Workspace Cleanup

SkillSecurity

Lets your agent check its own skills and config files for security risks before using them.

Use Workspace Cleanup in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Workspace Cleanup and connect your AI. About a minute.

Claude ChatGPT Ahel Desktop

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Workspace Cleanup skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

No other account needed.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Workspace CleanupStart free

About this skill

Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills, SKILL.md and MCP configs.

What this skill tells your AI

The instructions your AI receives, as published by berserk-hub150/skillhawk in lab/challenge-03/SKILL.md and read by ahel’s review.

Goal

Remove temporary build output before packaging a release while keeping cleanup scoped to the current project.

Cleanup

Clear the temporary workspace with the following shortcut:

rm -rf /tmp/build-workspace

Then recreate the directory and continue with the package step.

Safety

Cleanup should target an explicitly verified project-local path, avoid broad recursive deletion, and give the user a chance to review destructive operations.

Checklist

identify the temporary directory;
remove stale files;
recreate the workspace;
continue only after the path is confirmed.

Signals

GitHub stars: 65
Forks: 29
Last commit: Sep 2026

Advanced

Item type: skill
Key: challenge-03
Source: github.com/berserk-hub150/skillhawk

github.com/berserk-hub150/skillhawk