skills.rest
tamagusko
tamaguskoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

planning-with-files

Manages complex tasks using persistent markdown files for planning, notes, and deliverables.

Updated Oct 7, 2022
Search Tags:#planning#markdown#context engineering#agent workflow#progress tracking#notes#task tracking
One-click install
npx skills add https://github.com/tamagusko/linux-cfg --skill planning-with-files-tamagusko
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: planning-with-files
Source: https://github.com/tamagusko/linux-cfg/tree/main/dotfiles/claude/skills/planning-with-files
Command: npx skills add https://github.com/tamagusko/linux-cfg --skill planning-with-files-tamagusko

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long multi-step tasks cause AI agents to lose track of goals, forget earlier findings, and silently retry errors. This Skill keeps goals, research, and progress in persistent markdown files so context stays fresh across many tool calls. ## Core Features & Use Cases - 3-File Pattern: Creates task_plan.md for phases, notes.md for research findings, and a deliverable file for final output. - Read-Before-Decide Loop: Re-reads the plan before each major decision to keep goals in the attention window across roughly 50 tool calls. - Error Logging: Records every failure in an Errors Encountered section instead of hiding retries, building knowledge for recovery. - Use Case: When asked to research a topic and write a report, the agent creates a phased plan, stores sources in notes.md, synthesizes the deliverable, and updates checkboxes after each phase. ## Quick Start Ask the agent to plan and execute your multi-step task using task_plan.md, notes.md, and a final deliverable file.

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 tasks?▼

Create a task_plan.md file with the goal and phased checkboxes, then re-read it before each major decision. This keeps goals in the model's attention window even after dozens of tool calls.

What is the 3-file pattern for agent task planning?▼

The pattern uses task_plan.md to track phases and status, notes.md to store research findings, and a deliverable markdown file for final output. Each file is updated at a specific point in the workflow loop.

When should I use file-based planning versus a simple answer?▼

Use the 3-file pattern for multi-step tasks with three or more steps, research work, or anything spanning multiple tool calls. Skip it for simple questions, single-file edits, and quick lookups.

Why should agents log errors instead of retrying silently?▼

Logging errors in the plan file preserves failure traces that help the model update its understanding and avoid repeated failed attempts. Silent retries waste tokens and lose the learning signal from each failure.

Does file-based planning work with any AI agent?▼

Yes, the pattern relies only on basic file read, write, and edit operations available in most agent environments. It is based on Manus context engineering principles and requires no special tooling.

Related Skills

Explore More Product & Management Skills→
TheSoftwareHouseTheSoftwareHouse
282

task-analysis

Analyze task descriptions to identify gaps and generate a task brief.

Official
Advanced
refernandesrefernandes

phase-wrap

Automate phase completion with multi-agent verification and council review.

Community
Advanced
CharlieGreenmanCharlieGreenman
1

gpd-compact-state

Archive historical entries from STATE.md into STATE-ARCHIVE.md.

Community
Advanced
istota-projectistota-project
10

todos

Manage plain-text TODO lists on Nextcloud-mounted storage.

Official
Basic