gptpro-handoff
规范化把复杂代码库交给 ChatGPT/GPT Pro 等深度推理模型的流程。
依赖 Web UI 上传/预加载代码，存在敏感数据外泄风险。
在编码代理与慢速前沿模型间执行研究/审计交接流程与提示模板。
把编码代理的工作交给慢速深度模型（比如 GPT Pro）时用的完整交接流程：先准备高信号提示并把代码打包成 zip bundles，模型返回报告后再把每条发现对照 LIVE 代码核实并实现可行项。常用于深度研究、漏洞挖掘或性能分析的深入复核。重点是流程化地构建/刷新 zip 包并做严格的、可验证的回译核查。
▸ 展开 SKILL.md 英文原文
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-hunting, or optimization analysis, OR when a report comes back and needs checking against the code before anything is implemented. This is the WORKFLOW skill — to build or refresh the zip bundles themselves, use the separate `gptpro` export skill.
帮我安装这个 skill：https://raw.githubusercontent.com/avenoxai/avenoxskills/main/skills/gptpro-handoff/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/avenoxai/avenoxskills/main/skills/gptpro-handoff/SKILL.md"# Deep-model handoff loop A **slow, non-agentic frontier reasoning model** is a different tool from your coding agent, and it needs a different workflow. This skill is that workflow. Written against GPT Pro on the ChatGPT web UI, with the codebase loaded into a Project as split zip bundles (produced by the `gptpro` export skill). It transfers to any deep model you reach through a chat UI rather than a harness. The defining fact: **the model is non-agentic** — no shell, no live filesystem, bounded context. It reasons over a static snapshot. That drives the entire discipline: **it proposes, you verify, then you implement.** Its report is the strongest kind of input, but it is read against