Skill Claude CodeCodex
Interactively generate all required EUREKA problem input files (INSTRUCTION.md, SUBMISSIONFORMAT.md, evaluate.py) and the launch script (run.sh) from a researcher's natural language description, then validate the evaluation pipeline.
Skill Claude CodeCodex
Run a grader-driven experiment from an assigned initial hypothesis. Reads the hypothesis brief, writes code, submits candidates through the grading service, and iterates on official scores within one approach directory.
Skill Claude CodeCodex
Validate problem setup, test the evaluation pipeline, and configure the environment before the propose-implement loop begins.
Skill Claude CodeCodex
Propose initial hypotheses for an optimization problem. Reads problem and submission format from workspace inputs, generates diverse starting strategies, and writes a manifest for parallel grader-driven experiments.