Function main

skills/skill-creator/scripts/run_eval.py:259–306

()

def main():
    parser = argparse.ArgumentParser(description="Run trigger evaluation for a skill description")
    parser.add_argument("--eval-set", required=True, help="Path to eval set JSON file")
    parser.add_argument("--skill-path", required=True, help="Path to skill directory")
    parser.add_argument("--description", default=None, help="Override description to test")
    parser.add_argument("--num-workers", type=int, default=10, help="Number of parallel workers")
    parser.add_argument("--timeout", type=int, default=30, help="Timeout per query in seconds")
    parser.add_argument("--runs-per-query", type=int, default=3, help="Number of runs per query")
    parser.add_argument("--trigger-threshold", type=float, default=0.5, help="Trigger rate threshold")
    parser.add_argument("--model", default=None, help="Model to use for claude -p (default: user's configured model)")
    parser.add_argument("--verbose", action="store_true", help="Print progress to stderr")
    args = parser.parse_args()

    eval_set = json.loads(Path(args.eval_set).read_text())
    skill_path = Path(args.skill_path)

    if not (skill_path / "SKILL.md").exists():
        print(f"Error: No SKILL.md found at {skill_path}", file=sys.stderr)
        sys.exit(1)

    name, original_description, content = parse_skill_md(skill_path)
    description = args.description or original_description
    project_root = find_project_root()

    if args.verbose:
        print(f"Evaluating: {description}", file=sys.stderr)

    output = run_eval(
        eval_set=eval_set,
        skill_name=name,
        description=description,
        num_workers=args.num_workers,
        timeout=args.timeout,
        project_root=project_root,
        runs_per_query=args.runs_per_query,
        trigger_threshold=args.trigger_threshold,
        model=args.model,
    )

    if args.verbose:
        summary = output["summary"]
        print(f"Results: {summary['passed']}/{summary['total']} passed", file=sys.stderr)
        for r in output["results"]:
            status = "PASS" if r["pass"] else "FAIL"
            rate_str = f"{r['triggers']}/{r['runs']}"
            print(f"  [{status}] rate={rate_str} expected={r['should_trigger']}: {r['query'][:70]}", file=sys.stderr)

    print(json.dumps(output, indent=2))


if __name__ == "__main__":