plan

0xmsc's avatarfrom 0xmsc

Guidelines for iteratively planning tasks and changes before implementation. Use this when the user requests a non-trivial task or when you need to align on a complex implementation strategy.

⭐0stars🔀0forks📁View on GitHub🕐Updated Jan 3, 2026

When & Why to Use This Skill

The 'Plan' skill provides a structured, iterative framework for managing complex tasks and implementation strategies. It ensures that AI agents perform thorough information gathering, dependency mapping, and requirement clarification before executing changes, significantly reducing errors and improving alignment on non-trivial projects.

Use Cases

  • Complex Software Feature Implementation: Use this skill to break down multi-step development tasks into manageable steps with clear verification criteria before any code is written.
  • System Refactoring and Migration: Plan large-scale architectural changes by exploring dependencies and drafting a zero-impact strategy to ensure system stability during the transition.
  • Strategic Technical Alignment: Facilitate better communication between the user and the AI by generating clarifying questions and proposed solutions for complex implementation strategies.
  • Risk Mitigation in Production Environments: Apply the 'Zero-Impact' principle to explore and plan changes without modifying live files until a verified plan is approved.
nameplan
descriptionGuidelines for iteratively planning tasks and changes before implementation. Use this when the user requests a non-trivial task or when you need to align on a complex implementation strategy.

Task Planning

Workflow

  1. Gather Information: Explore codebase and list dependencies.
  2. Draft Plan:
    • Objective: Goal of the task.
    • Approach: High-level strategy.
    • Steps: Sequential actions.
    • Verification: How to prove it works.
  3. Clarify: Include at least 3 clarifying questions with proposed answers.
  4. Approve: Wait for user "go ahead" (empty response = approval).
  5. Implement: Execute only after approval.

Principles

  • Zero-Impact: Do not modify files during planning.
  • Iterative: Refine based on feedback.
  • Concise: Keep plans readable and progress tracked via TODOs.

References