Recommended)\nRouter activates automatically when:\n1. User asks question with 5+ words\n2. Question contains action verbs\n3. Question seems like a task (not just info)\n\nNo manual activation needed!\n\n### Manual Testing\nTest router analysis before dispatching:\n\n```bash\n# Analyze a question\nnode .claude\u002Fskills\u002Fintelligent-router\u002Fscripts\u002Fanalyze-intent.js analyze \"Maak een API\"\n\n# Get JSON output\nnode .claude\u002Fskills\u002Fintelligent-router\u002Fscripts\u002Fanalyze-intent.js analyze \"Fix bug\" --json\n```\n\n### Integration with Hooks\nRouter integrates via `.claude\u002Fhooks\u002Fpre-prompt.sh` (optional):\n```bash\n#!\u002Fbin\u002Fbash\n# Activate intelligent-router for every question\n# Router internally checks if it should activate\n```\n\n## Configuration\n\n### Customize Routing Matrix\nEdit `routing-matrix.json` to:\n- Add new routes\n- Modify trigger keywords\n- Adjust priorities\n- Add custom agents\u002Fskills\n\n### Customize Auto-Detect\nEdit `auto_detect_config` in routing-matrix.json:\n```json\n{\n  \"min_word_count\": 5,\n  \"action_verbs\": [\"maak\", \"bouw\", \"fix\", ...],\n  \"skip_keywords\": [\"wat is\", \"hoe werkt\", ...],\n  \"always_check_memory\": true\n}\n```\n\n### Complexity Thresholds\nAdjust in `complexity_thresholds`:\n```json\n{\n  \"simple\": {\n    \"max_words\": 10,\n    \"max_domains\": 1,\n    \"auto_dispatch\": true\n  },\n  ...\n}\n```\n\n## Router Decision Tree\n\n```\nUser Question\n    ↓\n[Should Activate?]\n    ├─ No → Normal response (skip router)\n    └─ Yes → Continue\n         ↓\n    [Find Matches]\n         ↓\n    [No Matches?]\n         ├─ Yes → Normal response\n         └─ No → Continue\n              ↓\n         [Analyze Complexity]\n              ↓\n         [Simple\u002FMedium\u002FHigh] → Auto-dispatch primary agent\n         [Complex] → Dispatch master-orchestrator\n              ↓\n         [Display Analysis]\n              ↓\n         [Execute Dispatch]\n```\n\n## Best Practices\n\n### For Users\n- ✅ Be specific in your questions (better matching)\n- ✅ Use action verbs when you want work done\n- ✅ Trust the router's suggestions\n- ✅ Dispatch optional agents if they make sense\n\n### For Developers\n- ✅ Keep routing-matrix.json updated\n- ✅ Add new routes for new capabilities\n- ✅ Test routes with analyze-intent.js\n- ✅ Monitor which routes get triggered most\n- ✅ Refine trigger keywords based on usage\n\n## Troubleshooting\n\n### Router Not Activating\n```bash\n# Check question meets criteria\nnode scripts\u002Fanalyze-intent.js analyze \"your question\"\n\n# If \"activate: false\", question too simple\n# Solution: Add more context or action verbs\n```\n\n### Wrong Agent Dispatched\n```bash\n# Check routing matrix matches\ncat routing-matrix.json | grep -A 5 \"your_keyword\"\n\n# Update triggers if needed\n```\n\n### Skills Not Loading\n```bash\n# Verify skills exist\nnode ..\u002Fskill-loader.js list\n\n# Check skill names in routing-matrix.json match\n```\n\n## Metrics & Improvement\n\nTrack router effectiveness:\n- **Activation rate** - How often it activates vs skips\n- **Accuracy** - Did it pick right agent\u002Fskills?\n- **User satisfaction** - Did suggestions help?\n- **Iteration count** - How many back-and-forth needed?