Agent skill
/theory-ingest
将一篇理论建模论文摄取为理论研究 wiki：论文卡片 + 假设/原语 + 命题/定理 + 解概念 + 可检验推论，并与实证层在同一张 graph 上接桥
OpenClawData & Analytics
Lambenthan41
Agent skills
Reusable instructions for compatible AI agents.
Explore by field
Loading catalog totals…Counts cover every published resource in this section. A resource can belong to several fields and platforms.
Resources
25 resourcesAgent skill
/edit
根据用户要求增删 raw sources 或更新 wiki 内容
OpenClawDesign
Lambenthan41
Agent skill
/empirical-design
基于已摄取文献和本地数据，生成经管实证研究设计：问题、机制、变量、模型、识别、机制、异质性、稳健性
OpenClawData & Analytics
Lambenthan41
Agent skill
/variable-map
汇总某个经管实证变量在文献中的测算口径、数据来源、模型角色和项目可用性
OpenClawData & Analytics
Lambenthan41
Agent skill
/empirical-ingest
将一篇经管实证论文摄取为实证研究 wiki：论文卡片 + 变量 + 数据 + 模型 + 机制 + 识别 + 稳健性 + 异质性 + 表格线索
OpenClawData & Analytics
Lambenthan41
Agent skill
/exp-run
实验执行全流程：准备代码 → 部署运行 → 监控状态 → 收集结果，支持三种运行模式
OpenClawData & Analytics
Lambenthan41
Agent skill
/exp-eval
实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
OpenClawData & Analytics
Lambenthan41
Agent skill
/exp-design
Claim-driven 实验设计：界定目标 claims → 设计实验块（baseline/validation/ablation/robustness）→ 构建执行顺序 → 可选 Review LLM review → 写入 wiki
OpenClawData & Analytics
Lambenthan41
Agent skill
/ideate
多阶段研究 idea 生成管道：景观扫描 → 双模型脑暴 → 初筛 → 深度验证 → 写入 wiki
OpenClawData & Analytics
Lambenthan41
Agent skill
/novelty
多源 novelty 验证：WebSearch + Semantic Scholar + wiki + Review LLM cross-verify，输出 novelty 评分与建议
OpenClawData & Analytics
Lambenthan41
Agent skill
/paper-draft
从 PAPER_PLAN 起草 LaTeX 论文：逐 section 从 wiki 取材撰写 + 生成 figures/tables + BibTeX 验证 + de-AI polish
OpenClawData & Analytics
Lambenthan41
Agent skill
/paper-compile
LaTeX 编译 → PDF：latexmk 编译 + 自动修复 + 页数/匿名/字体/[UNCONFIRMED] 检查 + 提交清单
OpenClawEducation & Research
Lambenthan41
No matching resources
Try a broader search or clear some filters.
Platform labels describe intended use. Read each resource's author credits, requirements and available access methods.