{"slug":"agent-eval","source_name":"agent-eval","name":"Agent Eval","description":"Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics","version":1,"lift":{"pass_rate_delta_pts":45.83,"pass_rate_pct":50,"total_cases":24,"passed_cases":12,"tokens_delta_pct":-20.4,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-07-27T16:11:47.069467+00:00"},"skill_score":0.5,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":45.83,"with_pass_pct":50,"without_pass_pct":4.2,"tokens_delta_pct":-20.4,"turns_delta_pct":0,"total_cases":24,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-07-27T16:11:47.069467+00:00","run_id":"77e6f5a6-6563-423e-9701-ce2850e97e54","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":null,"content_status":"clean","indexable":true},"license":"MIT","install_count":1,"manifest_hash":"4b623ffac222cb21ebb82043fcfb2d35055c72536467d5c55abd2792086c828c","raw_url":"https://app.decimal.ai/s/agent-eval/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/agent-eval"}