菜单
Use GPT Pro for research-paper brainstorming, claim sharpening, novelty analysis, related-work positioning, reviewer objections, and experiment story design. Best for algorithm/research ideas where Codex alone is too implementation-biased.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/WILLOSCAR/codex-pro-bridge --skill gpt-pro-paper-brainstormer命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Coordinate the single-user Auto Research system across Primary, Research Orchestrator, Track Mentor, Student, local Codex chats, and one-to-many GPT Pro web conversations. Use when an Auto Research request concerns Research Line identity, Idea Variants, Student or Mentor routing, Chat binding, Pro Teacher conversation lineage, WIP, Handoff, asynchronous replies, or Settlement. Delegate external review and experiments to the existing Bridge skills; use those skills directly for generic work outside an Auto Research SOP.
Bind one local research repository to one existing or new ChatGPT Project, synchronize stable Project Sources, inspect Project tasks, or repair Project routing. Use when the user mentions a ChatGPT Project, shared files across conversations, several research sessions, project binding, or Project-aware Codex Pro Bridge work; normal external questions still enter through gpt-pro-question-window, which resolves the route automatically.
Bridge Codex to the correct signed-in ChatGPT/GPT Pro conversation through a Chrome DevTools MCP-first browser route, automatically choosing standalone or a bound ChatGPT Project, with scoped upload, conversation reuse, raw answer capture, and later Codex verification. Use for normal GPT Pro questions and as the browser/persistence foundation for other Codex Pro Bridge skills; do not use for local tasks that need no external reasoning.
| name | gpt-pro-paper-brainstormer |
| description | Use GPT Pro for research-paper brainstorming, claim sharpening, novelty analysis, related-work positioning, reviewer objections, and experiment story design. Best for algorithm/research ideas where Codex alone is too implementation-biased. |
Gather only the evidence needed to test the research claim, then ask GPT Pro to act as a skeptical research advisor.
$gpt-pro-project-workspace. Preserve the returned
Project and Thread identity, or use the standalone path when no shared
Project context is needed.$bundle-algorithm-context if code, experiments, docs, or logs matter.$gpt-pro-question-window to ask GPT Pro.bridge-thread-id.Completion criterion: claims and related-work references are marked as verified or unverified, the required experiments are concrete, and the publishability judgment is preserved separately from Codex's local verdict.
Ask GPT Pro to cover:
GPT Pro may invent related work or overstate novelty. After GPT Pro responds, Codex should mark related-work items as unverified unless it has searched or the user supplied citations.