lobster-debugging
A systematic 4-phase debugging framework to find root causes, eliminate flaky tests, and prevent regressions.
skill install https://www.promptspace.in/skills/lobster-debuggingWhat it does
Lobster Debugging is a rigorous, 4-phase framework designed to eliminate the "guess-and-check" cycle that plagues modern software development. It transforms your AI agent from a simple code-patcher into a systematic forensic investigator. Instead of applying shallow fixes, it enforces a strict protocol: investigation, condition-based synchronization, defense-in-depth, and academic verification.
Why use this skill
Standard LLMs often rush to provide the first plausible-looking fix, which leads to regression and technical debt. This skill implements the 'Iron Law' of debugging: no fixes allowed without proven root cause isolation. It prevents common pitfalls like "magic" sleep timers, flaky test patches, and symptom-only repairs. By using this skill, you ensure that every bug fixed is a bug that never returns.
How it works
- Phase 1: Investigation: Systematic binary search of the codebase and diagnostic instrumentation.
- Phase 2: Synchronization: Replacing flaky timeouts with robust event-based waiting.
- Phase 3: Defense-in-Depth: Implementing guards that prevent entire classes of similar vulnerabilities.
- Phase 4: Verification: Proving the fix handles edge cases and handles regression testing.
Use cases
- Eliminate flaky test suites by replacing timeouts with event-driven logic
- Perform deep root-cause analysis on complex, multi-component system failures
- Implement defense-in-depth guards to prevent recurring bug categories
- Automate regression test generation for every bug fix discovered
Example
Prompt
Output
[ROOT CAUSE FOUND]: Race condition in Auth Provider. [PREVENTION]: Replaced 500ms sleep with Promise.all() synchronization. [UNIT TEST]: test_auth_persistence_on_slow_network verified. [REGRESSION]: Validated against 4 existing auth edge cases. Result: Bug eliminated, not patched.