{"slug":"agentscope-ai-01-auto-arena","source_name":"agentscope-ai/01-auto-arena","name":"Agentscope AI/01 Auto Arena","description":"Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a cust","version":1,"lift":{"pass_rate_delta_pts":59.09,"pass_rate_pct":95.7,"total_cases":23,"passed_cases":22,"tokens_delta_pct":61.8,"turns_delta_pct":0,"verdict":"pass","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-10-11T00:21:55.670588+00:00"},"skill_score":1,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":59.09,"with_pass_pct":100,"without_pass_pct":40.9,"tokens_delta_pct":61.8,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":22,"verdict":"pass","never_hurt":true,"completed_at":"2026-10-11T00:21:55.670588+00:00","run_id":"a0e1c278-ad7c-4090-b3db-b526b9a1e074","latest_attempt":{"id":"a0e1c278-ad7c-4090-b3db-b526b9a1e074","runner_model":"gemini-3.6-flash","overall_verdict":"pass","completed_at":"2026-10-11T00:21:55.670588+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":"Apache-2.0","install_count":0,"total_uses":0,"total_users":0,"manifest_hash":"5d125861191f4dfa5055c4ade83c820d3bd6b6e8ab476f660da32a490db7d503","install_name":"agentscope-ai-01-auto-arena","version_id":"99e05cbc-72fe-4207-b2ee-32bab8b23a33","body_sha256":"5d125861191f4dfa5055c4ade83c820d3bd6b6e8ab476f660da32a490db7d503","render_hash":"0467fe0133ef602c41f02cf369ca834ec9f6a37987b345f3364d7fd69fa9157e","raw_url":"https://app.decimal.ai/s/agentscope-ai-01-auto-arena/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/agentscope-ai-01-auto-arena"}