plan-refactor — community plan-refactor, super-red, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for Code Analysis Agents needing advanced refactoring capabilities for GitHub repositories. An endless-runner style mobile game

adtak adtak
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The plan-refactor skill by adtak is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Perfect for Code Analysis Agents needing advanced refactoring capabilities for GitHub repositories.

Core Value

Empowers agents to analyze codebases for refactoring opportunities, create GitHub issues, and present plans to users, leveraging file analysis, duplication detection, and inconsistency resolution.

Capabilities Granted for plan-refactor

Analyzing codebases for large files and duplication
Generating GitHub issues for approved refactoring proposals
Presenting refactoring plans to users for approval and implementation

! Prerequisites & Limits

  • Requires GitHub repository access
  • Limited to codebases with identifiable refactoring opportunities
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

plan-refactor

Install plan-refactor, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Plan Refactor

Analyze the codebase for refactoring opportunities, present a plan to the user, and create GitHub issues for each approved proposal.

Steps

  1. Analyze the codebase — Explore the codebase to identify refactoring opportunities. Focus on:

    • Large files — Files that mix multiple concerns and could benefit from extraction (hooks, utilities, constants)
    • Duplication — Repeated styles, logic, or patterns across files
    • Inconsistency — Style definitions, naming conventions, or patterns that differ from the rest of the codebase
    • Magic numbers — Hardcoded values that should be named constants
    • Dead code — Unused imports, variables, or exports

    Use the project's CLAUDE.md to understand conventions and architecture.

  2. Clarify unknowns — If the analysis reveals ambiguous areas or multiple valid approaches, ask the user before proceeding. Do not make assumptions on ambiguous points.

  3. Draft the plan — Write a refactoring plan listing each proposal. Use the template in plan-template.md for each proposal. Keep proposals independent — each should be implementable on its own.

  4. Present to the user — Show the full plan and ask for approval. The user may:

    • Approve all proposals
    • Remove or modify specific proposals
    • Ask for additional analysis

    Do NOT proceed to issue creation until the user explicitly approves.

  5. Create GitHub issues — For each approved proposal, create a separate GitHub issue using gh issue create --title "<title>" --body "<plan>". Use a HEREDOC for the body to preserve formatting. Title is Short, imperative, in English (e.g., "Extract game loop logic into a custom hook").

  6. Report results — After all issues are created, show the user a summary table with issue numbers, titles, and URLs.

Guidelines

  • Write all issue content in English (project convention).
  • Converse with the user in Japanese (project convention).
  • Keep proposals minimal and focused — one concern per issue.
  • Do not propose changes that add complexity without clear benefit.
  • Reference actual file paths discovered during exploration, not guessed paths.
  • For each file change, specify whether it is Create, Modify, or Delete.
  • Do not include full code in the plan — describe what changes are needed and why.
  • Code snippets are acceptable when they clarify intent (e.g., type definitions, key structures).

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is plan-refactor?

Perfect for Code Analysis Agents needing advanced refactoring capabilities for GitHub repositories. An endless-runner style mobile game

How do I install plan-refactor?

Run the command: npx killer-skills add adtak/super-red/plan-refactor. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for plan-refactor?

Key use cases include: Analyzing codebases for large files and duplication, Generating GitHub issues for approved refactoring proposals, Presenting refactoring plans to users for approval and implementation.

Which IDEs are compatible with plan-refactor?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for plan-refactor?

Requires GitHub repository access. Limited to codebases with identifiable refactoring opportunities.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add adtak/super-red/plan-refactor. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use plan-refactor immediately in the current project.

Related Skills

Looking for an alternative to plan-refactor or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI