What problem does it solve?
This Skill eliminates the risk of losing track of goals, progress, and critical discoveries during long, multi-step AI tasks that require dozens of tool calls, where volatile context windows cause important information to be forgotten between interactions.
Core Features & Use Cases
- Persistent Phase Tracking: Creates and maintains a task_plan.md file to break complex work into manageable phases, track completion status, and log errors to avoid repeating failed actions.
- Research & Discovery Storage: Uses findings.md to capture research results, technical decisions, and multimodal content (like browser results or image findings) immediately after discovery, before context is lost.
- Session Recovery & Parallel Workflows: Automatically recovers unsynced context after a /clear command, and supports isolated plan directories for working on multiple independent tasks in the same repository simultaneously.
- Use Case: Ideal for tasks like technical research, feature development, complex bug fixes, or any project requiring 5 or more tool calls across multiple sessions.
Quick Start
Ask the AI to use the planning-with-files skill to break down your multi-step project into tracked phases, capture all research findings and errors, and maintain a session log for seamless recovery after context resets.