skills.rest
chisuhua
chisuhuaCOMMUNITY
Explore all skills by this author →
GitHub

planning-with-files

Creates persistent markdown planning files to track phases, findings, and progress across sessions.

Updated Mar 4, 2026
Search Tags:#workflow#planning#documentation#markdown#context management#task tracking#session recovery
One-click install
npx skills add https://github.com/chisuhua/home --skill planning-with-files-chisuhua
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: planning-with-files
Source: https://github.com/chisuhua/home/tree/main/.config/opencode/skills/planning-with-files
Command: npx skills add https://github.com/chisuhua/home --skill planning-with-files-chisuhua

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Complex multi-step tasks lose context when sessions end or the context window fills up, causing repeated mistakes and forgotten goals. This Skill stores plans, findings, and progress in markdown files on disk so work survives interruptions and stays organized. ## Core Features & Use Cases - File-Based Planning: Creates task_plan.md, findings.md, and progress.md in your project directory to track phases, discoveries, and session logs. - Session Recovery: Detects unsynced context from previous sessions via a catchup script that checks planning files and uncommitted git changes. - Structured Error Handling: Enforces a 3-strike error protocol and error logging to prevent repeating failed approaches. - Use Case: When starting a research project or feature build requiring many tool calls, initialize the three planning files, then update them after each phase so you can resume instantly after a break or /clear. ## Quick Start Ask the AI to initialize planning files for this project and create a task plan before starting the complex task.

Frequently Asked Questions about planning-with-files

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

FAQPage Schema
How do I keep an AI agent on track during long multi-step tasks?▼

Create persistent markdown files (task_plan.md, findings.md, progress.md) in your project root before starting work. Re-read the plan before decisions and update it after each phase so goals stay in the attention window.

How to recover context after clearing an AI chat session?▼

Run the session-catchup.py script with your project directory as the argument. It reports the status of planning files and uncommitted git changes, letting you reconcile the plan with actual code changes before resuming.

When should I use file-based planning instead of a todo list?▼

Use it for tasks with three or more phases, research projects, or anything requiring more than five tool calls. Skip it for single-file edits, quick lookups, and simple questions where persistence adds overhead.

Where are the planning files created?▼

Planning files go in your project root directory, not the skill installation folder. Only templates and scripts live in the skill directory; working files travel with your project.

What happens if a task keeps failing with the same error?▼

The 3-strike protocol applies: first diagnose and fix, then try an alternative approach, then rethink assumptions. After three failures, escalate to the user with the full attempt history logged in the plan file.

Related Skills

Explore More Software Engineering Skills→
hilaryosbornehilaryosborne

da-planning

Define objectives and scope for data analytics project planning.

Community
Basic
juniorfontenelejuniorfontenele

implement-task

Create semantic branches, write code, run quality gates, and update progress tracking.

Community
Advanced
cloudbro-kube-aicloudbro-kube-ai
14

verification-before-completion

string

Official
Intermediate
foomakersfoomakers
6

pair-capability-write-issue

Create or update issues in GitHub Projects, Jira, or Linear using templates.

Official
Advanced