[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DER5JHTW3GP0A51EVZP6R7":3,"skill-same:01M6DER5JHTW3GP0A51EVZP6R7":86},{"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":18,"publishedAt":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M6DER5JHTW3GP0A51EVZP6R7","intake",null,"Capture a story idea from conversation into the backlog as a stub — fast context preservation without the full create-story pipeline.","iamsteveholmes\u002Fmomentum","iamsteveholmes","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F92353?v=4","01M6DENK56DRSF72CJ6FJQ4RT1","Steve Holmes","01M6DENK9KCZRYFFEB0M689F7D",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fintake\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32],"create","fast","pipeline","capture","context","Story","idea","conversation","backlog","full","as","preservation","stub","context preservation","2026-11-10 10:12:30",false,"---\nnamespace: aiwg\nname: nl-router\nplatforms: [all]\ndescription: Route natural language requests to appropriate skills and workflows by parsing intent and matching trigger patterns\n---\n\n# nl-router\n\nRoute natural language requests to appropriate skills and workflows.\n\n## Triggers\n\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"route this\" → explicit NL routing request\n- \"what skill handles [X]\" → skill discovery\n\n## Purpose\n\nThis skill interprets natural language requests and routes them to the appropriate skills or workflows by:\n- Parsing user intent from natural language\n- Matching to available skills and commands\n- Handling ambiguous requests with clarification\n- Suggesting relevant actions\n- Learning from routing patterns\n\n## Behavior\n\nWhen triggered, this skill:\n\n1. **Parses user intent**:\n   - Extract action verbs\n   - Identify objects\u002Ftargets\n   - Detect qualifiers and constraints\n   - Recognize context from conversation\n\n2. **Matches to skills**:\n   - Search skill trigger patterns\n   - Score match confidence\n   - Consider context relevance\n\n3. **Routes request**:\n   - High confidence: Route directly\n   - Medium confidence: Confirm with user\n   - Low confidence: Offer options\n   - No match: Suggest alternatives\n\n4. **Handles follow-ups**:\n   - Track routing context\n   - Enable corrections\n   - Learn from feedback\n\n## Routing Patterns\n\n### SDLC Workflows\n\n```yaml\nsdlc_patterns:\n  phase_transitions:\n    patterns:\n      - \"transition to {phase}\"\n      - \"move to {phase}\"\n      - \"start {phase}\"\n      - \"begin {phase}\"\n      - \"ready for {phase}\"\n    routes_to: flow-{from}-to-{to}\n    extract: [from_phase, to_phase]\n\n  gate_checks:\n    patterns:\n      - \"check gate\"\n      - \"can we transition\"\n      - \"ready for {phase}\"\n      - \"validate {gate}\"\n      - \"gate check\"\n    routes_to: gate-evaluation\n    extract: [gate_name, phase]\n\n  project_status:\n    patterns:\n      - \"where are we\"\n      - \"what's next\"\n      - \"project status\"\n      - \"current phase\"\n      - \"status update\"\n    routes_to: project-awareness\n    action: status_report\n\n  risk_management:\n    patterns:\n      - \"update risks\"\n      - \"risk review\"\n      - \"new risk\"\n      - \"mitigate {risk}\"\n    routes_to: risk-cycle\n    extract: [risk_id, action]\n\n  security_review:\n    patterns:\n      - \"security review\"\n      - \"run security\"\n      - \"threat model\"\n      - \"security scan\"\n    routes_to: security-assessment\n    extract: [scope]\n```\n\n### Artifact Operations\n\n```yaml\nartifact_patterns:\n  create:\n    patterns:\n      - \"create {artifact}\"\n      - \"generate {artifact}\"\n      - \"new {artifact}\"\n      - \"draft {artifact}\"\n    routes_to: artifact-orchestration\n    extract: [artifact_type]\n\n  review:\n    patterns:\n      - \"review {artifact}\"\n      - \"check {artifact}\"\n      - \"validate {artifact}\"\n    routes_to: artifact_type_specific_review\n    extract: [artifact_type]\n\n  trace:\n    patterns:\n      - \"trace {requirement}\"\n      - \"what implements {id}\"\n      - \"coverage for {id}\"\n    routes_to: traceability-check\n    extract: [requirement_id]\n```\n\n### Marketing Workflows\n\n```yaml\nmarketing_patterns:\n  brand_review:\n    patterns:\n      - \"brand review\"\n      - \"check brand compliance\"\n      - \"is this on-brand\"\n      - \"brand