{"slug":"agentscope-ai-align-human","source_name":"agentscope-ai/align-human","name":"Agentscope AI/Align Human","description":"Use when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with humans, detect systematic biases, determine whether automatic evaluation can replace human review, or build a human-reduction roadmap. Also use when the user mentions calibration, TPR/TNR, judge validation, inter-rater agreement, Cohen's kappa, bias detection, or \"is my automatic evaluation trustworthy.\" Merges the calibrate and align functions into one skill.","version":1,"lift":{"pass_rate_delta_pts":41.67,"pass_rate_pct":87.5,"total_cases":24,"passed_cases":21,"tokens_delta_pct":121.5,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-14T18:54:29.565985+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":41.67,"with_pass_pct":87.5,"without_pass_pct":45.8,"tokens_delta_pct":121.5,"turns_delta_pct":0,"total_cases":24,"cases_aggregated":23,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-14T18:54:29.565985+00:00","run_id":"89697ce6-c866-4201-b62c-8617718394b5","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":"Apache-2.0","install_count":0,"manifest_hash":"2090c968481a6b23a60e183c2b6d2edb03509bf3d731bd66503fc98f9daa6ddf","raw_url":"https://app.decimal.ai/s/agentscope-ai-align-human/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/agentscope-ai-align-human"}