{"slug":"avenoxai-gptpro-handoff","source_name":"avenoxai/gptpro-handoff","name":"Avenoxai/Gptpro Handoff","description":"Run the research/audit handoff loop between an agentic coding harness and a slow, non-agentic frontier reasoning model (GPT Pro on the ChatGPT web UI, or equivalent) with the codebase pre-loaded as split zip bundles. Author a high-signal prompt, then later take the returned report, verify every finding against the LIVE codebase, and implement what holds up. Use whenever the operator wants to send something to a deep external model, prep a prompt or report, scope an issue for deep research, bug-h","version":1,"lift":{"pass_rate_delta_pts":37.5,"pass_rate_pct":87.5,"total_cases":24,"passed_cases":21,"tokens_delta_pct":80.4,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-03T11:11:34.270269+00:00"},"skill_score":0.875,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":37.5,"with_pass_pct":87.5,"without_pass_pct":50,"tokens_delta_pct":80.4,"turns_delta_pct":0,"total_cases":24,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-03T11:11:34.270269+00:00","run_id":"6f8fc47c-f551-4fa5-a110-3b3e33710019","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":"3a705a42b5692e10915dd8c5c0e00dc89b5d39fe7e194bba5cfff4e5d5fdeb00","raw_url":"https://app.decimal.ai/s/avenoxai-gptpro-handoff/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/avenoxai-gptpro-handoff"}