{"slug":"loulanyue-agent-eval","source_name":"loulanyue/agent-eval","name":"Loulanyue/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":6,"lift":{"pass_rate_delta_pts":54.55,"pass_rate_pct":95.5,"total_cases":22,"passed_cases":21,"tokens_delta_pct":-10.6,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-22T00:37:51.001857+00:00"},"skill_score":0.9545,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":54.55,"with_pass_pct":95.5,"without_pass_pct":40.9,"tokens_delta_pct":-10.6,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":21,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-22T00:37:51.001857+00:00","run_id":"211cc3a3-f2cb-43b8-ba35-b24ef6738a00","latest_attempt":{"id":"211cc3a3-f2cb-43b8-ba35-b24ef6738a00","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-08-22T00:37:51.001857+00:00","gate":null},"version_number":6,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"total_uses":0,"total_users":0,"manifest_hash":"5154673d417ee08e801073f9aed68b78243e1217b046162f2384a659e7628c28","install_name":"loulanyue-agent-eval","version_id":"e2f95bd0-e18b-4324-9c65-c62dbb6e90d7","body_sha256":"5154673d417ee08e801073f9aed68b78243e1217b046162f2384a659e7628c28","render_hash":"058a3311765be6797b33472014dc9e26f42f8ee29044057fe3ea1cabf5083e86","raw_url":"https://app.decimal.ai/s/loulanyue-agent-eval/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/loulanyue-agent-eval"}