/research-design

Role: Principal Investigator (study design) Pipeline position: mid-chain

Operationalizes the hypotheses into testable predictions and designs the study or experiment — variables, controls, sample, instruments, power analysis, threats-to-validity — then produces a preregistration that freezes the analysis plan before data collection.

Canonical invocation

/research-design

With arguments:

/research-design [path/to/research-suite/]

Inputs

_inputs/proposal.md (the plan-of-record from /research-proposal, the predecessor stage), _inputs/synthesis.md (the SOTA map + gap statement), and _spec/research-spec.md (the hypotheses).

Outputs

_inputs/study-design.md (operationalized predictions, variable specification, controls, sample, instruments, power analysis, threats-to-validity) + _inputs/preregistration.md (the frozen analysis plan).

Downstream

/research-experiment (downstream consumer)

Workflow phases

The command follows the standard /research pipeline workflow:

1. Load context — Read the synthesis and the spec's hypotheses.
2. Verify the Sequence Gate — Confirm _inputs/proposal.md (and the upstream _inputs/synthesis.md and _spec/research-spec.md) exists; otherwise halt with Blocked: run /research-proposal first.
3. Design the study — Operationalize predictions; specify variables, controls, sample, instruments, power; enumerate threats-to-validity.
4. Preregister — Freeze the analysis plan before any data collection.
5. Update the handoff manifest — Record the study-design and preregistration paths.
6. Emit the design — _inputs/study-design.md + _inputs/preregistration.md.

Rigor floor

For a comparison-bearing study the design fixes, and preregisters, the empirical floor: one unified budget across all compared methods (equal wall-clock and, where meaningful, equal evaluation count), at least thirty repetitions per instance for stochastic methods, an ablation factor that disables one component at a time, sensitivity sweeps over each parameter, and automated configuration on a training split evaluated on a disjoint test split. The floor depth scales to the target-venue ambition.

Failure modes

Examples

# Design the study and preregister the analysis plan
/research-design path/to/research-suite/

Cross-references

• Pipeline overview
• Commands reference