planning-with-files-es

Create task_plan.md, findings.md, and progress.md to track multi-step tasks across sessions.

1|Updated Apr 22, 2026
One-click install
npx skills add https://github.com/Herxinsasa/Skills-Collector --skill planning-with-files-es
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: planning-with-files-es
Source: https://github.com/Herxinsasa/Skills-Collector/tree/main/planning-with-files/skills/planning-with-files-es
Command: npx skills add https://github.com/Herxinsasa/Skills-Collector --skill planning-with-files-es

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires orjson, and includes scripts (resource) components.

What problem does it solve?

Complex multi-step tasks often exceed an AI's context window, causing lost objectives, forgotten progress, and repeated mistakes after context resets or long sessions.

Core Features & Use Cases

  • Persistent Task Planning: Creates and maintains task_plan.md to track phases, objectives, and decisions across sessions.
  • Findings Repository: Uses findings.md to capture research, discoveries, and visual/browser data before it disappears from context.
  • Progress Logging: Maintains progress.md as a chronological session record for error tracking and restart validation.
  • Auto-Recovery: Includes session catch-up scripts to restore context after /clear or interruptions.
  • Use Case: Ideal for research projects, multi-phase development, bug investigations, or any task requiring more than 5 tool calls where context persistence is critical.

Quick Start

Use the planning-with-files-es skill to organize your complex multi-step project by creating task_plan.md, findings.md, and progress.md files to track phases, findings, and progress.

Frequently Asked Questions about planning-with-files-es

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

FAQPage Schema
How do I maintain project planning state across multiple AI sessions?

Maintain project planning state across multiple AI sessions by using persistent markdown files like task_plan.md, findings.md, and progress.md to track phases, log discoveries, and record chronological progress. This prevents context loss and forgotten objectives during complex multi-step tasks.

Why does my AI lose track of objectives during complex multi-step tasks?

Your AI loses track of objectives during complex multi-step tasks because the required operations exceed the context window, causing forgotten progress and repeated mistakes. Persistent markdown planning files solve this by storing task phases, findings, and decisions externally.

How to recover task context after a context window reset or session interruption?

Recover task context after a context window reset or session interruption by running session catch-up automation scripts that read the persistent task_plan.md, findings.md, and progress.md files to restore the previous workflow state and validate restart points.

When do I need persistent markdown files for task tracking?

You need persistent markdown files for task tracking when working on research projects, multi-phase development, or bug investigations requiring more than five tool calls. This approach ensures state recovery and context persistence across long sessions where context window limits cause data loss.

Do I need orjson to use markdown-based planning and tracking?

Yes, you need the orjson dependency installed to run the initialization and session catch-up automation scripts. These scripts manage the creation and recovery of task_plan.md, findings.md, and progress.md files in your project root directory.