project-maintenance

Automate project closure, plan archiving, and memory cleanup in Claude Code.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Git-Fg/taches-principled-light --skill project-maintenance-git-fg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: project-maintenance
Source: https://github.com/Git-Fg/taches-principled-light/tree/main/skills/project-maintenance
Command: npx skills add https://github.com/Git-Fg/taches-principled-light --skill project-maintenance-git-fg

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps streamline the process of wrapping up projects, archiving completed plans, and maintaining clean Claude's working memory to prevent knowledge duplication and stale data accumulation.

Core Features & Use Cases

  • Project Archival: Safely archive completed plans to preserve project knowledge and learnings.
  • Memory Hygiene: Deduplicate and archive memory files to clean Claude's working memory and optimize session insights.
  • Use Case: After completing a project, use this Skill to archive all associated plans and memory entries, ensuring that the next project starts with a clean slate.

Quick Start

To archive the current project, run the project-maintenance skill with the 'archive plan' command.

Frequently Asked Questions about project-maintenance

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

FAQPage Schema
How do I automate plan archiving and memory cleanup in Claude Code?

Automate plan archiving and memory cleanup by running the project-maintenance skill with the 'archive plan' command, which safely archives completed plans and deduplicates memory files to optimize session insights.

What is the best way to deduplicate working memory files after a project wraps up?

The best way to deduplicate working memory files is using project-maintenance, which cleans Claude's working memory by archiving stale data and preventing knowledge duplication, ensuring the next project starts fresh.

Does Claude Code project closure require Python and YAML for metadata processing?

Yes, Claude Code project closure requires Python for file manipulation and YAML for metadata processing to safely archive plans and clean up memory artifacts.

When do I need to archive completed plans and clean project memory?

You need to archive completed plans and clean project memory after finishing a project to prevent stale data accumulation, preserve project knowledge, and maintain a clean slate for future sessions.

Can I generate reports on memory and plan artifacts during project closure?

Yes, you can generate reports on memory and plan artifacts during project closure, as the project-maintenance skill supports deduplication, archiving, and reporting on these artifacts.

Why does stale data accumulate in Claude's working memory and how is it managed?

Stale data accumulates in Claude's working memory from ongoing project artifacts, managed by project-maintenance through memory deduplication and archiving to prevent knowledge duplication and optimize session insights.