Skill Claude CodeCodex
Skill "mcp-eval-logging" from sunny-glow/Auto-BenchMax, covering mcp eval logging, structuring this skill, resources (optional), scripts/ and references/.
1.5k 1mo ago A 20 tokens
Skill Claude CodeCodex
Synthesize training data for ANY tool-use / agentic benchmark, in ANY repo. Given a handful of runnable reference tasks, produce thousands of "same-distribution, different-entity" tasks, roll out real trajectories, and emit SFT, RL data. Use this when: you have a tool-calling / MCP / agentic benchmark and want to…
1.5k 1mo ago A 183 tokens