workspace-trash
Soft-delete protection for workspace files. Intercept file deletions and move them to a recoverable trash instead of permanent removal. Use when deleting, removing, or cleaning up files in the workspace. Triggers on /trash, /trash:view, /trash:empty, /trash:restore, or any file deletion request. Also use when the agent needs to rm/delete/remove any file — always trash instead of permanently deleting.
Why use this skill?
Prevent accidental data loss in OpenClaw with workspace-trash. Safely move files to a recoverable trash folder instead of permanent deletion. Easy restore and management.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/crewhaus/workspace-trashWhat This Skill Does
The workspace-trash skill provides essential soft-delete protection for your OpenClaw workspace. Instead of performing irreversible deletions with rm, this skill intercepts file removal requests and moves files to a secure, hidden .trash directory within your workspace. It includes full management capabilities, allowing you to list, restore, or permanently purge files only when you are absolutely certain. By enforcing path validation and symlink resolution, it ensures that your workspace remains safe from accidental data loss or directory traversal vulnerabilities.
Installation
To integrate this safety layer into your environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/crewhaus/workspace-trash
Ensure your OPENCLAW_HOME environment variable is correctly configured, as the skill relies on this to define the safe scope for trash operations.
Use Cases
This skill is indispensable for agents performing routine file maintenance or complex development tasks. Use it when cleaning up old project assets, rotating logs, or deleting redundant code modules. It is particularly valuable during automated cleanup scripts where logic errors might otherwise lead to the permanent loss of work-in-progress files. By routing all deletion requests through this skill, you create a safety net for your AI agent's file system operations.
Example Prompts
- "Delete the
node_modulesfolder in the current project, but put it in the trash in case I need to recover something later." - "/trash:view, show me everything currently sitting in the trash so I can decide what to empty."
- "Restore the
config.jsonfile that I accidentally deleted earlier today."
Tips & Limitations
- Safety First: Always use
/trash:viewbefore running/trash:emptyto verify exactly what files are about to be permanently destroyed. - Scope Boundaries: The skill only functions on paths within
OPENCLAW_HOME. Attempting to trash system files outside this scope will be blocked to ensure your OS remains intact. - Cross-Filesystem: If you encounter issues with
mvcommands across different drives, the skill automatically switches to a safecpandrmfallback, ensuring data integrity during the move process. - Irreversibility: Be aware that the
emptycommand is the only destructive action; there is no 'undo' for emptied trash.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-crewhaus-workspace-trash": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write, code-execution
Related Skills
crewhaus
Quick startup idea evaluation from your terminal. Score ideas on 3 dimensions, run deeper scans with real competitor data and risk assessment. A structured thinking tool for founders — not an oracle.
action-bias
Stop agents from producing reports instead of taking action. Restructure prompts, cron jobs, and agent shifts so they DO things — send emails, post content, make API calls, push code — instead of writing plans about doing things. Use when: agents keep outputting strategy docs instead of executing, sub-agent sessions produce reports nobody reads, you notice your crew is busy but nothing external is happening, heartbeat/shift results are all 'here's what we should do' with no proof of doing it, or you want to audit whether your agents are actually shipping.
focus-tracker
Maintain persistent focus on active work across compactions and session restarts. Use when starting a multi-step project, when resuming after compaction, when the user says "we're working on X", or when you notice you've lost track of what was being done. Also use proactively at session start to check if there's unfinished work. Prevents the agent from forgetting mid-project context, drifting between topics, or asking "what were we doing?" after a compaction.
crew-school
Structured learning system for AI agent crews. Design curricula, run research sessions, track progress, and prevent common failure modes (lazy output, planning-without-executing). Use when setting up agent learning, running training sessions, auditing knowledge gaps, or building a curriculum for specialized agents. Works for single agents or multi-agent crews.
recall
Teaches agents to check before they guess. Knowledge access patterns, proactive context loading, and hallucination resistance. Install before taking the Knowledge-Driven Agent certification.