audit\"\n    routes_to: brand-compliance\n    extract: [asset_path]\n\n  approval:\n    patterns:\n      - \"submit for approval\"\n      - \"approval workflow\"\n      - \"get sign-off\"\n      - \"approval status\"\n    routes_to: approval-workflow\n    extract: [asset_id]\n\n  performance:\n    patterns:\n      - \"how are we doing\"\n      - \"marketing report\"\n      - \"performance summary\"\n      - \"campaign results\"\n    routes_to: performance-digest\n    extract: [period, channel]\n\n  competitive:\n    patterns:\n      - \"competitor analysis\"\n      - \"what are competitors doing\"\n      - \"competitive landscape\"\n    routes_to: competitive-intel\n    extract: [competitor_name]\n```\n\n### Research & Investigation\n\n```yaml\nresearch_patterns:\n  lookup:\n    patterns:\n      - \"look up {topic}\"\n      - \"what does {thing} do\"\n      - \"how does {thing} work\"\n      - \"find documentation for {topic}\"\n      - \"search for {query}\"\n      - \"check the docs for {topic}\"\n      - \"read about {topic}\"\n      - \"research {topic}\"\n    routes_to: research-investigation\n    extract: [topic, scope]\n    rule_activation: research-before-decision\n\n  codebase_exploration:\n    patterns:\n      - \"how is {feature} implemented\"\n      - \"where is {thing} defined\"\n      - \"find {pattern} in the codebase\"\n      - \"what pattern does this project use for {thing}\"\n      - \"show me examples of {pattern}\"\n    routes_to: codebase-exploration\n    extract: [feature, pattern]\n    rule_activation: research-before-decision\n\n  error_investigation:\n    patterns:\n      - \"why is {thing} failing\"\n      - \"investigate {error}\"\n      - \"debug {issue}\"\n      - \"what's causing {problem}\"\n      - \"root cause of {error}\"\n    routes_to: error-diagnosis\n    extract: [error, context]\n    rule_activation: research-before-decision\n```\n\n### Planning & Strategy\n\n```yaml\nplanning_patterns:\n  approach_planning:\n    patterns:\n      - \"plan how to {task}\"\n      - \"design approach for {task}\"\n      - \"think through {task}\"\n      - \"strategize {task}\"\n      - \"how should I approach {task}\"\n      - \"what's the best way to {task}\"\n    routes_to: approach-planning\n    extract: [task, constraints]\n\n  implementation_planning:\n    patterns:\n      - \"plan the implementation of {feature}\"\n      - \"break down {task}\"\n      - \"outline the steps for {task}\"\n      - \"what do I need to do for {task}\"\n    routes_to: implementation-planning\n    extract: [feature, scope]\n\n  decision_support:\n    patterns:\n      - \"help me decide between {options}\"\n      - \"compare {a} and {b}\"\n      - \"trade-off analysis for {topic}\"\n      - \"which should I choose\"\n      - \"pros and cons of {approach}\"\n    routes_to: decision-support\n    extract: [decision_topic, options]\n```\n\n### Clarification & Recovery\n\n```yaml\nclarification_patterns:\n  re_read:\n    patterns:\n      - \"re-read my instructions\"\n      - \"that's not what I asked\"\n      - \"I said {correction}\"\n      - \"go back and read what I wrote\"\n      - \"you missed {thing}\"\n      - \"I already told you {thing}\"\n    routes_to: instruction-reparse\n    rule_activation: instruction-comprehension\n    priority: high\n\n  confusion:\n    patterns:\n      - \"I'm confused about {topic}\"\n      - \"can you explain {thing}\"\n      - \"what do you mean by {thing}\"\n      - \"I don't understand {thing}\"\n    routes_to: clarification\n    extract: [topic]\n\n  correction:\n    patterns:\n      - \"no, I meant {correction}\"\n      - \"not {wrong}, use {right}\"\n      - \"change that to {correction}\"\n      - \"that's wrong, it should be {correction}\"\n    routes_to: instruction-correction\n    rule_activation: instruction-comprehension\n    priority: high\n    extract: [correction]\n```\n\n### Utility Operations\n\n```yaml\nutility_patterns:\n  decision:\n    patterns:\n      - \"help me decide\"\n      - \"compare options\"\n      - \"trade-off analysis\"\n      - \"which should I choose\"\n    routes_to: decision-support\n    extract: [decision_topic]\n\n  test_coverage:\n    patterns:\n      - \"test coverage\"\n      - \"what's not tested\"\n      - \"coverage report\"\n    routes_to: test-coverage\n    extract: [scope]\n\n  incident:\n    patterns:\n      - \"production