bug-hunter
Investigates and repairs software defects using evidence-based root cause analysis and minimal patches.
Install
mkdir -p .claude/skills/bug-hunter && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15079" && unzip -o skill.zip -d .claude/skills/bug-hunter && rm skill.zipInstalls to .claude/skills/bug-hunter
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.
Investigate and fix software defects with reproducible evidence and minimal-risk patches. Use for crashes, regressions, flaky behavior, and logic faults in frontend or backend. Keywords: debug, root cause, repro, regression.Key capabilities
- →Define the failure contract including expected vs. actual behavior
- →Reproduce the bug minimally or list variability factors
- →Trace code paths and state transitions around the fault boundary
- →Build and eliminate hypotheses using direct evidence
- →Implement the smallest durable fix at the causal layer
- →Add or update regression tests for the failed behavior
How it works
The skill systematically investigates software defects by defining the failure, reproducing the issue, tracing code paths, and building hypotheses. It then implements a minimal fix and ensures regression protection through targeted tests.
Inputs & outputs
When to use bug-hunter
- →Fixing a production crash
- →Investigating flaky tests
- →Patching a regression after deployment
About this skill
Bug Hunter
Mission
Find the true fault, apply the smallest durable fix, and prove it will not regress.
Use This Skill When
- A feature is broken and the failure reason is unclear
- A regression appeared after recent changes
- The same issue is hard to reproduce consistently
- You need a minimal fix with regression protection
Non-Goals
- Do not perform broad refactors while debugging.
- Do not mark root cause as confirmed without evidence.
Required Inputs
- Expected behavior
- Actual behavior
- Reproduction steps and environment details
- Logs, stack traces, or failing test output if available
Procedure
- Define failure contract: expected vs actual, scope, impact.
- Reproduce minimally; if not reproducible, list variability factors and rank likely causes.
- Trace code path and state transitions around the fault boundary.
- Build 1-3 hypotheses and eliminate alternatives using direct evidence.
- Implement smallest durable fix at the causal layer.
- Add or update regression test for the failed behavior.
- Re-run targeted validations and nearby critical flows.
Edge Cases To Check
- Null, empty, malformed, and extreme input values
- Race conditions and async ordering
- Permission and role-dependent paths
- Retry/timeout behavior and partial failures
- Environment-specific config drift
Exit Criteria
- Reproduction is documented or uncertainty is explicitly bounded.
- Root cause is evidenced and fix is applied/proposed.
- Validation evidence is provided for fix and adjacent flow safety.
Output Format
- Reproduction summary
- Confirmed root cause
- Applied or proposed fix
- Validation evidence
- Regression-prevention checklist
When not to use it
- →When performing broad refactors while debugging
- →When marking root cause as confirmed without evidence
- →When the goal is not to find the true fault and apply a minimal fix
Limitations
- →Does not perform broad refactors during debugging.
- →Requires evidence to confirm the root cause.
- →The fix must be the smallest durable change at the causal layer.
How it compares
This skill provides a structured, evidence-based approach to bug fixing, focusing on minimal, durable changes and regression prevention, which is more rigorous than ad-hoc debugging.
Compared to similar skills
bug-hunter side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| bug-hunter (this skill) | 0 | 4mo | No flags | Advanced |
| python-testing-patterns | 77 | 2mo | Review | Intermediate |
| chrome-devtools | 41 | 7mo | Review | Intermediate |
| bats | 9 | 7mo | Review | Intermediate |
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.
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.
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.
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.
performance-profiling
davila7
Performance profiling principles. Measurement, analysis, and optimization techniques.
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".