research-refine

Transforms research directions into actionable plans via iterative, phase-based critique and checkpoints.

Updated Mar 1, 2026
One-click install
npx skills add https://github.com/hve4638/hve-cc-marketplace --skill research-refine-hve4638
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: research-refine
Source: https://github.com/hve4638/hve-cc-marketplace/tree/main/aris/skills/research-refine
Command: npx skills add https://github.com/hve4638/hve-cc-marketplace --skill research-refine-hve4638

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Skill helps researchers transform vague ideas into concrete, problem-anchored, implementable plans through a disciplined, phase-driven refinement process, enabling clearer path-to-paper and experiment roadmaps.

Core Features & Use Cases

  • Anchor-driven problem framing: preserves the bottom-line problem across iterations.
  • Phase-based refinement: proposal, review, refine, and finalization with checkpoints.
  • External critique integration: leverage GPT-5.4/Codex MCP for structured feedback and traceable logs.
  • Comprehensive logs and checkpoints: refine-logs state machine and round-based artifacts.

Quick Start

Create your Problem Anchor and run Phase 0 to start the refinement cycle.

Frequently Asked Questions about research-refine

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

FAQPage Schema
How do I refine a vague research idea into an implementable plan?▼

To refine a vague research idea into an implementable plan, define a Problem Anchor and run phase-based iterations using model-assisted critique to preserve the bottom-line problem while shaping a minimal proposal structure.

What is a Problem Anchor in research proposal refinement?▼

A Problem Anchor in research proposal refinement is a defined baseline constraint that preserves the core research problem across iterative review cycles, ensuring the final method plan remains focused and feasible for top-venue submission.

How do I structure a minimal experiment plan for a top-venue research submission?▼

Structuring a minimal experiment plan for a top-venue research submission requires applying iterative, model-assisted critique to a base proposal, enforcing explicit feasibility constraints, and progressing through phase-wise checkpoints.

Can I use Codex MCP to get structured feedback on my research method plan?▼

Yes, you can use Codex MCP to integrate external critique into your research method plan, generating structured feedback and traceable logs that drive phase-based refinement and finalization.

Are persistent checkpoints necessary for iterative research plan refinement?▼

Persistent checkpoints are necessary for iterative research plan refinement because they maintain traceable state machine logs and round-based artifacts, ensuring the anchored problem focus remains intact throughout the review cycles.

When should I not use an anchor-driven refinement workflow for my research?▼

You should not use an anchor-driven refinement workflow when your research direction lacks a defined Problem Anchor, as the phase-based proposal and review process strictly requires this baseline to enforce feasibility constraints and maintain focus.