planning-with-files

Maintain task_plan.md, findings.md, and progress.md for multi-step task planning.

Updated Aug 27, 2013
One-click install
npx skills add https://github.com/pkking/dotfiles --skill planning-with-files-pkking
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: planning-with-files
Source: https://github.com/pkking/dotfiles/tree/main/dotfiles/dot_config/opencode/skills/planning-with-files/dot_opencode/skills/planning-with-files
Command: npx skills add https://github.com/pkking/dotfiles --skill planning-with-files-pkking

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill enables Manus-style file-based planning by keeping task_plan.md, findings.md, and progress.md in your project directory as persistent memory that guides decisions.

Core Features & Use Cases

  • Persistent planning: Phases, decisions, and progress are stored on disk to prevent loss of context across sessions.
  • External memory for complex tasks: Centralizes planning artifacts so you can recover after interruptions and refresh context before decisions.
  • Use Case: Start a multi-step research or development task and rely on on-disk planning artifacts to coordinate phases and document findings.

Quick Start

  • Create task_plan.md from templates and begin your plan.
  • Create findings.md and progress.md to log discoveries and session progress.
  • Update phase statuses as you complete milestones and refer back to the plan before decisions.

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 complex projects?

Persistent task planning is achieved by storing phases, decisions, and progress in on-disk markdown files, preventing context loss across sessions during multi-step project execution.

What's the best way to track multi-step research phases and document findings?

Multi-step research phases are tracked by maintaining task_plan.md for milestones, findings.md for discoveries, and progress.md for session updates to align goals across execution phases.

Can I recover my project execution progress after a session reset?

Yes, session recovery after resets is supported by reading the persistent on-disk planning documents, which serve as external working memory to restore context and resume task execution.

Do I need any specific dependencies to use on-disk working memory for task planning?

No external dependencies are required to use on-disk working memory for task planning, as the skill utilizes standard markdown files and built-in scripts for initialization and completion checks.

When should I use file-based planning artifacts instead of in-memory context for project execution?

File-based planning artifacts should be used for complex tasks requiring numerous tool calls, multi-step research, or when project execution needs to survive interruptions and session resets reliably.