\n\nStore in: `.claude-memory\u002Frouter-metrics.md`\n\n## Version History\n\n### v1.0.0 (Initial Release)\n- Smart auto-detect activation\n- 20+ predefined routes\n- Complexity assessment\n- Multi-level skill loading\n- Transparent reporting\n- Optional agent suggestions\n\n## Future Enhancements\n\nPlanned features:\n- [ ] Learning from past routing decisions\n- [ ] User preference tracking\n- [ ] Route effectiveness scoring\n- [ ] Dynamic route creation\n- [ ] Integration with episodic-memory for pattern learning\n- [ ] Web UI for route visualization\n\n## Resources\n\n- **Routing Matrix:** `routing-matrix.json`\n- **Intent Analyzer:** `scripts\u002Fanalyze-intent.js`\n- **Examples:** `examples\u002Frouting-scenarios.md`\n- **Tests:** `examples\u002Ftest-cases.md`\n\n---\n\n**Version:** 1.0.0\n**Author:** CLAUDE Framework Team\n**License:** MIT\n**Compatibility:** Claude Code 1.0+, Claude 3.5 Sonnet+\n","# 🎯 Intelligent Router - Smart Agent\u002FSkill\u002FPlugin Dispatch\n\n## Overview\n\nThe Intelligent Router is an **automatic orchestration system** that analyzes user questions and intelligently selects the optimal combination of:\n- 🤖 **Agents** (specialized subagents)\n- 🎯 **Skills** (knowledge bundles)\n- 🔌 **Plugins** (global tools)\n- 📚 **Docs** (project documentation)\n- 🛠️ **Tools** (native Claude tools)\n\n**Design Philosophy: B - Medium Router**\n- ✅ Auto-loads relevant skills\n- ✅ Auto-dispatches primary agent\n- 💡 Suggests optional agents (you choose)\n- 📊 Transparent reporting (you see everything)\n\n## When This Skill Activates\n\n**Smart Auto-Detect** triggers on:\n- ✅ Questions with 5+ words\n- ✅ Action verbs: \"maak\", \"bouw\", \"fix\", \"deploy\", \"test\", etc.\n- ✅ Complex requests (multiple domains)\n\n**Skips on:**\n- ❌ Simple questions: \"Wat is X?\", \"Hoe werkt Y?\"\n- ❌ Short queries (\u003C 5 words)\n- ❌ Informational requests\n\n## How It Works\n\n### Phase 1: Analysis\n```\nUser Question\n    ↓\nIntent Detection (analyze-intent.js)\n    ↓\nMatch Against Routing Matrix\n    ↓\nCalculate Match Scores\n    ↓\nIdentify Domains & Complexity\n```\n\n### Phase 2: Resource Collection\n```\nCollect ALL Matched Routes\n    ↓\nPrimary Route = Highest Score\n    ↓\nGather:\n  - Skills from all matches\n  - Plugins from all matches\n  - Docs from all matches\n  - Tools from primary route\n  - Optional agents from secondary matches\n```\n\n### Phase 3: Dispatch\n```\nAuto-Load:\n  ✅ Skills (via skill-loader.js)\n  ✅ Docs (loaded into context)\n  ✅ Plugins (activated)\n\nAuto-Dispatch:\n  ✅ Primary Agent (Task tool)\n\nSuggest:\n  💡 Optional Agents (you choose to dispatch)\n  💡 Additional tools\n  💡 Memory check (episodic-memory)\n```\n\n### Phase 4: Transparent Reporting\n```\nDisplay Formatted Analysis:\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n🎯 INTELLIGENT ROUTER ANALYSIS\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n📊 Detected Intent: [...]\n📁 Complexity: [SIMPLE|MEDIUM|HIGH|COMPLEX]\n🎯 Domains: [...]\n\n✅ AUTO-LOADED SKILLS: [...]\n✅ AUTO-DISPATCHED: [agent] → [reason]\n💡 OPTIONAL DISPATCH: [suggestions]\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n```\n\n## Routing Matrix\n\nThe router uses `routing-matrix.json` with 20+ predefined routes:\n\n### Critical Routes (Always Priority)\n- **memory_recall** - Episodic memory search\n- **security_review** - OWASP compliance, vulnerability scanning\n- **authentication** - User auth, login systems\n- **complex_feature** - Multi-domain features → master-orchestrator\n\n### High Priority Routes\n- **backend_api** - REST\u002FGraphQL API development\n- **backend_database** - SQL, schema design, queries\n- **frontend_ui** - React\u002FVue components, UI work\n- **testing_unit** - TDD, unit\u002Fintegration tests\n- **architecture** - System design, tech stack decisions\n- **debugging** - Bug fixes, error resolution\n\n### Medium Priority Routes\n- **ux_design** - UI\u002FUX, dashboards, premium interfaces\n- **testing_e2e** - Playwright, browser automation\n- **data_engineering** - ETL pipelines, data warehouses\n- **deployment** - CI\u002FCD, production deploys\n- **ai_ml_integration** - LLM, RAG, vector databases\n- **accessibility** - WCAG compliance, inclusive design\n\n### Specialized Routes\n- **code_search** - Finding code, codebase analysis\n- **browser_automation** - Web scraping, UI testing\n- **git_operations** - Worktrees, branching\n- **documentation** - Writing