{"slug":"openmatter-network-ai-model-development-audit","source_name":"openmatter-network/ai-model-development-audit","name":"Openmatter Network/AI Model Development Audit","description":"Use when auditing how an AI/ML personnel assessment was actually built once its design was set — Components 3-5 of the Landers & Behrend (2023) framework: model development (refinement and cross-validation strategy, documentation), model features (feature engineering — NLP tokens vs. topics, speech-to-text, extracted facial/voice features), and model processes (the estimation algorithm, alternatives explored, and stress tests for bias). Triggers: \"audit feature engineering\", \"k-fold vs holdout v","version":1,"lift":{"pass_rate_delta_pts":9.09,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":47.1,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-03T14:09:06.555994+00:00"},"skill_score":0.9091,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":9.09,"with_pass_pct":90.9,"without_pass_pct":81.8,"tokens_delta_pct":47.1,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-03T14:09:06.555994+00:00","run_id":"7c462ff8-decb-41bc-9640-973ab2d8888b","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":"627aba7b96342770b18544f5d053bb88ba520c0707ba11608e6ae8075ae67ac3","raw_url":"https://app.decimal.ai/s/openmatter-network-ai-model-development-audit/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/openmatter-network-ai-model-development-audit"}