Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
š NEW FEATURES: ā¢ benchmark command - Get AI intelligence-driven recommendations ā¢ report command - Generate usage and cost analysis ā¢ model-benchmarks integration - Real-time capability data ā¢ Enhanced task classification - 40% better accuracy ā” IMPROVEMENTS: ā¢ 40% faster startup (2.3s ā 1.4s) ā¢ 29% memory reduction (45MB ā 32MB) ā¢ 99.2% API reliability (up from 92%) ā¢ Real-time pricing with performance weighting š MAJOR FIXES: ā¢ Fixed OpenRouter timeout issues (10s ā 30s) ā¢ Resolved config corruption problems ā¢ Improved error handling and user messages ā¢ Better cross-platform compatibility š USER IMPACT: ā¢ Cost savings: 35% ā 67% average reduction ā¢ Task classification: 65% ā 91% accuracy ā¢ User satisfaction: 4.2 ā 4.8 stars ā¢ 78% cost reduction with model-benchmarks combo š PERFECT COMBO: Install with model-benchmarks skill for maximum optimization!
What This Skill Does
Routes AI tasks to cost-appropriate models based on task complexity. Fetches real-time pricing from OpenRouter and classifies tasks into simple, coding, creative, or complex categories. Integrates with a companion benchmarks skill for data-driven model selection.
Instead of manually tracking model pricing and capabilities across providers, it automates routing decisions and updates cost data in real time.
When to use it
- Routing translation jobs to cheaper models to cut API costs
- Comparing current OpenRouter model prices before starting a project
- Setting a budget cap with alerts for a team's monthly API spend
- Generating a 30-day cost report to audit model usage
- Automatically switching to a stable fallback when a cheap model fails repeatedly
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: plan 'translate this product description to French'
- 1Fetches current model pricing from OpenRouter
- 2Classifies the task as simple content work
- 3Identifies GPT-4o-mini or Gemini Flash as cost-optimal choices
- 4Returns recommended model with estimated cost and savings percentage
Routing recommendation: use GPT-4o-mini at $0.60/1M tokens (96% cheaper than premium models)
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.