planning-with-files

Maintain plan, findings, and progress in on-disk files for long-running projects.

2|Updated Mar 20, 2026
One-click install
npx skills add https://github.com/Gonglitian/agent-skills --skill planning-with-files-gonglitian
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: planning-with-files
Source: https://github.com/Gonglitian/agent-skills/tree/main/skills/planning-with-files
Command: npx skills add https://github.com/Gonglitian/agent-skills --skill planning-with-files-gonglitian

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Manus-style planning addresses the challenge of maintaining context and progress across long, multi-tool tasks by storing planning artifacts on disk, enabling recovery and continuity between sessions.

Core Features & Use Cases

  • Persistent plan, findings, and progress files enable recovery after breaks and sessions.
  • Phase-tracking and templates guide structured workflows for complex tasks.
  • Hooks and scripts support automated reminders, session initialization, and progress updates.

Quick Start

Create task_plan.md, findings.md, and progress.md in your project root to start a new planning session.

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 persistent context for long-running multi-phase tasks?

To plan complex tasks, initialize task_plan.md, findings.md, and progress.md in your project root using provided templates and scripts to structure workflows and track phase completion.

Can I recover a planning session after a break or unexpected interruption?

Session recovery is supported by reading existing on-disk files like progress.md and task_plan.md, allowing you to resume cross-tool workflows exactly where the previous session left off.

What is the best way to coordinate cross-tool workflows without losing track of findings?

Coordinate cross-tool workflows by writing intermediate findings to a dedicated findings.md file on disk, ensuring research data persists independently of active session memory.

Do I need any external dependencies to implement on-disk persistent memory for task planning?

No external dependencies are required to implement persistent memory; the workflow relies entirely on standard on-disk markdown files and bundled scripts for initialization and updates.