uncertainty-routing
Route tasks to small model by default, escalate to large model only on low confidence detection, achieving 87% faster learning and 10-30x cost reduction while maintaining accuracy. Use for cost optimization, confidence-based delegation, routine vs complex task routing, and resource efficiency. Triggers on "optimize cost", "model routing", "confidence threshold", "small model first", "escalate on uncertainty".
npx skills add majiayu000/claude-skill-registry --skill uncertainty-routing-dredd-us-seashells-a40aece5 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Uncertainty Routing ## Purpose Route tasks to small models by default, escalate to large models only on low confidence, achieving 87% faster learning and 10-30x cost reduction while maintaining accuracy. ## When to Use - Cost optimization for routine tasks - Confidence-based task routing - Resource-efficient workflows - Mixed-complexity workloads - Budget-conscious operations - High-volume processing ## Core Instructions ### Basic Routing Pattern ```python def route_with_uncertainty(task, confidence_threshold=0.7): """ Route to appropriate model based on confidence """ # Step 1: Try small model first result, confidence = small_model.execute(task) # Step 2: Check confidence if confidence >= confidence_threshold: # High confidence: use small model result return result else: # Low confidence: escalate to large model result = large_model.execute(task) return result ``` ### Confidence Detection ```python class ConfidenceEstimator: """ Estimate confidence in model's response """ def estimate(self, task, response): """ Estimate confidence score (0.0 to 1.0) """ signals = { 'task_familiarity': self.check_familiarity(task), 'response_consistency': self.check_consistency(response), 'explic
- Purpose
- When to Use
- Core Instructions
- Basic Routing Pattern
- Confidence Detection
- Advanced Router with Learning
- Performance Characteristics
- Example Workflows
- Example 1: Routine vs Complex
- Example 2: Batch Processing
- Threshold Tuning
- Conservative (High Accuracy Priority)
- Balanced (Default)
- Aggressive (Maximum Cost Savings)
What does the uncertainty-routing skill do?
Route tasks to small model by default, escalate to large model only on low confidence detection, achieving 87% faster learning and 10-30x cost reduction while maintaining accuracy. Use for cost optimization, confidence-based delegation, routine vs complex task routing, and resource efficiency. Triggers on "optimize cost", "model routing", "confidence threshold", "small model first", "escalate on uncertainty".
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill uncertainty-routing-dredd-us-seashells-a40aece5 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.