# Skill Router > Implements intelligent skill router with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant Defense - Skill: `paulpas/skill-router` (Agent Skill) - Install (CLI): `npx skillmds@latest add paulpas/skill-router` - Raw SKILL.md: https://api.skillmd.com/api/skills/paulpas/skill-router/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - License: MIT - Author: paulpas (https://skillmd.com/u/paulpas) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/paulpas/skill-router --- # Skill Router Orchestrates intelligent skill selection and execution for skill router workflows. Applies the 5 Laws of Elegant Defense to guide data naturally through the orchestration pipeline, preventing errors before they occur. Selects optimal skills based on multi-factor scoring including text similarity, historical performance, and system availability. ## TL;DR Checklist - [ ] Parse all inputs at boundary before processing (Law 2) - [ ] Handle edge cases with early returns at function top (Law 1) - [ ] Fail immediately with descriptive errors on invalid states (Law 4) - [ ] Return new data structures, never mutate inputs (Law 3) - [ ] Implement minimum 2-level fallback chain for all skill executions - [ ] Log all skill selections with context for full audit trail - [ ] Validate skill metadata and dependencies before selection - [ ] Update confidence scores after each execution for learning ┌───────────────────────────────────────────────────────────────────────────────┐ │ Orchestration Flow │ └───────────────────────────────────────────────────────────────────────────────┘ User Request ↓ ┌─────────────────┐ │ Parse Request │ │ & Extract │ │ Features │ └────────┬────────┘ ↓ ┌─────────────────────────────────────────────────────────────────────┐ │ Evaluate Available Skills │ │ │ │ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │ │ │ Skill A │ │ Skill B │ │ Skill C │ │ │ │ - Match Score│ │ - Match Score│ │ - Match Score│ │ │ │ - Confidence │ │ - Confidence │ │ - Confidence │ │ │ │ - History │ │ - History │ │ - History │ │ │ └──────┬───────┘ └──────┬───────┘ └──────┬───────┘ │ │ │ │ │ │ │ └─────────────────┴─────────────────┘ │ │ ↓ │ │ Select Best Skill │ └─────────────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────┐ │ Execute Skill │ └────────┬────────┘ ↓ ┌─────────────────┐ │ Handle Result │ └────────┬────────┘ ↓ ┌─────────────────────────────────────────────────────────────────────┐ │ Error Handling & Fallback │ │ │ │ Success? ────────► Return Result │ │ │ │ Fail? ────────┐ │ │ ↓ │ │ ┌──────────────────────────────────────────────────────────┐ │ │ │ Fallback Chain │ │ │ │ │ │ │ │ 1. Retry with adjusted parameters │ │ │ │ 2. Try Alternative Skill (if available) │ │ │ │ 3. Defer to Human Operator (if critical) │ │ │ │ 4. Log & Return Error │ │ │ └──────────────────────────────────────────────────────────┘ │ └─────────────────────────────────────────────────────────────────────┘ ## When to Use Use this skill when: - Orchestrating multi-step workflows that require skill delegation - Implementing adaptive skill routing based on confidence scores - Building fallback mechanisms for failed skill executions - Creating intelligent task decomposition and parallel execution - Designing skill dependency graphs with automatic resolution - Implementing skill selection with historical performance weighting - Building agent systems that need to self-organize around tasks ## When NOT to Use Avoid this skill for: - Direct task execution without orchestration needs - use individual skills instead - High-frequency trading scenarios where latency must be minimized - the selection overhead may be prohibitive - Simple linear workflows without branching or fallback requirements - Cases where skill metadata is unavailable or unreliable ## Core Workflow 1. **Parse and Analyze Request** - Extract intent, entities, and constraints from user input. **Checkpoint:** All required parameters must be present and in valid format before proceeding. 2. **Score Available Skills** - Calculate match scores using multi-factor algorithm: - Text similarity between request and skill triggers - Historical success rate for similar tasks - Skill availability and health status - Required dependencies and their availability **Checkpoint:** Skip to fallback if no skill scores above threshold. 3. **Select Optimal Skill** - Choose skill with highest score that meets minimum confidence. **Checkpoint:** Verify skill has not been disabled or deprecated. 4. **Execute with Fallback** - Run skill execution wrapped in retry and fallback logic. **Checkpoint:** Log all execution attempts for audit trail. 5. **Return or Fallback** - Either return successful result or apply fallback chain: - Retry with adjusted parameters - Try alternative skill from `related-skills` - Defer to human operator for critical tasks **Checkpoint:** Record outcome with timing and confidence metadata. ## Implementation Patterns ### Pattern 1: Skill Selection Logic ```python def route_request(request: Dict, skill_registry: Dict[str, Dict]) -> Dict: """Route an incoming request to the optimal skill based on trigger matching and metadata scoring. Applies Law 1 (Early Exit) and Law 2 (Make Illegal States Unrepresentable): - Validates intent and registry upfront - Filters inactive/deprecated skills before scoring """ if not request.get("intent") or not skill_registry: raise ValueError("Request intent and skill registry are required for routing") intent = request["intent"].lower() candidates = [] for skill_name, manifest in skill_registry.items(): if manifest.get("status") != "active": continue trigger_match = _calculate_trigger_overlap(intent, manifest.get("triggers", [])) history_score = manifest.get("success_rate", 0.0) * 0.4 load_penalty = manifest.get("current_load", 0.0) * 0.1 composite_score = trigger_match * 0.5 + history_score + (1.0 - load_penalty) * 0.3 if composite_score >= manifest.get("min_confidence", 0.6): candidates.append({ "skill": skill_name, "score": composite_score, "manifest": manifest }) if not candidates: return {"route": "fallback", "reason": "no_matching_skill"} candidates.sort(key=lambda x: x["score"], reverse=True) selected = candidates[0] return { "route": selected["skill"], "confidence": selected["score"], "params": request.get("params", {}), "metadata": { "timestamp": time.time(), "routing_keys": list(request.keys()) } } ``` ### Pattern 