nl-router

nl-router

Route natural language requests to appropriate skills and workflows.

Triggers

Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):

• "route this" → explicit NL routing request
• "what skill handles [X]" → skill discovery

Purpose

This skill interprets natural language requests and routes them to the appropriate skills or workflows by:

• Parsing user intent from natural language
• Matching to available skills and commands
• Handling ambiguous requests with clarification
• Suggesting relevant actions
• Learning from routing patterns

Behavior

When triggered, this skill:

1. Parses user intent:

   • Extract action verbs
   • Identify objects/targets
   • Detect qualifiers and constraints
   • Recognize context from conversation

2. Matches to skills:

   • Search skill trigger patterns
   • Score match confidence
   • Consider context relevance

3. Routes request:

   • High confidence: Route directly
   • Medium confidence: Confirm with user
   • Low confidence: Offer options
   • No match: Suggest alternatives

4. Handles follow-ups:

   • Track routing context
   • Enable corrections
   • Learn from feedback

Routing Patterns

SDLC Workflows

sdlc_patterns:
  phase_transitions:
    patterns:
      - "transition to {phase}"
      - "move to {phase}"
      - "start {phase}"
      - "begin {phase}"
      - "ready for {phase}"
    routes_to: flow-{from}-to-{to}
    extract: [from_phase, to_phase]

  gate_checks:
    patterns:
      - "check gate"
      - "can we transition"
      - "ready for {phase}"
      - "validate {gate}"
      - "gate check"
    routes_to: gate-evaluation
    extract: [gate_name, phase]

  project_status:
    patterns:
      - "where are we"
      - "what's next"
      - "project status"
      - "current phase"
      - "status update"
    routes_to: project-awareness
    action: status_report

  risk_management:
    patterns:
      - "update risks"
      - "risk review"
      - "new risk"
      - "mitigate {risk}"
    routes_to: risk-cycle
    extract: [risk_id, action]

  security_review:
    patterns:
      - "security review"
      - "run security"
      - "threat model"
      - "security scan"
    routes_to: security-assessment
    extract: [scope]