Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Added _meta.json file to the skill package. - No changes to skill behavior or documentation.
What This Skill Does
A slash command that forwards your exact shell command directly to OpenClaw's exec tool without any model rewriting or planning overhead. You type the command, it runs as-is. Useful when you want deterministic, immediate terminal execution.
Bypasses the model planning loop entirely, so you get immediate execution with zero rewriting when you already know the exact command.
When to use it
- Running git status or log checks without agent overhead
- Quickly grepping for TODOs across a project
- Inspecting files and directories during a debug session
- Checking Peekaboo bridge status on macOS
- Running one-liner scripts for structured JSON output
Example Workflow
Here's how your AI assistant might use this skill in practice.
User types: /term rg -n "TODO|FIXME" .
- 1Receives raw argument string: rg -n "TODO|FIXME" .
- 2Forwards it unchanged to the exec tool
- 3Executes the command in the current runtime environment
- 4Returns stdout/stderr output directly to the user
Line-numbered list of all TODO and FIXME occurrences in the project