Research Planning
Create comprehensive research plans and paper architectures from a research topic or idea.
Input
$0 — Research topic, idea description, or paper to reproduce
References
- 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
Workflow
Step 1: Understand the Research Context
- Read any provided papers, code, or references
- Identify the core research question and its significance
- Assess available resources (datasets, compute, existing code)
Step 2: Generate Research Plan
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
Step 3: Structure the Paper
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
Step 4: Create Task Dependency Graph
- Order tasks by dependency (data → model → training → evaluation → writing)
- Identify parallelizable tasks
- Flag risks and potential failure modes
Output Format
{
"research_question": "...",
"methodology": "...",
"paper_structure": {
"sections": ["Abstract", "Introduction", ...],
"section_plans": { "Introduction": "..." }
},
"task_list": [
{"task": "...", "depends_on": [], "priority": 1}
],
"baselines": ["..."],
"datasets": ["..."],
"evaluation_metrics": ["..."],
"risks": ["..."]
}
Rules
- Each plan component must be detailed and actionable
- Include specific implementation references when available
- Ensure all components work together coherently
- Always include a testing/evaluation plan
- Flag ambiguities explicitly rather than making assumptions
Related Skills
1---2name: research-planning3description: Design research plans and paper architectures. Given a research topic or idea, generate structured plans with methodology outlines, paper structure, dependency-ordered task lists, UML diagrams, and experiment designs. Use when starting a new research project or paper.4---56# Research Planning78Create comprehensive research plans and paper architectures from a research topic or idea.910## Input1112- `$0` — Research topic, idea description, or paper to reproduce1314## References1516- Planning prompts from Paper2Code, AI-Researcher, AgentLaboratory: `~/.claude/skills/research-planning/references/planning-prompts.md`17- Output schemas and templates: `~/.claude/skills/research-planning/references/output-schemas.md`1819## Workflow2021### Step 1: Understand the Research Context22- Read any provided papers, code, or references23- Identify the core research question and its significance24- Assess available resources (datasets, compute, existing code)2526### Step 2: Generate Research Plan27Use the 4-stage planning approach (adapted from Paper2Code):28291. **Overall Plan** — Strategic overview: methodology, key experiments, evaluation metrics302. **Architecture Design** — File structure, system design, Mermaid class/sequence diagrams313. **Logic Design** — Task breakdown with dependencies, required packages, shared knowledge324. **Configuration** — Extract or specify hyperparameters, training details, config.yaml3334### Step 3: Structure the Paper35Design the paper structure with section-by-section plan:36- Abstract, Introduction, Background, Related Work, Methods, Experiments, Results, Discussion/Conclusion37- For each section: key points to cover, required figures/tables, target word count3839### Step 4: Create Task Dependency Graph40- Order tasks by dependency (data → model → training → evaluation → writing)41- Identify parallelizable tasks42- Flag risks and potential failure modes4344## Output Format4546```json47{48 "research_question": "...",49 "methodology": "...",50 "paper_structure": {51 "sections": ["Abstract", "Introduction", ...],52 "section_plans": { "Introduction": "..." }53 },54 "task_list": [55 {"task": "...", "depends_on": [], "priority": 1}56 ],57 "baselines": ["..."],58 "datasets": ["..."],59 "evaluation_metrics": ["..."],60 "risks": ["..."]61}62```6364## Rules6566- Each plan component must be detailed and actionable67- Include specific implementation references when available68- Ensure all components work together coherently69- Always include a testing/evaluation plan70- Flag ambiguities explicitly rather than making assumptions7172## Related Skills73- Upstream: [idea-generation](../idea-generation/), [literature-review](../literature-review/)74- Downstream: [experiment-design](../experiment-design/), [paper-assembly](../paper-assembly/)75- See also: [atomic-decomposition](../atomic-decomposition/)
om-scogo