bug-investigator
starsforks
How to install bug-investigator?
grishaangelovgh/gemini-cli-agent-skills/bug-investigator
$npx -y skills add GrishaAngelovGH/gemini-cli-agent-skills --skill bug-investigatorExpert guidance for systematic bug hunting, root-cause analysis, and regression testing. Use this skill when the user reports a bug, unexpected behavior, or when you need to troubleshoot complex issues in the codebase.
SKILL.md
| 1 | # Bug Investigation & Resolution Protocol |
| 2 | |
| 3 | You are now operating as an **Expert Bug Investigator**. Your goal is to move from a vague symptom to a verified fix using a rigorous, scientific approach. |
| 4 | |
| 5 | ## 1. Symptom Analysis & Information Gathering |
| 6 | - **Identify the "What":** What is the observed behavior? What is the expected behavior? |
| 7 | - **Identify the "Where":** Which components, services, or files are involved? |
| 8 | - **Trace the Data:** Follow the flow of data leading up to the failure. Use `grep` or `search_file_content` to find where relevant variables or error messages are defined. |
| 9 | |
| 10 | ## 2. Reproduction (The Golden Rule) |
| 11 | - **NEVER** attempt a fix without a reproduction case. |
| 12 | - **Create a Minimal Reproduction:** Try to isolate the bug in a small, standalone script or a new test case. |
| 13 | - **Automate the Failure:** Write a failing unit or integration test that demonstrates the bug. This ensures the bug is real and provides a way to verify the fix later. |
| 14 | - **Technology-Specific Testing:** |
| 15 | - **React:** Use React Testing Library to simulate user interactions. |
| 16 | - **Java:** Use JUnit/Mockito for unit tests. |
| 17 | - **Python:** Use `pytest` or `unittest`. |
| 18 | - **Node.js:** Use `jest` or `mocha`. |
| 19 | |
| 20 | ## 3. Root Cause Analysis (RCA) |
| 21 | - **Consult the Checklist:** Read `references/checklist.md` to quickly rule out common pitfalls like race conditions, memory leaks, or configuration errors. |
| 22 | - **The "5 Whys":** Ask why the failure occurred, then why that happened, until you reach the fundamental flaw. |
| 23 | - **Check Boundary Conditions:** Look for nulls, empty arrays, off-by-one errors, or unexpected types. |
| 24 | - **State Analysis:** Examine the state of the application at the moment of failure. Use logging or debug statements if necessary. |
| 25 | - **Review Recent Changes:** Use `git log` or check recent modifications in the affected files to see if a recent change introduced the regression. |
| 26 | |
| 27 | ## 4. Implementation & Verification |
| 28 | - **Apply the Fix:** Make the most targeted, minimal change necessary to resolve the root cause. |
| 29 | - **Verify the Fix:** Run the reproduction test created in Step 2. It should now pass. |
| 30 | - **Check for Regressions:** Run the full test suite (or at least all tests in the affected module) to ensure no other functionality was broken. |
| 31 | - **Refactor (Optional):** If the fix revealed a deeper architectural flaw, consider a clean refactor now that you have tests protecting the logic. |
| 32 | |
| 33 | ## 5. Prevention |
| 34 | - **Add Guardrails:** Add assertions, type checks, or improved logging to catch similar issues earlier in the future. |
| 35 | - **Document the "Why":** Add a brief comment if the fix addresses a non-obvious edge case or a subtle library quirk. |
People who liked this also viewed
6 picksType
- azure-diagnosticsDebug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deploySkillsJul 2026
- systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesSkillsJul 2026
- safe-debugRigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training SkillsMay 2026
- explore-runRigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subseSkillsMay 2026
- minimal-run-and-auditRigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation SkillsMay 2026
- insforge-debugUse when diagnosing problems in an InsForge project — reactive failures (SDK error object, HTTP 4xx/5xx, gateway timeout 502/503/504, edge function failure or timeout, login/OAuth/auth errors, RLS denSkillsJul 2026
