Advanced debugger

Skill rafaelghif/antigravity-agents/.agents/skills/advanced-debugger

Enterprise-Grade Guardrails, Zero-Assumption Execution, and Quality Gates for Autonomous AI Coding Agents.

Install

npx -y skills add rafaelghif/antigravity-agents --skill advanced-debugger

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Enforces a scientific, methodical approach to debugging across any tech stack.

SKILL.md

1.8 KB, as published. Nobody here has run it

Advanced Debugger Skill

Objective

To prevent the agent from blindly guessing solutions or wildly changing code when facing a bug. This skill enforces the "Scientific Debugging Method" using verifiable logging and stack trace analysis.

When to Execute

Whenever resolving an issue labeled as a "bug".
Whenever a test fails during execution.
Whenever a runtime error or unexpected output occurs.

Execution Steps

Hypothesis Formulation:
- STOP. Do not change the application logic yet.
- Read the error message or stack trace carefully.
- Formulate 1-3 hypotheses about what could be causing the issue (e.g., "Null pointer at line X because the API returned empty").
Probe Insertion (Language-Agnostic):
- Insert temporary logging or debugging probes into the code to verify the hypothesis.
- Use the appropriate syntax for the language:
  - Python: print(), logging.debug()
  - PHP: var_dump(), error_log()
  - JS/TS: console.log()
  - Java/C#: System.out.println(), Console.WriteLine()
  - Go: fmt.Printf()
Execution & Evidence Gathering:
- Run the specific file, test, or trigger the endpoint.
- Collect the output of the probes.
Analysis & Targeted Fix:
- Did the probe output confirm the hypothesis?
  - Yes: Implement the targeted fix for the logic.
  - No: Remove the old probes, formulate a new hypothesis, and repeat Step 2.
Cleanup:
- Once the bug is fixed, MUST remove all temporary debugging probes (print, console.log, etc.) before committing the code.