workspace-cleanup

Identify and archive clutter in workspace directories using similarity, timestamps, and reference analysis.

Updated Aug 23, 2026

Search Tags:#maintenance #cleanup #workspace #organization #archive #file-management #ai-context

Ready to run

npx skills add https://github.com/dbmcco/claude-agent-toolkit --skill workspace-cleanup

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: workspace-cleanup
Source: https://github.com/dbmcco/claude-agent-toolkit/tree/main/skills/workspace-cleanup
Command: npx skills add https://github.com/dbmcco/claude-agent-toolkit --skill workspace-cleanup

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates workspace clutter that accumulates from AI code generation, preventing context window pollution and making your projects more organized.

Core Features & Use Cases

Multi-Signal Detection: Uses similarity analysis, timestamp checking, and reference scanning to identify actual clutter.
Two-Stage Safety: Archives files first, then prompts for permanent deletion after 30+ days.
Use Case: When your project has multiple versions like auth.ts, auth-new.ts, and auth-fixed.ts, this Skill intelligently identifies and archives the older duplicates while keeping the current version.

Quick Start

Use the workspace-cleanup skill to clean up the current directory and remove clutter.

Frequently Asked Questions about workspace-cleanup

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

FAQPage Schema

How do I reduce AI context pollution from duplicate files in my workspace?▼

Workspace cleanup identifies and archives duplicate or obsolete files like `auth.ts`, `auth-new.ts`, and `auth-fixed.ts` using similarity analysis, timestamp checking, and reference scanning. This removes clutter that consumes AI context without losing data—archived files stay retrievable for 30+ days before permanent deletion.

What's the best way to organize a messy project with temp files and old versions?▼

Multi-signal detection scans your directory for temp files, sync conflicts, and abandoned experiments, applying tiered confidence scoring to distinguish clutter from active code. Files move to a central archive with metadata, preserving your project structure while clearing the workspace.

Can I safely clean up my workspace without permanently deleting files?▼

Yes, a two-stage safety workflow archives files first, then prompts for deletion only after 30+ days. This gives you time to verify nothing critical was removed before permanent cleanup occurs.

How does workspace cleanup handle recursive cleanup across nested directories?▼

The Skill supports both recursive cleanup across entire workspace trees and scoped targets for specific directories based on your prompts. You control the scope—clean everything or target particular folders with clutter.

What types of clutter can the cleanup process detect?▼

Detection identifies temp files, multiple versions of the same file, sync conflicts, and abandoned experiments through similarity matching, timestamp analysis, and import/reference tracking across your project.