akitaonrails/llm-coding-benchmark
Skill Claude CodeCodex
Automatically evaluates an LLM coding benchmark result using a standardized 0-100 rubric across 8 dimensions. Use when a benchmark finishes, when the user asks to evaluate a model, analyze a run's quality, or generate a score for a result. Also activates for 'score', 'evaluate benchmark', 'audit model', or 'analyze…
not rated 304
+6 today A 74 tokens