research-refine

Refine vague research directions into anchored method plans with Codex MCP review.

2|Updated Mar 20, 2026
One-click install
npx skills add https://github.com/Gonglitian/agent-skills --skill research-refine-gonglitian
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research-refine
Source: https://github.com/Gonglitian/agent-skills/tree/main/skills/research-refine
Command: npx skills add https://github.com/Gonglitian/agent-skills --skill research-refine-gonglitian

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps researchers transform vague directions into anchored, elegant, and implementable research plans.

Core Features & Use Cases

  • Anchored problem formulation: freezes a core Problem Anchor to keep iterations focused.
  • Phase-driven refinement: Phase 1 scans grounding material, Phase 2 reviews, Phase 3 refines, Phase 4 re-evaluates.
  • Output-ready proposals: produces a concrete method plan with a minimal validation roadmap suitable for publication or grant proposals.

Quick Start

Provide a rough research idea and a target outcome; the skill will generate an anchored, implementable plan and a concise validation path.

Frequently Asked Questions about research-refine

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

FAQPage Schema
How do I turn a vague research idea into a concrete method plan?

To turn a vague research idea into a concrete method plan, use an iterative, round-based refinement process that scans grounding material and freezes a core problem anchor. This produces an anchored, elegant, and implementable proposal with a minimal validation roadmap.

What is an anchored problem in research proposal development?

An anchored problem in research proposal development is a frozen core focus point that prevents scope drift during iterative refinement. Formulating an anchored problem keeps subsequent phases of method planning targeted and ensures the final proposal remains implementable.

Can I use iterative round-based refinement for grant proposal validation?

Yes, you can use iterative round-based refinement for grant proposal validation. The process evaluates and re-evaluates the research plan across multiple phases, producing an output-ready proposal with a concise, minimal validation path suitable for publication or grant submissions.

How do I create a publish-ready research plan from a rough direction?

You create a publish-ready research plan from a rough direction by submitting a rough idea and target outcome to a phase-driven refinement workflow. The system scans, reviews, and refines the direction into a focused method with a practical validation roadmap.

Does automated proposal review work for student research projects?

Automated proposal review works effectively for student research projects by providing phase-driven refinement. It helps students transform unstructured directions into elegant, implementable plans with minimal validation steps, ensuring their proposals are practical and focused.

What are the limitations of automated research plan refinement?

The limitations of automated research plan refinement include its dependency on the initial rough idea's viability and the need for Codex MCP review. While it produces an implementable plan, researchers must still manually ensure the anchored problem aligns with real-world constraints.