research-planning

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Research Planning

研究规划

Create comprehensive research plans and paper architectures from a research topic or idea.

基于研究主题或想法生成完整的研究计划和论文架构。

Input

输入

```
$0
```
— Research topic, idea description, or paper to reproduce

```
$0
```
— 研究主题、想法描述，或待复现的论文

References

参考资料

Planning prompts from Paper2Code, AI-Researcher, AgentLaboratory:

~/.claude/skills/research-planning/references/planning-prompts.md

Output schemas and templates:

~/.claude/skills/research-planning/references/output-schemas.md

来自Paper2Code、AI-Researcher、AgentLaboratory的规划提示词：
```
~/.claude/skills/research-planning/references/planning-prompts.md
```

输出schema与模板：

~/.claude/skills/research-planning/references/output-schemas.md

Workflow

工作流

Step 1: Understand the Research Context

步骤1：理解研究背景

Read any provided papers, code, or references
Identify the core research question and its significance
Assess available resources (datasets, compute, existing code)

阅读所有提供的论文、代码或参考资料
明确核心研究问题及其意义
评估现有可用资源（数据集、算力、现有代码）

Step 2: Generate Research Plan

步骤2：生成研究计划

Use the 4-stage planning approach (adapted from Paper2Code):

Overall Plan — Strategic overview: methodology, key experiments, evaluation metrics
Architecture Design — File structure, system design, Mermaid class/sequence diagrams
Logic Design — Task breakdown with dependencies, required packages, shared knowledge
Configuration — Extract or specify hyperparameters, training details, config.yaml

使用4阶段规划方法（改编自Paper2Code）：

整体规划 — 战略概览：方法、核心实验、评估指标
架构设计 — 文件结构、系统设计、Mermaid类图/时序图
逻辑设计 — 带依赖关系的任务拆解、所需依赖包、共享知识
配置项 — 提取或指定超参数、训练细节、config.yaml

Step 3: Structure the Paper

步骤3：搭建论文结构

Design the paper structure with section-by-section plan:

Abstract, Introduction, Background, Related Work, Methods, Experiments, Results, Discussion/Conclusion
For each section: key points to cover, required figures/tables, target word count

设计论文结构并给出逐节规划：

摘要、引言、背景、相关工作、研究方法、实验、结果、讨论/结论
针对每个章节：需覆盖的核心要点、所需图表、目标字数

Step 4: Create Task Dependency Graph

步骤4：生成任务依赖图

Order tasks by dependency (data → model → training → evaluation → writing)
Identify parallelizable tasks
Flag risks and potential failure modes

按依赖关系排序任务（数据 → 模型 → 训练 → 评估 → 撰写）
识别可并行执行的任务
标注风险和潜在失败模式

Output Format

输出格式

json

{
  "research_question": "...",
  "methodology": "...",
  "paper_structure": {
    "sections": ["Abstract", "Introduction", ...],
    "section_plans": { "Introduction": "..." }
  },
  "task_list": [
    {"task": "...", "depends_on": [], "priority": 1}
  ],
  "baselines": ["..."],
  "datasets": ["..."],
  "evaluation_metrics": ["..."],
  "risks": ["..."]
}