{"slug":"smithersai-eval-driven-development","source_name":"smithersai/eval-driven-development","name":"Smithersai/Eval Driven Development","description":"How this repo does eval-driven development (EDD) for Smithers workflows — write the failing suite first, build until green, validate on a holdout, then optimize. Use when adding evals to a workflow, changing a prompt/model/graph that has a suite, setting up a dev/holdout split, or wiring eval gates into CI. For suite-authoring mechanics see skills/eval-writer/SKILL.md; this skill is the loop and the discipline.","version":1,"lift":{"pass_rate_delta_pts":68.18,"pass_rate_pct":95.5,"total_cases":22,"passed_cases":21,"tokens_delta_pct":19.7,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-21T06:29:08.418382+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":19.7,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-21T06:29:08.418382+00:00","run_id":"75b8a805-5ba5-48cb-a58c-649eea818813","latest_attempt":{"id":"75b8a805-5ba5-48cb-a58c-649eea818813","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-08-21T06:29:08.418382+00:00","gate":null},"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,"total_uses":0,"total_users":0,"manifest_hash":"f76c615f7e9cac5d92a0480b9ca275e45b0b43c5748cf1b4389d3f36305a5164","install_name":"smithersai-eval-driven-development","version_id":"125384ea-5a34-4e0d-9903-d61c1825a1cc","body_sha256":"f76c615f7e9cac5d92a0480b9ca275e45b0b43c5748cf1b4389d3f36305a5164","render_hash":"cc2f0633888f54d7366105632ffd40eb85d9d4f97f212fb3726c7d67f7deff79","raw_url":"https://app.decimal.ai/s/smithersai-eval-driven-development/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/smithersai-eval-driven-development"}