planning-with-files-zh

Create Markdown planning files to track progress across multi-session tasks.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

When working on complex, multi-step tasks that require dozens of tool calls across multiple sessions, the AI's volatile context window loses track of progress, past decisions, and research findings, leading to repeated work, inconsistent outputs, and broken context after session resets or /clear commands.

Core Features & Use Cases

  • Persistent Planning Files: Creates three durable Markdown files (task_plan.md for phase tracking, findings.md for research and decisions, progress.md for session logs) that act as long-term working memory outside the context window.
  • Automatic Session Recovery: Detects unsynced context from previous sessions after context resets, and provides a summary of missed work to resume tasks seamlessly.
  • Built-in Guardrails: Enforces rules like the two-step operation rule to prevent loss of multimodal findings, error logging to avoid repeated failures, and a three-strike failure protocol to break out of unproductive loops.
  • Use Cases: Ideal for product analysis, multi-step project planning, complex bug diagnosis, research tasks, and any workflow requiring more than 5 sequential tool calls.

Quick Start

Use the planning-with-files-zh skill to break down my upcoming 3-phase e-commerce checkout feature redesign into tracked steps and initialize the required planning files in my project directory.

Frequently Asked Questions about planning-with-files-zh

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

FAQPage Schema
How do I preserve context and track progress for complex multi-step tasks across multiple sessions?

To preserve context for complex multi-step tasks, you can use persistent Markdown planning files like task_plan.md, findings.md, and progress.md that act as long-term working memory outside the AI's volatile context window. This prevents inconsistent outputs and repeated work after session resets.

What is automatic session recovery for project planning workflows?

Automatic session recovery detects unsynced context from previous sessions after context resets or /clear commands. It provides a summary of missed work to resume multi-step project planning and research workflows seamlessly without losing track of past decisions.

How do I prevent repeated failures during long technical troubleshooting workflows?

To prevent repeated failures during technical troubleshooting, built-in guardrails enforce error logging and a three-strike failure protocol to break out of unproductive loops. A two-step operation rule also safeguards multimodal research findings from being lost.

When do I need persistent planning files for task tracking?

You need persistent planning files for task tracking when working on complex workflows requiring more than 5 sequential tool calls. They are ideal for product analysis, multi-step project planning, complex bug diagnosis, and research tasks that exceed the AI's volatile working memory.

Can I use Markdown files to manage multi-step research workflows without losing findings?

Yes, you can use durable Markdown files to manage multi-step research workflows without losing findings. The skill creates findings.md specifically to store research data and decisions, ensuring multimodal findings persist outside the context window across sessions.