| name | experiment-planning |
| description | Use when an operator needs to convert a research objective into an executable plan with deliverables, checkpoints, dependencies, and validation criteria. |
Experiment Planning
When to Use This Skill
Use this skill when the node needs to:
- turn a vague research goal into a concrete plan
- define inputs, outputs, metrics, and success criteria
- break work into stages for planner, coder, and reviewer nodes
- identify risky steps before execution begins
- decide what evidence is needed to claim success
Workflow
- Rewrite the objective as a measurable question.
- List required inputs, tools, datasets, and dependencies.
- Break the task into stages with expected deliverables.
- Add validation gates for each stage.
- Mark high-risk assumptions and fallback paths.
Expected Outputs
- a staged execution plan
- a deliverable checklist
- a risk register
- validation checkpoints
Quality Rules
- plans should be executable, not aspirational
- every stage should produce an inspectable artifact
- note blockers early instead of hiding them in later steps
- define what counts as success before running the work
