aris-research-refine-pipeline

Chains method refinement and experiment planning into one end-to-end research proposal pipeline.

1.1k|116|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/OpenLAIR/dr-claw --skill aris-research-refine-pipeline
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aris-research-refine-pipeline
Source: https://github.com/OpenLAIR/dr-claw/tree/main/skills/aris-research-refine-pipeline
Command: npx skills add https://github.com/OpenLAIR/dr-claw --skill aris-research-refine-pipeline

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Turning a vague research direction into both a focused method proposal and a detailed experiment roadmap normally requires running two separate workflows and manually keeping them consistent. This Skill chains the aris-research-refine and aris-experiment-plan stages so the final proposal, review history, and validation plan stay aligned in one pass.

Core Features & Use Cases

  • End-to-End Pipeline: Runs method refinement first, then generates a claim-driven experiment plan grounded in the refined proposal.
  • Planning Gate: Enforces an explicit checkpoint that verifies the method thesis, dominant contribution, and rejected complexity before any experiments are planned.
  • Structured Deliverables: Produces FINAL_PROPOSAL.md, REVIEW_SUMMARY.md, REFINEMENT_REPORT.md, EXPERIMENT_PLAN.md, EXPERIMENT_TRACKER.md, and PIPELINE_SUMMARY.md under refine-logs/.
  • Use Case: A researcher with only a rough idea for a paper asks to do everything end-to-end, and receives a stabilized method thesis plus a prioritized experiment roadmap with run order, budget, and decision gates.

Quick Start

Ask the assistant to run the aris-research-refine-pipeline on your rough research idea to produce a refined proposal and experiment plan together.

Frequently Asked Questions about aris-research-refine-pipeline

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

FAQPage Schema
How do I go from a vague research idea to an experiment plan in one step?

Run the aris-research-refine-pipeline with your rough research direction. It first stabilizes the method thesis through the refinement stage, then generates a claim-driven experiment plan, ending with a PIPELINE_SUMMARY.md describing next actions.

What files does the research refine pipeline generate?

It writes six Markdown deliverables under refine-logs/: FINAL_PROPOSAL.md, REVIEW_SUMMARY.md, REFINEMENT_REPORT.md, EXPERIMENT_PLAN.md, EXPERIMENT_TRACKER.md, and PIPELINE_SUMMARY.md. These keep the method claims consistent across the proposal and experiment plan.

When should I use the pipeline instead of the individual refine or experiment-plan skills?

Use the pipeline when you want both the refined method and the experiment roadmap in one shot. If you only need method refinement or only experiment planning, invoke aris-research-refine or aris-experiment-plan separately.

Can the pipeline reuse an existing final proposal?

Yes. During triage it checks whether refine-logs/FINAL_PROPOSAL.md exists and still matches the current request. If the proposal is strong and aligned, it skips refinement and jumps directly to experiment planning.

What happens if the method is still marked REVISE after refinement?

The pipeline only proceeds to experiment planning if the remaining weaknesses are clearly documented. A planning gate verifies the method thesis, dominant contribution, and rejected complexity before any experiments are designed.