subagent-driven-analysis

Name: subagent-driven-analysis
Availability: InStock
Author: K-Dense

Dispatch a fresh subagent per preregistered analysis step with two-stage reviews.

282|26|Updated May 28, 2026

Search Tags:#automation #subagents #reproducibility #analysis-plan #protocol-review #pre-registered #rigor-review

Ready to run

npx skills add https://github.com/K-Dense-AI/science-superpowers --skill subagent-driven-analysis

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-driven-analysis
Source: https://github.com/K-Dense-AI/science-superpowers/tree/main/skills/subagent-driven-analysis
Command: npx skills add https://github.com/K-Dense-AI/science-superpowers --skill subagent-driven-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating pre-registered analyses by dispatching a fresh subagent per step to ensure isolation, auditability, and reproducible results.

Core Features & Use Cases

Fresh subagent per step to keep context isolated and reduce cross-step leakage.
Two-stage review: protocol-compliance review followed by rigor/quality review for reproducibility and correctness.
Enforced preregistration: analyses must be frozen before execution; deviations are flagged and handled.
End-to-end research workflows: suitable for multi-step experiments, simulations, or data analyses with auditable traces.

Quick Start

Dispatch the analyst subagent for each preregistered step, then complete protocol-compliance and rigor reviews and commit the results.

Frequently Asked Questions about subagent-driven-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I run pre-registered analyses without cross-step context leakage?▼

To run pre-registered analyses without context leakage, dispatch a fresh subagent for each step to ensure isolation. This approach maintains independent step execution and produces auditable traces for your research workflow.

What is the best way to enforce protocol compliance during automated data analysis?▼

The best way to enforce protocol compliance in automated data analysis is using a two-stage review process. After dispatching the analyst subagent, complete a protocol-compliance review followed by a rigor review to validate outputs and ensure reproducibility.

Can I execute an analysis plan if the preregistration is not frozen?▼

No, you cannot execute an analysis plan if the preregistration is not frozen. The workflow requires the analysis preregistration to be frozen before execution, and any deviations from this frozen protocol are flagged and handled.

How does dispatching isolated subagents improve research reproducibility?▼

Dispatching isolated subagents improves research reproducibility by keeping context separate for each step. This isolation prevents cross-step leakage, ensures strict adherence to preregistered steps, and generates auditable traces for multi-step experiments and data analyses.

When do I need a two-stage rigor review for my analysis protocol?▼

You need a two-stage rigor review when executing multi-step experiments or simulations requiring strict adherence to preregistered steps. The protocol-compliance and rigor reviews validate outputs, ensuring correctness and reproducible results after the analyst subagent finishes.

Does this subagent-driven analysis approach work for multi-step experiments?▼

Yes, this subagent-driven analysis approach works for multi-step experiments, simulations, and data analyses. It coordinates end-to-end research workflows by dispatching fresh subagents per step and committing the results after two-stage reviews.