issue\"\n      - \"system down\"\n      - \"incident\"\n      - \"P0\"\n      - \"SEV1\"\n    routes_to: incident-triage\n    priority: urgent\n\n  config:\n    patterns:\n      - \"validate config\"\n      - \"check setup\"\n      - \"config issues\"\n    routes_to: config-validator\n```\n\n## Intent Classification\n\n### Action Verbs\n\n```yaml\naction_verbs:\n  create:\n    words: [create, generate, new, draft, make, build, write]\n    intent: creation\n\n  review:\n    words: [review, check, validate, verify, audit, assess]\n    intent: validation\n\n  update:\n    words: [update, change, modify, edit, revise]\n    intent: modification\n\n  delete:\n    words: [delete, remove, deprecate, archive]\n    intent: removal\n\n  analyze:\n    words: [analyze, understand, explain, investigate, explore]\n    intent: analysis\n\n  research:\n    words: [research, look up, find out, search for, read about, check docs]\n    intent: investigation\n    rule_activation: research-before-decision\n\n  plan:\n    words: [plan, design, strategize, outline, think through, approach]\n    intent: planning\n\n  clarify:\n    words: [clarify, re-read, explain, what did I, I said, not what I asked]\n    intent: clarification\n    rule_activation: instruction-comprehension\n\n  transition:\n    words: [transition, move, progress, advance, start, begin]\n    intent: workflow_progression\n\n  compare:\n    words: [compare, contrast, versus, vs, trade-off]\n    intent: comparison\n```\n\n### Object Mappings\n\n```yaml\nobject_mappings:\n  artifacts:\n    sad: software-architecture-document\n    adr: architecture-decision-record\n    test_plan: test-plan\n    requirements: software-requirements-spec\n    threat_model: threat-model\n\n  phases:\n    inception: inception\n    elaboration: elaboration\n    construction: construction\n    transition: transition\n    production: production\n\n  gates:\n    lom: lifecycle-objective-milestone\n    abm: architecture-baseline-milestone\n    ioc: initial-operational-capability\n    prm: product-release-milestone\n```\n\n## Confidence Scoring\n\n```yaml\nconfidence_levels:\n  high:\n    threshold: 0.85\n    action: route_directly\n    example: \"create SAD\" → artifact-orchestration (SAD)\n\n  medium:\n    threshold: 0.60\n    action: confirm_before_routing\n    example: \"review this\" → \"Did you mean brand review or code review?\"\n\n  low:\n    threshold: 0.40\n    action: offer_options\n    example: \"help\" → \"Here are things I can help with...\"\n\n  none:\n    threshold: 0.0\n    action: clarify\n    example: \"do the thing\" → \"I'm not sure what you'd like to do. Can you clarify?\"\n```\n\n## Routing Response Format\n\n### Direct Route (High Confidence)\n\n```yaml\nrouting_response:\n  confidence: high\n  matched_skill: artifact-orchestration\n  extracted_params:\n    artifact_type: sad\n  message: \"Creating Software Architecture Document...\"\n  next_action: invoke_skill\n```\n\n### Confirmation Route (Medium Confidence)\n\n```yaml\nrouting_response:\n  confidence: medium\n  candidates:\n    - skill: brand-compliance\n      confidence: 0.72\n      reason: \"brand\" keyword matched\n    - skill: code-reviewer\n      confidence: 0.65\n      reason: \"review\" action detected\n  message: \"I found multiple possible actions. Did you mean...\"\n  next_action: await_clarification\n```\n\n### Options Route (Low Confidence)\n\n```yaml\nrouting_response:\n  confidence: low\n  suggestions:\n    - category: Documentation\n      actions: [create SAD, generate ADR, draft requirements]\n    - category: Review\n      actions: [brand review, code review, security review]\n    - category: Status\n      actions: [project status, coverage report, risk review]\n  message: \"I'm not sure what you'd like to do. Here are some options...\"\n  next_action: await_selection\n```\n\n## Usage Examples\n\n### Clear Intent\n\n```\nUser: \"Generate the architecture document\"\n\nSkill routes:\n- Intent: create\n- Object: architecture document → SAD\n- Confidence: 0.95 (high)\n\nOutput:\n\"Routing to artifact-orchestration to generate Software Architecture Document.\n\nStarting SAD generation...