docs, README files\n\n## Complexity Assessment\n\nRouter automatically determines complexity:\n\n### Simple (1 domain, \u003C 10 words)\n- Single file edit\n- Small bug fix\n- Quick query\n→ **Auto-dispatch:** Direct to specialist agent\n\n### Medium (2 domains, 10-30 words)\n- New feature in one area\n- Moderate refactoring\n- Standard API endpoint\n→ **Auto-dispatch:** Primary agent + suggest related agents\n\n### High (3 domains, 30-50 words)\n- Cross-cutting feature\n- Security + functionality\n- Multiple file changes\n→ **Auto-dispatch:** Primary agent + optional specialists\n\n### Complex (3+ domains, complex requirements)\n- Complete new module\n- System redesign\n- Multi-domain integration\n→ **Requires:** master-orchestrator with sub-agents\n\n## Progressive Context Loading\n\nRouter uses 3 levels for skills:\n\n### Level 1: Always Load\n- Core principles (2-5KB)\n- Quick reference\n- Essential patterns\n\n### Level 2: Load on Request\n- Detailed patterns (10-15KB)\n- Complete examples\n- Architecture guidance\n\n### Level 3: Full Context\n- All scripts\n- Templates\n- Automation tools\n\n**Default:** Router loads Level 1 for all matched skills\n**Escalation:** Request Level 2\u002F3 if needed\n\n## Example Routing Scenarios\n\n### Example 1: Simple Bug Fix\n```\nUser: \"Fix deze error in login.ts\"\n\nRouter Analysis:\n  Intent: Bug fixing\n  Complexity: SIMPLE\n  Domains: debugging, backend\n\nAuto-Loaded:\n  - systematic-debugging skill\n  - testing-fundamentals skill\n\nAuto-Dispatched:\n  - senior-fullstack-developer\n\nOptional:\n  - qa-testing-engineer (regression tests)\n```\n\n### Example 2: Authentication System\n```\nUser: \"Maak een login systeem met registratie\"\n\nRouter Analysis:\n  Intent: User authentication\n  Complexity: HIGH\n  Domains: security, backend, frontend\n\nAuto-Loaded:\n  - security-essentials skill\n  - backend-development-patterns skill\n  - testing-fundamentals skill\n\nAuto-Dispatched:\n  - backend-specialist (primary)\n\nOptional:\n  - security-specialist (OWASP review)\n  - frontend-specialist (login UI)\n  - qa-testing-engineer (security tests)\n\nDocs Loaded:\n  - docs\u002Fsecurity.md\n  - docs\u002Fbackend.md\n```\n\n### Example 3: Complete Feature\n```\nUser: \"Bouw een dashboard met gebruikers, data visualisatie en export\"\n\nRouter Analysis:\n  Intent: Multi-domain feature\n  Complexity: COMPLEX\n  Domains: frontend, backend, data, ux\n\nAuto-Loaded:\n  - backend-development-patterns skill\n  - testing-fundamentals skill\n  - brainstorming skill\n\nAuto-Dispatched:\n  - master-orchestrator\n    Sub-agents (parallel):\n      - backend-specialist (API)\n      - frontend-specialist (Dashboard UI)\n      - data-engineer (Data pipeline)\n      - ux-design-expert (Charts\u002FUX)\n      - qa-testing-engineer (Test strategy)\n```\n\n### Example 4: Database Query\n```\nUser: \"Optimaliseer deze SQL query die te langzaam is\"\n\nRouter Analysis:\n  Intent: Database optimization\n  Complexity: MEDIUM\n  Domains: data-engineering, backend\n\nAuto-Loaded:\n  - backend-development-patterns skill\n\nAuto-Dispatched:\n  - data-engineer\n\nTools Activated:\n  - sql-universal-expert\n\nOptional:\n  - senior-fullstack-developer (code refactor)\n\nDocs Loaded:\n  - docs\u002Fbackend.md\n```\n\n## Usage\n\n### Automatic (Recommended)\nRouter activates automatically when:\n1. User asks question with 5+ words\n2. Question contains action verbs\n3. Question seems like a task (not just info)\n\nNo manual activation needed!\n\n### Manual Testing\nTest router analysis before dispatching:\n\n```bash\n# Analyze a question\nnode .claude\u002Fskills\u002Fintelligent-router\u002Fscripts\u002Fanalyze-intent.js analyze \"Maak een API\"\n\n# Get JSON output\nnode .claude\u002Fskills\u002Fintelligent-router\u002Fscripts\u002Fanalyze-intent.js analyze \"Fix bug\" --json\n```\n\n### Integration with Hooks\nRouter integrates via `.claude\u002Fhooks\u002Fpre-prompt.sh` (optional):\n```bash\n#!