Super Session Cleanup
Paste the following prompt into your AI chat to install this skill:
Please install @user_573a6bcd/super-session-cleanup using https://skillhub.cn/install/skillhub.md.
About this skill
Problem
Agent sessions often leave behind temporary files, pip / npm packages, and Skill directories. Some are demo scripts, some are system software, and after the session they are easy to forget, which can pollute the workspace and make safe removal harder.
How It Works
The skill uses a two-phase workflow:
- Tracking: after activation, it writes to /.workbuddy/session-track.json and records temporary files, package installs, Skill paths, and explicitly tracked items after tool calls.
- Cleanup: it prints a checklist, classifies items into safe to delete and needs confirmation, then deletes temp files directly while asking before removing packages or Skills, preferring trash-first behavior.
Boundaries
It is meant for session-scoped artifact cleanup, not general disk cleaning. Removing a Skill is permanent, and system software, global packages, or dependencies require confirmation. If deletion fails, the skill stops and reports the error instead of widening the deletion path.
Use Cases
- After an agent creates multiple demo scripts, start tracking and delete them from a final checklist.
- After installing temporary Python and npm packages for validation, confirm and uninstall only unwanted deps.
- After initializing a trial Skill under `.workbuddy/skills`, list the Skill path and confirm directory removal.
- When a demo script must be kept, mark it to skip, then clean the remaining session resources.
Best For
- Developers maintaining Claw-family agents who want safe cleanup of session files and installed packages.
- Automation engineers who need checklist-based confirmation after testing scripts, packages, or Skills.
- AI workspace teams who want to track `.workbuddy` session artifacts without deleting project files.
- Agent users on macOS, Windows, or Linux who need OS-aware trash-first cleanup of temporary resources.
Related Skills
Automatically searches job postings based on the user profile, AI-scores fit, saves desktop reports, and sends email updates with scheduled tracking.
Activates bionic reasoning for causal judgment, numerical prediction, and hypothesis validation, using hypothesis-driven checks, Bayesian updates, falsifiability tests, bias defense, and physical constraints.
Triggered by /plan, it asks the agent to output a plan, risks, impact scope, and validation approach before execution.
For AI chat and Skill development, provides templates, batch creation, context archiving, and model selection guidance to reduce token and credit usage.