Standardized process to identify and fix bugs through repeatable testing.

Install

mkdir -p .claude/skills/debug-mrgit-bit && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13498" && unzip -o skill.zip -d .claude/skills/debug-mrgit-bit && rm skill.zip

Installs to .claude/skills/debug-mrgit-bit

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Disciplined debugging loop for broken behavior, failing tests, exceptions, flaky failures, and performance regressions. Use when the user says "debug this", "diagnose this", "this is broken", "this is failing", or reports a reproducible or intermittent bug.
257 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Build a repeatable feedback loop for bugs
  • Reproduce reported failures
  • Formulate falsifiable hypotheses
  • Instrument code to probe hypotheses
  • Apply fixes with regression coverage

How it works

The skill establishes a feedback loop to reproduce bugs, generates falsifiable hypotheses, probes them through instrumentation, and applies fixes with regression tests.

Inputs & outputs

You give it
Reported symptom or failing test
You get back
Confirmed root cause, validated fix, and regression coverage

When to use debug

  • Debug failing test
  • Reproduce intermittent bug
  • Analyze system exception

About debug

Facilitates a loop of creating failing tests, reproducing symptoms, and applying verified fixes to ensure regression coverage.

Disciplined debugging loop for broken behavior, failing tests, exceptions, flaky failures, and performance regressions. Use when the user says "debug this", "diagnose this", "this is broken", "this is failing", or reports a reproducible or intermittent bug.

When not to use it

  • When the cause of the bug is already confirmed
  • When no useful feedback loop can be created

Limitations

  • Skip a phase only when the reason is explicit
  • If no useful loop is possible, stop and state what was tried

How it compares

This skill provides a disciplined, phased approach to debugging, focusing on repeatable reproduction and falsifiable hypotheses, unlike ad-hoc troubleshooting.

Compared to similar skills

debug side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
debug (this skill)03moNo flagsIntermediate
python-testing-patterns772moReviewIntermediate
chrome-devtools417moReviewIntermediate
bats97moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

python-testing-patterns

wshobson

Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.

77204

chrome-devtools

mrgoonie

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

41157

bats

OleksandrKucherenko

Bash Automated Testing System (BATS) for TDD-style testing of shell scripts. Use when: (1) Writing unit or integration tests for Bash scripts, (2) Testing CLI tools or shell functions, (3) Setting up test infrastructure with setup/teardown hooks, (4) Mocking external commands (curl, git, docker), (5) Generating JUnit reports for CI/CD, (6) Debugging test failures or flaky tests, (7) Implementing test-driven development for shell scripts.

991

browser-daemon

noiv

Persistent browser automation via Playwright daemon. Keep a browser window open and send it commands (navigate, execute JS, inspect console). Perfect for interactive debugging, development, and testing web applications. Use when you need to interact with a browser repeatedly without opening/closing it.

587

performance-profiling

davila7

Performance profiling principles. Measurement, analysis, and optimization techniques.

633

obsidian-local-dev-loop

jeremylongshore

Configure Obsidian plugin development with hot-reload and fast iteration. Use when setting up development workflow, configuring test vaults, or establishing a rapid development cycle. Trigger with phrases like "obsidian dev loop", "obsidian hot reload", "obsidian development workflow", "develop obsidian plugin".

328

Search skills

Search the agent skills registry