\u002Fbin\u002Fbash\n# Activate intelligent-router for every question\n# Router internally checks if it should activate\n```\n\n## Configuration\n\n### Customize Routing Matrix\nEdit `routing-matrix.json` to:\n- Add new routes\n- Modify trigger keywords\n- Adjust priorities\n- Add custom agents\u002Fskills\n\n### Customize Auto-Detect\nEdit `auto_detect_config` in routing-matrix.json:\n```json\n{\n  \"min_word_count\": 5,\n  \"action_verbs\": [\"maak\", \"bouw\", \"fix\", ...],\n  \"skip_keywords\": [\"wat is\", \"hoe werkt\", ...],\n  \"always_check_memory\": true\n}\n```\n\n### Complexity Thresholds\nAdjust in `complexity_thresholds`:\n```json\n{\n  \"simple\": {\n    \"max_words\": 10,\n    \"max_domains\": 1,\n    \"auto_dispatch\": true\n  },\n  ...\n}\n```\n\n## Router Decision Tree\n\n```\nUser Question\n    ↓\n[Should Activate?]\n    ├─ No → Normal response (skip router)\n    └─ Yes → Continue\n         ↓\n    [Find Matches]\n         ↓\n    [No Matches?]\n         ├─ Yes → Normal response\n         └─ No → Continue\n              ↓\n         [Analyze Complexity]\n              ↓\n         [Simple\u002FMedium\u002FHigh] → Auto-dispatch primary agent\n         [Complex] → Dispatch master-orchestrator\n              ↓\n         [Display Analysis]\n              ↓\n         [Execute Dispatch]\n```\n\n## Best Practices\n\n### For Users\n- ✅ Be specific in your questions (better matching)\n- ✅ Use action verbs when you want work done\n- ✅ Trust the router's suggestions\n- ✅ Dispatch optional agents if they make sense\n\n### For Developers\n- ✅ Keep routing-matrix.json updated\n- ✅ Add new routes for new capabilities\n- ✅ Test routes with analyze-intent.js\n- ✅ Monitor which routes get triggered most\n- ✅ Refine trigger keywords based on usage\n\n## Troubleshooting\n\n### Router Not Activating\n```bash\n# Check question meets criteria\nnode scripts\u002Fanalyze-intent.js analyze \"your question\"\n\n# If \"activate: false\", question too simple\n# Solution: Add more context or action verbs\n```\n\n### Wrong Agent Dispatched\n```bash\n# Check routing matrix matches\ncat routing-matrix.json | grep -A 5 \"your_keyword\"\n\n# Update triggers if needed\n```\n\n### Skills Not Loading\n```bash\n# Verify skills exist\nnode ..\u002Fskill-loader.js list\n\n# Check skill names in routing-matrix.json match\n```\n\n## Metrics & Improvement\n\nTrack router effectiveness:\n- **Activation rate** - How often it activates vs skips\n- **Accuracy** - Did it pick right agent\u002Fskills?\n- **User satisfaction** - Did suggestions help?\n- **Iteration count** - How many back-and-forth needed?\n\nStore in: `.claude-memory\u002Frouter-metrics.md`\n\n## Version History\n\n### v1.0.0 (Initial Release)\n- Smart auto-detect activation\n- 20+ predefined routes\n- Complexity assessment\n- Multi-level skill loading\n- Transparent reporting\n- Optional agent suggestions\n\n## Future Enhancements\n\nPlanned features:\n- [ ] Learning from past routing decisions\n- [ ] User preference tracking\n- [ ] Route effectiveness scoring\n- [ ] Dynamic route creation\n- [ ] Integration with episodic-memory for pattern learning\n- [ ] Web UI for route visualization\n\n## Resources\n\n- **Routing Matrix:** `routing-matrix.json`\n- **Intent Analyzer:** `scripts\u002Fanalyze-intent.js`\n- **Examples:** `examples\u002Frouting-scenarios.md`\n- **Tests:** `examples\u002Ftest-cases.md`\n\n---\n\n**Version:** 1.0.0\n**Author:** CLAUDE Framework Team\n**License:** MIT\n**Compatibility:** Claude Code 1.0+, Claude 3.5 Sonnet+\n",{"name":5,"agents":47,"version":48,"triggers":49,"activation":50,"description":7,"context_levels":51},[],"1.0.0",[],"smart-auto-detect",{"full":52,"minimal":53,"detailed":54},"Scripts