sibyl-simulated-reviewer
Sibyl 模拟 Reviewer agent - 从真实 reviewer 视角重新评估 rebuttal
Sibyl 模拟 Reviewer agent - 从真实 reviewer 视角重新评估 rebuttal
Sibyl 新颖性检查 agent - 搜索文献验证 idea 是否与已有论文撞车
Sibyl 文献调研 agent - 使用 arXiv + Web 双源搜索进行系统性文献调研
Sibyl Rebuttal 理论专家 agent - 强化理论论证和数学证明
Sibyl 终审 agent - NeurIPS/ICML 级别的论文终审
Sibyl 跨学科者 agent - 从认知科学、物理、生物等领域引入类比和方法
Sibyl 修正主义者 agent - 基于实验结果反思假设,提出修正方向
Patterns for data loading, exploration, and statistical analysis
Patterns for data loading, exploration, and statistical analysis
Best practices for designing reproducible experiments
Best practices for designing reproducible experiments
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
Adversarial code review using the opposite model. Spawns 1–3 reviewers on the opposing model (Claude spawns Codex, Codex spawns Claude) to challenge work from distinct critical lenses. Triggers: "adversarial review".
Use when user asks to read, summarize, or analyze a research paper (PDF or text). Triggers on keywords like "read paper", "summarize paper", "paper summary", "literature review", "analyze this paper"
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Make AI-powered assertions about screen state
Capture and manage screenshots during test execution