\"\n\n[Invokes artifact-orchestration with artifact_type=sad]\n```\n\n### Ambiguous Intent\n\n```\nUser: \"Review the landing page\"\n\nSkill analyzes:\n- Intent: review\n- Object: landing page\n- Possible skills: brand-compliance, qa-protocol, code-reviewer\n- Confidence: 0.65 (medium)\n\nOutput:\n\"I found a few review options for 'landing page':\n\n1. **Brand Review** - Check brand compliance\n2. **QA Review** - Check quality and specs\n3. **Content Review** - Check copy and messaging\n\nWhich would you like?\"\n```\n\n### Unclear Intent\n\n```\nUser: \"Help with the project\"\n\nSkill analyzes:\n- Intent: unclear\n- Object: project (generic)\n- Confidence: 0.30 (low)\n\nOutput:\n\"I can help with many things! Here are some common actions:\n\n**Project Status**\n- Where are we? → Project status\n- What's next? → Phase recommendations\n\n**Documentation**\n- Create SAD → Architecture document\n- Generate ADR → Decision record\n\n**Reviews**\n- Security review → Threat assessment\n- Brand review → Compliance check\n\nWhat would you like to do?\"\n```\n\n### Contextual Routing\n\n```\nUser: (After discussing a bug) \"Create a ticket for this\"\n\nSkill analyzes:\n- Context: Bug discussion\n- Intent: create\n- Object: ticket\n- Inference: incident or defect ticket\n- Confidence: 0.80 (high with context)\n\nOutput:\n\"Based on our discussion, I'll create an incident ticket for the authentication issue.\n\nRouting to incident-triage...\"\n```\n\n## Integration\n\nThis skill is the central router and integrates with all other skills:\n- All SDLC skills\n- All MMK skills\n- All utility skills\n- All workflow commands\n\n## Configuration\n\n### Custom Patterns\n\nAdd custom routing patterns in `.aiwg\u002Fconfig\u002Frouting.yaml`:\n\n```yaml\ncustom_patterns:\n  - trigger: \"standup update\"\n    routes_to: project-awareness\n    action: standup_summary\n\n  - trigger: \"weekly report\"\n    routes_to: performance-digest\n    params:\n      period: weekly\n```\n\n### Priority Overrides\n\n```yaml\npriority_overrides:\n  # Urgent patterns always match first\n  urgent:\n    - \"production down\"\n    - \"SEV1\"\n    - \"security breach\"\n\n  # Exact matches before fuzzy\n  exact_first: true\n\n  # Prefer skill in current context\n  context_boost: 0.15\n```\n\n## Output Locations\n\n- Routing logs: `.aiwg\u002Flogs\u002Frouting\u002F`\n- Pattern analytics: `.aiwg\u002Fanalytics\u002Frouting-patterns.json`\n\n## References\n\n- Skill catalog: Available skills from all frameworks\n- Command catalog: Available workflow commands\n- Translation table: docs\u002Fsimple-language-translations.md\n","# nl-router\n\nRoute natural language requests to appropriate skills and workflows.\n\n## Triggers\n\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"route this\" → explicit NL routing request\n- \"what skill handles [X]\" → skill discovery\n\n## Purpose\n\nThis skill interprets natural language requests and routes them to the appropriate skills or workflows by:\n- Parsing user intent from natural language\n- Matching to available skills and commands\n- Handling ambiguous requests with clarification\n- Suggesting relevant actions\n- Learning from routing patterns\n\n## Behavior\n\nWhen triggered, this skill:\n\n1. **Parses user intent**:\n   - Extract action verbs\n   - Identify objects\u002Ftargets\n   - Detect qualifiers and constraints\n   - Recognize context from conversation\n\n2. **Matches to skills**:\n   - Search skill trigger patterns\n   - Score match confidence\n   - Consider context relevance\n\n3. **Routes request**:\n   - High confidence: Route directly\n   - Medium confidence: Confirm with user\n   - Low confidence: Offer options\n   - No match: Suggest alternatives\n\n4. **Handles follow-ups**:\n   - Track routing context\n   - Enable corrections\n   - Learn from feedback\n\n## Routing Patterns\n\n### SDLC Workflows\n\n```yaml\nsdlc_patterns:\n  phase_transitions:\n    patterns:\n      - \"transition to {phase}\"\n      - \"move to {phase}\"\n      - \"start {phase}\"\n      - \"begin {phase}\"\n      - \"ready for {phase}\"\n    routes_to: flow-{from}-to-{to}\n    extract: [from_phase, to_phase]\n\n  gate_checks:\n    patterns:\n      - \"check gate\"\n      - \"can we transition\"\n      - \"ready for {phase}\"\n      - \"validate {gate}\"\n      - \"gate check\"\n    routes_to: gate-evaluation\n    extract: [gate_name, phase]\n\n  project_status:\n    patterns:\n      - \"where are we\"\n      - \"what's next\"\n      - \"project status\"\n      - \"current phase\"\n      - \"status update\"\n    routes_to: