{"slug":"agentscope-ai-00-arena-router","source_name":"agentscope-ai/00-arena-router","name":"Agentscope AI/00 Arena Router","description":"Use when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router ","version":1,"lift":{"pass_rate_delta_pts":27.27,"pass_rate_pct":72.7,"total_cases":22,"passed_cases":16,"tokens_delta_pct":128.7,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.8-flash","grading_method":"judged","completed_at":"2026-11-03T04:39:53.758875+00:00"},"skill_score":0.7273,"benchmark_models":[{"model":"gemini-3.8-flash","headline":true,"delta_pts":27.27,"with_pass_pct":72.7,"without_pass_pct":45.5,"tokens_delta_pct":128.7,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-11-03T04:39:53.758875+00:00","run_id":"cd5c32ca-cb09-4bf6-821e-08c5057065c7","latest_attempt":{"id":"cd5c32ca-cb09-4bf6-821e-08c5057065c7","runner_model":"gemini-3.8-flash","overall_verdict":"mixed","completed_at":"2026-11-03T04:39:53.758875+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":"3c80359bb8bc2108f38ecfd3b7ab56e0f3b0255e7b9eda5a7dcf0a7aa1e3a757","install_name":"agentscope-ai-00-arena-router","version_id":"bf68d4c2-0791-408b-92e3-219618dd2cd1","body_sha256":"3c80359bb8bc2108f38ecfd3b7ab56e0f3b0255e7b9eda5a7dcf0a7aa1e3a757","render_hash":"d32ea773fd42134f1838f4bfa0e7d3bd785da61a06cb43b7b88ddeceb6f6447b","raw_url":"https://app.decimal.ai/s/agentscope-ai-00-arena-router/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/agentscope-ai-00-arena-router"}