{"slug":"mohitagw15856-agent-design-review","source_name":"mohitagw15856/agent-design-review","name":"Mohitagw15856/Agent Design Review","description":"Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools, memory/context, failure handling, cost, and safety — with prioritised findings and fixes.","version":1,"lift":{"pass_rate_delta_pts":18.18,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":27.3,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-14T01:35:48.308197+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":27.3,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-14T01:35:48.308197+00:00","run_id":"13f86b00-59c0-401a-a1fb-1967ce065336","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":"2369466c83208c3dc47635bd54df6c2719390d159068ac98d5621133b854677c","raw_url":"https://app.decimal.ai/s/mohitagw15856-agent-design-review/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/mohitagw15856-agent-design-review"}