project-awareness\n    action: status_report\n\n  risk_management:\n    patterns:\n      - \"update risks\"\n      - \"risk review\"\n      - \"new risk\"\n      - \"mitigate {risk}\"\n    routes_to: risk-cycle\n    extract: [risk_id, action]\n\n  security_review:\n    patterns:\n      - \"security review\"\n      - \"run security\"\n      - \"threat model\"\n      - \"security scan\"\n    routes_to: security-assessment\n    extract: [scope]\n```\n\n### Artifact Operations\n\n```yaml\nartifact_patterns:\n  create:\n    patterns:\n      - \"create {artifact}\"\n      - \"generate {artifact}\"\n      - \"new {artifact}\"\n      - \"draft {artifact}\"\n    routes_to: artifact-orchestration\n    extract: [artifact_type]\n\n  review:\n    patterns:\n      - \"review {artifact}\"\n      - \"check {artifact}\"\n      - \"validate {artifact}\"\n    routes_to: artifact_type_specific_review\n    extract: [artifact_type]\n\n  trace:\n    patterns:\n      - \"trace {requirement}\"\n      - \"what implements {id}\"\n      - \"coverage for {id}\"\n    routes_to: traceability-check\n    extract: [requirement_id]\n```\n\n### Marketing Workflows\n\n```yaml\nmarketing_patterns:\n  brand_review:\n    patterns:\n      - \"brand review\"\n      - \"check brand compliance\"\n      - \"is this on-brand\"\n      - \"brand audit\"\n    routes_to: brand-compliance\n    extract: [asset_path]\n\n  approval:\n    patterns:\n      - \"submit for approval\"\n      - \"approval workflow\"\n      - \"get sign-off\"\n      - \"approval status\"\n    routes_to: approval-workflow\n    extract: [asset_id]\n\n  performance:\n    patterns:\n      - \"how are we doing\"\n      - \"marketing report\"\n      - \"performance summary\"\n      - \"campaign results\"\n    routes_to: performance-digest\n    extract: [period, channel]\n\n  competitive:\n    patterns:\n      - \"competitor analysis\"\n      - \"what are competitors doing\"\n      - \"competitive landscape\"\n    routes_to: competitive-intel\n    extract: [competitor_name]\n```\n\n### Research & Investigation\n\n```yaml\nresearch_patterns:\n  lookup:\n    patterns:\n      - \"look up {topic}\"\n      - \"what does {thing} do\"\n      - \"how does {thing} work\"\n      - \"find documentation for {topic}\"\n      - \"search for {query}\"\n      - \"check the docs for {topic}\"\n      - \"read about {topic}\"\n      - \"research {topic}\"\n    routes_to: research-investigation\n    extract: [topic, scope]\n    rule_activation: research-before-decision\n\n  codebase_exploration:\n    patterns:\n      - \"how is {feature} implemented\"\n      - \"where is {thing} defined\"\n      - \"find {pattern} in the codebase\"\n      - \"what pattern does this project use for {thing}\"\n      - \"show me examples of {pattern}\"\n    routes_to: codebase-exploration\n    extract: [feature, pattern]\n    rule_activation: research-before-decision\n\n  error_investigation:\n    patterns:\n      - \"why is {thing} failing\"\n      - \"investigate {error}\"\n      - \"debug {issue}\"\n      - \"what's causing {problem}\"\n      - \"root cause of {error}\"\n    routes_to: error-diagnosis\n    extract: [error, context]\n    rule_activation: research-before-decision\n```\n\n### Planning & Strategy\n\n```yaml\nplanning_patterns:\n  approach_planning:\n    patterns:\n      - \"plan how to {task}\"\n      - \"design approach for {task}\"\n      - \"think through {task}\"\n      - \"strategize {task}\"\n      - \"how should I approach {task}\"\n      - \"what's the best way to {task}\"\n    routes_to: approach-planning\n    extract: [task, constraints]\n\n  implementation_planning:\n    patterns:\n      - \"plan the implementation of {feature}\"\n      - \"break down {task}\"\n      - \"outline the steps for {task}\"\n      - \"what do I need to do for {task}\"\n    routes_to: implementation-planning\n    extract: [feature, scope]\n\n  decision_support:\n    patterns:\n      - \"help me decide between {options}\"\n      - \"compare {a} and {b}\"\n      - \"trade-off analysis for {topic}\"\n      - \"which should I choose\"\n      - \"pros and cons of {approach}\"\n    routes_to: decision-support\n    extract: [decision_topic, options]\n```\n\n### Clarification & Recovery\n\n```yaml\nclarification_patterns:\n  re_read:\n    patterns:\n      - \"re-read my instructions\"\n      - \"that's not what I asked\"\n      - \"I said {correction}\"\n      - \"go back and read what I wrote\"\n      - \"you missed {thing}\"\n      - \"I already told you {thing}\"\n    routes_to: instruction-reparse\n    rule_activation: instruction-comprehension\n    priority: high\n\n  confusion:\n    patterns:\n      - \"I'm confused about {topic}\"\n      - \"can you explain {thing}\"\n      - \"what do you mean by {thing}\"\n      - \"I don't understand {thing}\"\n    routes_to: clarification\n    extract: [topic]\n\n  correction:\n    patterns:\n      - \"no, I meant {correction}\"\n      - \"not {wrong}, use {right}\"\n      - \"change that to {correction}\"\n      - \"that's wrong, it should be {correction}\"\n    routes_to: instruction-correction\n    rule_activation: instruction-comprehension\n    priority: high\n    extract: [correction]\n```\n\n### Utility Operations\n\n```yaml\nutility_patterns:\n  decision:\n    patterns:\n      - \"help me decide\"\n      - \"compare options\"\n      - \"trade-off analysis\"\n      - \"which should I choose\"\n    routes_to: decision-support\n    extract: [decision_topic]\n\n  test_coverage:\n    patterns:\n      - \"test coverage\"\n      - \"what's not tested\"\n      - \"coverage report\"\n    routes_to: test-coverage\n    extract: [scope]\n\n  incident:\n    patterns:\n      - \"production issue\"\n      - \"system down\"\n      - \"incident\"\n      - \"P0\"\n      - \"SEV1\"\n    routes_to: incident-triage\n    priority: urgent\n\n  config:\n    patterns:\n      - \"validate config\"\n      - \"check setup\"\n      - \"config issues\"\n    routes_to: config-validator\n```\n\n## Intent Classification\n\n### Action Verbs\n\n```yaml\naction_verbs:\n  create:\n    words: [create, generate, new, draft, make, build, write]\n    intent: creation\n\n  review:\n    words: [review, check, validate, verify, audit, assess]\n    intent: validation\n\n  update:\n    words: [update, change, modify, edit, revise]\n    intent: modification\n\n  delete:\n    words: [delete, remove, deprecate, archive]\n    intent: removal\n\n  analyze:\n    words: [analyze, understand, explain, investigate, explore]\n    intent: analysis\n\n  research:\n    words: [research, look up, find out, search for, read about, check docs]\n    intent: investigation\n    rule_activation: research-before-decision\n\n  plan:\n    words: [plan, design, strategize, outline, think through, approach]\n    intent: planning\n\n  clarify:\n    words: [clarify, re-read, explain, what did I, I said, not what I asked]\n    intent: clarification\n    rule_activation: instruction-comprehension\n\n  transition:\n    words: [transition, move, progress, advance, start, begin]\n    intent: workflow_progression\n\n  compare:\n    words: [compare, contrast, versus, vs, trade-off]\n    intent: comparison\n```\n\n### Object Mappings\n\n```yaml\nobject_mappings:\n  artifacts:\n    sad: software-architecture-document\n    adr: architecture-decision-record\n    test_plan: test-plan\n    requirements: software-requirements-spec\n    threat_model: threat-model\n\n  phases:\n    inception: inception\n    elaboration: elaboration\n    construction: construction\n    transition: transition\n    production: production\n\n  gates:\n    lom: lifecycle-objective-milestone\n    abm: architecture-baseline-milestone\n    ioc: initial-operational-capability\n    prm: product-release-milestone\n```\n\n## Confidence Scoring\n\n```yaml\nconfidence_levels:\n  high:\n    threshold: 0.85\n    action: route_directly\n    example: \"create SAD\" → artifact-orchestration (SAD)\n\n  medium:\n    threshold: 0.60\n    action: confirm_before_routing\n    example: \"review this\" → \"Did you mean brand review or code review?\"\n\n  low:\n    threshold: 0.40\n    action: offer_options\n    example: \"help\" → \"Here are things I can help with...\"\n\n  none:\n    threshold: 0.0\n    action: clarify\n    example: \"do the thing\" → \"I'm not sure what you'd like to do. Can you clarify?\"\n```\n\n## Routing Response Format\n\n### Direct Route (High Confidence)\n\n```yaml\nrouting_response:\n  confidence: high\n  matched_skill: artifact-orchestration\n  extracted_params:\n    artifact_type: sad\n  message: \"Creating Software Architecture Document...