{"slug":"agentsope-agentsop-llm-engine-selection","source_name":"agentsope/agentsop-llm-engine-selection","name":"Agentsope/Agentsop LLM Engine Selection","description":"Cross-engine decision rubric for self-hosting or recommending an LLM serving stack. Picks among vLLM, SGLang, TensorRT-LLM, TGI, llama.cpp, Ollama, and MLX as a function of (hardware × workload × constraint), not \"which is fastest\". Activates whenever a coder-agent must choose, defend, or migrate a serving runtime.","version":1,"lift":{"pass_rate_delta_pts":18.18,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":263.3,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-24T14:05:14.883734+00:00"},"skill_score":0.9091,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":18.18,"with_pass_pct":90.9,"without_pass_pct":72.7,"tokens_delta_pct":263.3,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":21,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-24T14:05:14.883734+00:00","run_id":"6a395bc9-b92d-4d2d-8f94-3d990d42dc25","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":"34afd9d4ee2de434ff59885e1c3e2aed8f2e6499ab5076997a42c9f0d55bbbbb","raw_url":"https://app.decimal.ai/s/agentsope-agentsop-llm-engine-selection/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/agentsope-agentsop-llm-engine-selection"}