{"slug":"diegosouzapw-cli-eval","source_name":"diegosouzapw/cli-eval","name":"Diegosouzapw/CLI Eval","description":"Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.","version":1,"lift":{"pass_rate_delta_pts":68.18,"pass_rate_pct":95.5,"total_cases":22,"passed_cases":21,"tokens_delta_pct":37.9,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-07T13:55:17.096181+00:00"},"skill_score":0.9545,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":68.18,"with_pass_pct":95.5,"without_pass_pct":27.3,"tokens_delta_pct":37.9,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-07T13:55:17.096181+00:00","run_id":"03101b9a-89bd-4588-a289-0ce4b01e65a5","version_number":1,"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,"manifest_hash":"ab631796c4e1cc44c74f6882e1052f27036b01934c71ffbc0e86ec83fdc9fed9","raw_url":"https://app.decimal.ai/s/diegosouzapw-cli-eval/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/diegosouzapw-cli-eval"}