planning-with-files

Create persistent Markdown planning files for goals, notes, and deliverables.

1|Updated May 6, 2026
One-click install
npx skills add https://github.com/yckkkk/reo --skill planning-with-files-yckkkk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: planning-with-files
Source: https://github.com/yckkkk/reo/tree/main/.agents/skills/planning-with-files
Command: npx skills add https://github.com/yckkkk/reo --skill planning-with-files-yckkkk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Complex tasks often lose track of goals, context, and progress as work spans multiple sessions and tools. This Skill provides a simple, durable memory by using a three-file pattern to plan, document findings, and capture deliverables.

Core Features & Use Cases

  • Three-file pattern: task_plan.md for goals and phases, notes.md for findings, and [deliverable].md for final output.
  • Loop-driven workflow: Plan → Research → Synthesize → Deliver with a read-before-decision habit to keep goals in focus.
  • Persistent memory: Store large context in files to avoid bloating the AI's memory, while keeping a lightweight in-memory index.
  • Error logging and decision tracing: Update the plan after actions to capture decisions and errors.

Quick Start

Create task_plan.md in your working directory and outline your goal and phases for the task.

Frequently Asked Questions about planning-with-files

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

FAQPage Schema
How do I maintain task planning context across multiple sessions for long-running projects?

Maintain task planning context across multiple sessions by using a persistent Markdown memory pattern. This approach stores goals, progress updates, and decision logs in files, preventing context loss when work spans multiple sessions.

What is the best way to structure complex task plans using Markdown files?

Structure complex task plans using a three-file Markdown pattern: task_plan.md for goals and phases, notes.md for research findings, and a deliverable file for final output. This separates planning from execution details.

How to track decisions and log errors during a multi-step project workflow?

Track decisions and log errors during a multi-step project workflow by updating the task_plan.md file after actions. This creates a durable decision log and captures in-plan errors for future reference.

Do I need any external dependencies to manage project workflows with persistent notes?

No external dependencies are required to manage project workflows with persistent notes. The system relies entirely on standard Markdown files within your working directory to store memory and structure deliverables.

How do I start a research task that requires structured goals and progress updates?

Start a research task by creating a task_plan.md file in your working directory to outline your goal and phases. Follow a loop-driven workflow of planning, researching, synthesizing, and delivering.