\"\n  next_action: invoke_skill\n```\n\n### Confirmation Route (Medium Confidence)\n\n```yaml\nrouting_response:\n  confidence: medium\n  candidates:\n    - skill: brand-compliance\n      confidence: 0.72\n      reason: \"brand\" keyword matched\n    - skill: code-reviewer\n      confidence: 0.65\n      reason: \"review\" action detected\n  message: \"I found multiple possible actions. Did you mean...\"\n  next_action: await_clarification\n```\n\n### Options Route (Low Confidence)\n\n```yaml\nrouting_response:\n  confidence: low\n  suggestions:\n    - category: Documentation\n      actions: [create SAD, generate ADR, draft requirements]\n    - category: Review\n      actions: [brand review, code review, security review]\n    - category: Status\n      actions: [project status, coverage report, risk review]\n  message: \"I'm not sure what you'd like to do. Here are some options...\"\n  next_action: await_selection\n```\n\n## Usage Examples\n\n### Clear Intent\n\n```\nUser: \"Generate the architecture document\"\n\nSkill routes:\n- Intent: create\n- Object: architecture document → SAD\n- Confidence: 0.95 (high)\n\nOutput:\n\"Routing to artifact-orchestration to generate Software Architecture Document.\n\nStarting SAD generation...\"\n\n[Invokes artifact-orchestration with artifact_type=sad]\n```\n\n### Ambiguous Intent\n\n```\nUser: \"Review the landing page\"\n\nSkill analyzes:\n- Intent: review\n- Object: landing page\n- Possible skills: brand-compliance, qa-protocol, code-reviewer\n- Confidence: 0.65 (medium)\n\nOutput:\n\"I found a few review options for 'landing page':\n\n1. **Brand Review** - Check brand compliance\n2. **QA Review** - Check quality and specs\n3. **Content Review** - Check copy and messaging\n\nWhich would you like?\"\n```\n\n### Unclear Intent\n\n```\nUser: \"Help with the project\"\n\nSkill analyzes:\n- Intent: unclear\n- Object: project (generic)\n- Confidence: 0.30 (low)\n\nOutput:\n\"I can help with many things! Here are some common actions:\n\n**Project Status**\n- Where are we? → Project status\n- What's next? → Phase recommendations\n\n**Documentation**\n- Create SAD → Architecture document\n- Generate ADR → Decision record\n\n**Reviews**\n- Security review → Threat assessment\n- Brand review → Compliance check\n\nWhat would you like to do?\"\n```\n\n### Contextual Routing\n\n```\nUser: (After discussing a bug) \"Create a ticket for this\"\n\nSkill analyzes:\n- Context: Bug discussion\n- Intent: create\n- Object: ticket\n- Inference: incident or defect ticket\n- Confidence: 0.80 (high with context)\n\nOutput:\n\"Based on our discussion, I'll create an incident ticket for the authentication issue.\n\nRouting to incident-triage...\"\n```\n\n## Integration\n\nThis skill is the central router and integrates with all other skills:\n- All SDLC skills\n- All MMK skills\n- All utility skills\n- All workflow commands\n\n## Configuration\n\n### Custom Patterns\n\nAdd custom routing patterns in `.aiwg\u002Fconfig\u002Frouting.yaml`:\n\n```yaml\ncustom_patterns:\n  - trigger: \"standup update\"\n    routes_to: project-awareness\n    action: standup_summary\n\n  - trigger: \"weekly report\"\n    routes_to: performance-digest\n    params:\n      period: weekly\n```\n\n### Priority Overrides\n\n```yaml\npriority_overrides:\n  # Urgent patterns always match first\n  urgent:\n    - \"production down\"\n    - \"SEV1\"\n    - \"security breach\"\n\n  # Exact matches before fuzzy\n  exact_first: true\n\n  # Prefer skill in current context\n  context_boost: 0.15\n```\n\n## Output Locations\n\n- Routing logs: `.aiwg\u002Flogs\u002Frouting\u002F`\n- Pattern analytics: `.aiwg\u002Fanalytics\u002Frouting-patterns.json`\n\n## References\n\n- Skill catalog: Available skills from all frameworks\n- Command catalog: Available workflow commands\n- Translation table: docs\u002Fsimple-language-translations.md\n",{"name":38,"namespace":39,"platforms":40,"description":42},"nl-router","aiwg",[41],"all","Route natural language requests to appropriate skills and workflows by parsing intent and matching trigger patterns","main","6754967c344ccb087a8de06972f55a41067b291b","skills\u002Fmomentum\u002Fskills\u002Fintake","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes","http:\u002F\u002Fcapitalcodemonkey.blogspot.com","2026-11-09 05:58:39",{"source":8,"skillName":38,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add iamsteveholmes\u002Fmomentum --skill nl-router",{"tool":56,"command":57},"bunx","bunx skills add iamsteveholmes\u002Fmomentum --skill nl-router",{"tool":59,"command":60},"pnpm","pnpm dlx skills add iamsteveholmes\u002Fmomentum --skill nl-router","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fintake\u002FSKILL.md",true,[64,70,74,78,82],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"evals\u002Feval-intake-captures-context.md","REFERENCE","参考文档",4298,"https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fintake\u002Fevals\u002Feval-intake-captures-context.md",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"evals\u002Feval-intake-routes-discovered-work-with-discovered-from.md",2716,"https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fintake\u002Fevals\u002Feval-intake-routes-discovered-work-with-discovered-from.md",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"evals\u002Feval-intake-runs-on-main-no-worktree.md",3838,"https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fintake\u002Fevals\u002Feval-intake-runs-on-main-no-worktree.md",{"path":79,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fstub-template.md",3545,"https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fintake\u002Freferences\u002Fstub-template.md",{"path":83,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":84,"sourceHtmlUrl":85},"workflow.md",9687,"https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fintake\u002Fworkflow.md",[87,108,125,146,163,181],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":33},"01M6DES6J0HGT27SEJJWF316FV","upstream-fix","Traces quality failures upstream to spec, rule, or workflow root cause. Proposes fixes at the right level.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fupstream-fix\u002FSKILL.md",[],[94,95,96,97,98,99,100,101,102,103,104,105,106,107],"upstream","upstream fix","fix","to spec","root cause","traces","fixes","at","high","root","rule","quality","workflow","spec",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":33},"01M6DES4A08NFWQM0AJBR2RRX5","triage","Dedup gate + batch-classify observations into five classes, enrich ARTIFACTs, batch-approve, delegate to intake\u002Fdecision or queue.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Ftriage\u002FSKILL.md",[],[110,115,5,116,117,118,119,120,102,121,122,123,124],"batch","artifacts","decision","queue","delegate","approve","observations","enrich","classify","gate",{"skillNo":126,"name":127,"nameZh":6,"description":128,"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":131,"publishedAt":33},"01M6DERYX8W6Z9Z4RM5V6E9HED","sprint-planning","Sprint planning — story selection, team composition, Gherkin specs, and visual companion plan gate for developer sign-off.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fsprint-planning\u002FSKILL.md",[],[132,133,134,102,135,136,137,138,139,140,141,142,24,143,144,145,124],"planning","sprint","sprint planning","visual companion","plan gate","for","companion","sign","visual","selection","Composition","plan","team","developer",{"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":152,"publishedAt":33},"01M6DERWCP7Y0WDY5KG6109RQB","sprint-manager","Sole writer of stories\u002Findex.json and sprints\u002Findex.json — validates state transitions, activates sprints, manages epic membership.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fsprint-manager\u002FSKILL.md",[],[153,133,154,155,156,157,158,159,160,161,162],"sprint manager","manager","writer","stories","sprints","EPIC","transitions","json","index","state",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":33},"01M6DERS7B4QHAH5GZHHBA4AHB","sprint-dev","Sprint execution — dependency-driven story development, post-merge AVFL, and team review.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fsprint-dev\u002FSKILL.md",[],[170,171,133,144,172,173,174,175,176,177,102,178,179,180,24],"dev","sprint dev","execution","team review","development","merge","review","dependency","post","avfl","driven",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":187,"publishedAt":33},"01M6DERP0A271FYSAXCV85GF04","retro","Sprint retrospective — transcript audit engine (dynamic Workflow), story verification, findings document, and sprint closure.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fretro\u002FSKILL.md",[],[183,188,189,102,190,133,191,24,192,193,194,195,196,106],"sprint retrospective","closure","dynamic workflow","document","engine","audit","verification","transcript","retrospective"]