planning

Name: planning
Availability: InStock
Author: felixmin

Create and refine dated canonical plans in docs/plan/ through multi-stage reviews.

Updated Oct 23, 2025

Search Tags:#workflow #planning #documentation #refinement #experiment design #review

Ready to run

npx skills add https://github.com/felixmin/robot-learning-from-video --skill planning-felixmin

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: planning
Source: https://github.com/felixmin/robot-learning-from-video/tree/main/.codex/skills/planning
Command: npx skills add https://github.com/felixmin/robot-learning-from-video --skill planning-felixmin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the process of scoping and refining non-trivial changes or experiments by establishing a clear, repo-local planning workflow.

Core Features & Use Cases

Canonical Plan Creation/Update: Generates or refines a dated, canonical plan document in docs/plan/.
Multi-Stage Review: Orchestrates reviews with designated pragmatic, system-level, and deep-learning reviewers, with optional compute and devil's advocate reviews.
Use Case: Before undertaking a significant refactor of the robot policy model, use this Skill to draft an initial plan, get it reviewed by the core team, and iterate on it until it's implementation-ready.

Quick Start

Use the planning skill to create a new plan for the upcoming feature.

Frequently Asked Questions about planning

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

FAQPage Schema

How do I plan and refine non-trivial code changes before implementation?▼

To plan and refine non-trivial code changes, you can use a structured planning workflow to generate a dated canonical plan document in `docs/plan/` and iteratively refine it through a multi-stage review process.

What is a repo-local planning workflow for software engineering?▼

A repo-local planning workflow is a structured process that scopes significant refactors or experiments by creating explicit written plans directly within the repository, ensuring team alignment and risk assessment before implementation begins.

How do I coordinate a multi-stage review for technical documentation?▼

You can coordinate a multi-stage review for technical documentation by orchestrating feedback from designated pragmatic, system-level, and deep-learning reviewers, alongside optional compute and devil's advocate reviews to refine the plan.

When do I need to create a canonical plan for an experiment design?▼

You need to create a canonical plan for an experiment design when undertaking non-trivial changes that require explicit written plans, risk assessment, and multi-reviewer alignment prior to starting the actual implementation.

Does the planning workflow require any external dependencies?▼

No, the planning workflow operates without external dependencies, relying entirely on repo-local scripts and references to manage the creation and refinement of your dated canonical plan documents.

What's the best way to scope a significant refactor with multiple reviewers?▼

The best way to scope a significant refactor with multiple reviewers is to draft an initial plan in `docs/plan/` and iterate on it through structured pragmatic, system-level, and deep-learning reviews until it is implementation-ready.