zwright8 Research Experiment Design Generator
Why This Skill Exists
We need this skill because research throughput degrades without reproducibility and prioritization. This specific skill converts unknowns into testable learning loops.
When To Use
Use this skill when the request explicitly needs "Research Experiment Design Generator" outcomes in the Scientific Research Systems domain.
Step-by-Step Implementation Guide
- Define the scope and success metrics for
Research Experiment Design Generator, including at least three measurable KPIs tied to non-reproducible results and wasted cycles. - Design and version the input/output contract for hypotheses, experiments, and replication evidence, then add schema validation and failure-mode handling.
- Implement the core capability using hypothesis-driven design, and produce experiment plans with deterministic scoring.
- Integrate the skill into swarm orchestration: task routing, approval gates, retry strategy, and rollback controls.
- Add unit, integration, and simulation tests that explicitly cover non-reproducible results and wasted cycles, then run regression baselines.
- Deploy behind a feature flag, monitor telemetry/alerts for two release cycles, and iterate thresholds based on observed outcomes.
Required Deliverables
- Capability contract: input schema, deterministic scoring, output schema, and failure modes.
- Runtime profile: general-capability using hypothesis-driven design to produce experiment plans.
- Orchestration integration: scientific-research-systems:general-capability routing, approval gates, retries, and rollback controls.
- Validation evidence: unit, integration, simulation, regression-baseline suites and rollout telemetry.
Operational Runbook
Preflight
- Confirm the Research Experiment Design Generator request scope, source evidence, and measurable success criteria before execution.
- Verify feature flag skill_0506_research-experiment-design-gener, approval gates, and rollback owner before autonomous use.
Execution
- Execute hypothesis-driven design with deterministic scoring and reproducible trace capture.
- Produce experiment plans plus scorecard, assumptions, and unresolved-risk notes.
Recovery
- Fail closed when required signals, evidence, or approval gates are missing.
- Rollback to the last stable baseline when posture is critical or validation fails.
Handoff
- Publish experiment plans, validation evidence, and telemetry links to downstream owners.
- Queue follow-up tasks for unresolved risks, threshold tuning, or approval review.
Guardrails
- [quality] Require deterministic scoring and validation evidence before promotion.
- [reliability] Preserve retries, rollback controls, and failure-mode evidence for every run.
- [safety] Route critical posture or missing approval gates to human review before autonomous action.