Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Internal debugging instinct - activates when agent hits bugs during tasks
What This Skill Does
An internal debugging and coding protocol for agents. Activates automatically when a command fails, a build breaks, or unexpected behavior occurs mid-task. Provides structured workflows for reproducing errors, tracing causes, applying fixes, and verifying results.
Gives the agent a consistent self-recovery protocol instead of halting and asking the user every time something breaks.
When to use it
- Recovering from a stack trace without interrupting the user
- Tracing a null reference error to its source file and line
- Running the test suite after a code change to confirm nothing regressed
- Spawning a background agent for a large multi-file refactor
- Diagnosing a missing environment variable or broken import path
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: build the project — agent hits a compilation error mid-task
- 1Re-run the failing command to reproduce the exact error
- 2Parse the stack trace to identify the file and line number
- 3Read the relevant file to understand the surrounding code
- 4Trace the call chain through imports and config to find the root cause
- 5Apply the minimal fix, re-run the command, confirm it passes
Build succeeds, agent briefly reports what broke and what changed, then continues the original task