shiqichen17/SkillCraft

Benchmark for LLM agents composing tool skills

View on index · View in 3D Map

Related repos

• Benchmark for agent skill composition
• Benchmarks AI coding agents with real tasks
• Scores 6,000+ agent skills on 6 dimensions
• Collection of skills for AI coding agents
• Benchmark evaluates LLMs as agents
• Collective skill evolution for AI agents
• Benchmark for LLMs on software engineering tasks
• Infrastructure for sharing and evaluating AI agent skills
• Package manager for AI agent skills
• Guidelines for LLM coding agents