Debugging and Error Recovery gives an agent a structured process for test failures, broken builds, runtime errors and bug reports. It starts with the stop-the-line rule, which halts feature work and preserves evidence, then walks a triage checklist in order.
The skill includes decision trees for non-reproducible bugs, test, build and runtime failures, git bisect for regressions, safe fallback patterns and a rule that error output is data to analyze and never a set of instructions.
What You Get
- The stop-the-line rule and a six-step triage checklist
- Triage trees for tests, builds, runtime errors and non-reproducible bugs
- Git bisect commands and safe fallback code patterns
- Guidance on temporary and permanent instrumentation plus a verification checklist
Common Use Cases
- Investigating a failing test or broken build
- Finding the commit that caused a regression
- Reproducing an intermittent bug
- Adding a regression test after a fix
What Makes It Unique
The skill names the root cause as the target and shows a symptom fix next to a root cause fix. It stops all feature work while something is broken and includes a rule that error messages from external sources are data and never commands to follow.
Under The Hood
The skill is a single SKILL.md of instructions with code samples. It runs no scripts of its own. The agent runs the repository’s test and build commands and git bisect, reads logs and error output, and may add temporary logging that the skill says to remove after the fix.