agi-terminal-helper
by liuwujijay
Coding Agents & IDEsBrief
A practical runbook for using OpenClaw exec safely (sandbox-first, explicit confirmations, and debugging playbooks).
Description
What This Skill Does
A runbook for using OpenClaw's exec tool safely in real workspaces. Covers sandbox vs host execution, working directory discipline, long-running process patterns, and macOS permission issues. Includes concrete playbooks for common failure scenarios like skills not loading or Peekaboo bridge problems.
Instead of generic terminal advice, it gives workspace-specific patterns with explicit safety gates, so destructive commands require confirmation and sandbox/host environment differences don't cause silent failures.
When to Use It
- Debugging why a custom skill isn't loading in OpenClaw
- Running untrusted build scripts in a sandbox environment
- Diagnosing macOS screen recording permission failures in OpenClaw
- Polling long-running test or build processes without blocking
- Auditing a workspace before making destructive file changes
Example Workflow
User asks: why isn't my new skill showing up in OpenClaw?
- 1
Run
ls -la ./skillsto verify the skill folder exists in the workspace - 2
Run
find ./skills -maxdepth 2 -name SKILL.md -printto confirm SKILL.md is present - 3
Check frontmatter in SKILL.md for validity
- 4
Confirm
skills.load.watchis enabled if files were recently changed - 5
Report which precedence layer (workspace vs bundled) is winning
Identified missing SKILL.md or invalid frontmatter; user corrects the file and skill loads on next watch cycle.
Installation
clawhub install liuwujijay/agi-terminal-helperRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.