and testing tools","Router logic and decision framework","Complete routing matrix and examples","main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__Primadetaautomation--intelligent-router",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add JSGforever\u002Fskillguard --skill intelligent-router",{"tool":68,"command":69},"bunx","bunx skills add JSGforever\u002Fskillguard --skill intelligent-router",{"tool":71,"command":72},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill intelligent-router","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Primadetaautomation--intelligent-router\u002FSKILL.md",true,[76,82,86,90],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"examples\u002Frouting-scenarios.md","REFERENCE","参考文档",6654,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Primadetaautomation--intelligent-router\u002Fexamples\u002Frouting-scenarios.md",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"README.md",8954,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Primadetaautomation--intelligent-router\u002FREADME.md",{"path":87,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":88,"sourceHtmlUrl":89},"routing-matrix.json",12687,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Primadetaautomation--intelligent-router\u002Frouting-matrix.json",{"path":91,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Fanalyze-intent.js","SCRIPT","脚本",12361,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Primadetaautomation--intelligent-router\u002Fscripts\u002Fanalyze-intent.js",[97,126,142,169,190,211],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":106,"publishedAt":42},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[103],{"categoryNo":104,"categoryName":105,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,37,125],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","when","review","malicious","permissions","exposure","audit","safe",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":130,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":138,"publishedAt":42},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[133],{"categoryNo":134,"categoryName":135,"taxonomyType":136,"taxonomyTypeDesc":137},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[139,140,141],"data","data exfiltrator","files",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":42},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","reliability","video editing","performance","conflict resolution","presence","access","apps","updates","Bash","activate","optimizer","react","streaming",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":178,"publishedAt":42},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[175],{"categoryNo":176,"categoryName":177,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[158,179,166,167,180,181,182,183,184,185,149,186,187,162,164,188,165,168,24,189],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","strategies",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":197,"publishedAt":42},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[196],{"categoryNo":176,"categoryName":177,"taxonomyType":20,"taxonomyTypeDesc":21},[198,168,199,200,201,202,158,149,203,204,205,164,165,166,206,167,207,208,209,210],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":215,"categories":216,"keywords":222,"publishedAt":42},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[217,218,221],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":219,"categoryName":220,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":104,"categoryName":105,"taxonomyType":20,"taxonomyTypeDesc":21},[223,224,225,226,227,228,229,156,184,41,230,231,165,189,232,210,233,234,235,236],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","ci","workflows","run","release","write","edit","git"]