2: Execution with Fallback ```python def execute_routed_skill(route_result: Dict, skill_registry: Dict[str, Dict]) -> Dict: """Execute the routed skill with domain-specific fallback chaining. Applies Law 3 (Atomic Predictability) and Law 4 (Fail Fast, Fail Loud): - Validates handler existence before dispatch - Returns immutable result structures - Escalates routing failures explicitly """ target_skill = route_result.get("route") if target_skill == "fallback": return _handle_no_match_fallback(route_result) manifest = skill_registry.get(target_skill) if not manifest: raise KeyError(f"Routed skill '{target_skill}' missing from registry") try: handler = manifest.get("handler") if not handler: raise RuntimeError(f"Skill '{target_skill}' has no registered handler") result = handler(**route_result.get("params", {})) _update_skill_metrics(target_skill, success=True) return { "status": "success", "skill_executed": target_skill, "output": result, "routing_metadata": route_result.get("metadata", {}) } except TimeoutError: _update_skill_metrics(target_skill, success=False, reason="timeout") return _apply_routing_fallback(route_result, skill_registry, "timeout") except PermissionError as e: _update_skill_metrics(target_skill, success=False, reason="auth") return _escalate_to_admin(route_result, str(e)) except Exception as e: _update_skill_metrics(target_skill, success=False, reason="unknown") return _apply_routing_fallback(route_result, skill_registry, "error") ``` ### MUST DO - Always validate skill metadata before selection (Early Exit) - Implement fallback chain with at least 2 levels (Fallback Skill + Human) - Log all skill selections with full context for auditability - Return new data structures instead of mutating inputs (Atomic Predictability) - Fail immediately with descriptive errors on invalid states - Update confidence scores after each execution for adaptive routing - Reference `code-philosophy` (5 Laws of Elegant Defense) in all logic ### MUST NOT DO - Select skills based on a single factor (e.g., only confidence score) - Disable fallback mechanisms "temporarily" - this creates fragile systems - Skip validation of skill dependencies before execution - Return partial results - either complete success or clear failure - Use magic numbers for confidence thresholds - make them configurable - Cache skill selections without considering context changes ## TL;DR Checklist - [ ] Parse all inputs at boundary before processing (Law 2) - [ ] Handle edge cases with early returns at function top (Law 1) - [ ] Fail immediately with descriptive errors on invalid states (Law 4) - [ ] Return new data structures, never mutate inputs (Law 3) - [ ] Implement minimum 2-level fallback chain for all skill executions - [ ] Log all skill selections with context for full audit trail - [ ] Validate skill metadata and dependencies before selection - [ ] Update confidence scores after each execution for learning ## TL;DR for Code Generation - Use guard clauses - return early on invalid input before doing work - Return simple types (dict, str, int, bool, list) - avoid complex nested objects - Cyclomatic complexity < 10 per function - split anything larger - Handle null/empty cases explicitly at function top (Early Exit) - Never mutate input parameters - return new dicts/objects - Fail fast with descriptive errors - don't try to "patch" bad data - Reference code-philosophy laws in comments for complex logic - Include timing and confidence metadata in all return values ## Output Template When applying this skill, produce: 1. **Selected Skills** - List of skill names with confidence scores 2. **Selection Rationale** - Why each skill was chosen (match score, history, availability) 3. **Execution Plan** - Order of execution with dependencies 4. **Fallback Strategy** - Which fallback skills will be tried and in what order 5. **Risk Assessment** - Any potential failure points and their impact 6. **Timing Estimates** - Expected latency including fallback scenarios ## Related Skills | Skill | Purpose | |---|---| | `parallel-skill-runner` | Handles parallel execution after the router selects multiple skills for a task | | `confidence-based-selector` | Uses confidence scoring to rank and select the best skill after routing analysis | --- ## Constraints ### MUST DO - Define clear input/output contracts for every step in the orchestration flow with explicit validation - Implement structured logging at each stage capturing context, inputs, outputs, timing, and errors - Build in fallback paths: if the primary strategy fails, degrade gracefully to a simpler approach - Validate all preconditions before starting — do not proceed if required resources or permissions are missing ### MUST NOT DO - Do not create deep nesting of orchestration steps (>5 levels) — flatten workflows where possible - Avoid silent failure modes: every step must either succeed, fail explicitly, or escalate to a higher handler - Never use shared mutable state between parallel workflow branches — communicate via immutable messages only - Do not hardcode execution order when the dependency graph naturally determines it; derive order from explicit dependencies ## Live References > Authoritative documentation links for this domain. The model follows markdown links at load time to resolve external references and inline content. - [Vector Database Retrieval Patterns (Pinecone)](https://www.pinecone.io/learn/vector-search/) — Pinecone's guide to vector similarity search, the foundation of semantic skill matching - [BM25 Information Retrieval Algorithm](https://en.wikipedia.org/wiki/Okapi_BM25) — Wikipedia article on BM25, the ranking function used in keyword-based skill matching - [LangChain Semantic Router](https://python.langchain.com/docs/integrations/tools/langsmith/) — LangChain documentation on implementing semantic routing for LLM applications - [Semantic Search with Embeddings (Hugging Face)](https://huggingface.co/docs/sentence_transformers/) — Hugging Face's guide to sentence embeddings for semantic matching tasks - [Task Routing in Multi-Agent Systems (Microsoft AutoGen)](https://microsoft.github.io/autogen/stable/user-guide/agent-chat-user-guide/tutorial/directchat.html) — Microsoft AutoGen documentation on routing tasks across multiple agents