| name | research-planning |
| description | Use when starting or reframing a computer science research project and you need to turn a vague idea into a scoped plan with research questions, milestones, risks, and next actions. |
Purpose
Turn an idea, problem statement, or paper goal into an executable CS research plan.
When To Use
- starting a new paper, thesis thread, or research prototype
- comparing several candidate directions before implementation
- decomposing a broad topic into concrete work packages
- needing a milestone plan for literature, coding, experiments, and writing
Inputs
- rough idea, question, or target venue
- constraints on time, compute, data, or collaborators
- relevant papers, repos, datasets, or notes if available
Outputs
- scoped research objective
- concrete research questions or hypotheses
- task breakdown by workstream
- milestone sequence and decision points
- risk list with fallback plans
- immediate next actions
Workflow
- Clarify the target artifact: paper, benchmark, reproduction, prototype, or thesis chapter.
- Fix hard constraints before expanding scope.
- Split work into literature, implementation, experiments, and writing tracks.
- Convert the plan into milestones with visible acceptance criteria.
- Surface risks, dependencies, and the minimum viable first step.
Constraints
- avoid vague tasks like "do research" without outputs
- prefer falsifiable or testable questions when possible
- distinguish required work from optional stretch work
- keep the first milestone small enough to execute immediately
