sibyl-theoretical
The sibyl-theoretical Claude Code skill generates research proposals that emphasize mathematical foundations and theoretical guarantees. Use this skill when developing academic research ideas that require rigorous mathematical grounding, formal proofs, or theoretical validation, particularly within the AutoResearch-SibylSystem framework. The skill outputs structured perspectives to a designated workspace directory for integration with broader research planning workflows.
git clone --depth 1 https://github.com/Sibyl-Research-Team/AutoResearch-SibylSystem /tmp/sibyl-theoretical && cp -r /tmp/sibyl-theoretical/.claude/skills/sibyl-theoretical ~/.claude/skills/sibyl-theoreticalSKILL.md
!`SIBYL_WORKSPACE="$ARGUMENTS[0]" .venv/bin/python3 -c "from sibyl.orchestrate import render_skill_prompt; import os; ws = os.environ.get('SIBYL_WORKSPACE', ''); print(render_skill_prompt('theoretical', workspace_path=ws))"`
AGENT_NAME: sibyl-theoretical
AGENT_TIER: sibyl-standard
SIBYL_ROOT: /Users/cwan0785/sibyl-system
Workspace path: $ARGUMENTS[0]
Topic (may contain spaces): $ARGUMENTS[1]
Write your output to $ARGUMENTS[0]/idea/perspectives/theoretical.mdSibyl Codex 独立第三方审查 - 使用 OpenAI Codex 提供不同 AI 视角的评审
Sibyl Codex 写作 agent - 使用 Codex (GPT-5) 撰写论文
Sibyl 比较分析者 agent - 对标 SOTA 和同类工作,定位结果贡献
Sibyl 反对者 agent - 挑战主流假设,寻找反面证据和盲点
Sibyl 批评者 agent - 苛刻但公正的学术批评
Sibyl 编辑 agent - 整合论文各章节为完整稿件
Sibyl 实验主义者 agent - 关注可复现性、数据质量和实验设计严谨性
Sibyl 后台实验监督 agent - 持续刷新 GPU 空闲状态、动态派发排队实验、处理运行时间/状态漂移