genius-debugger
A specialized debugger that analyzes stack traces, identifies root causes, and implements fixes for broken code.
Install
mkdir -p .claude/skills/genius-debugger && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17408" && unzip -o skill.zip -d .claude/skills/genius-debugger && rm skill.zipInstalls to .claude/skills/genius-debugger
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.
Error diagnosis and fixing skill. Analyzes errors, traces root causes, and implements fixes. Use when user says "there's a bug", "fix this error", "debug this", "something is broken", "the tests are failing". Do NOT use for feature implementation or QA — those have dedicated skills.Key capabilities
- →Gather evidence from error messages, stack traces, and recent changes
- →Reproduce reported issues to determine consistency
- →Isolate the failure location through narrowing down
- →Analyze the root cause of the problem
- →Implement fixes following the minimal change principle
- →Verify the fix and add regression tests
How it works
The debugger follows a protocol to gather evidence, reproduce the issue, isolate the failure, analyze the root cause, implement a minimal fix, and verify the solution. It logs findings to a memory file.
Inputs & outputs
When to use genius-debugger
- →Fix application errors
- →Debug test failures
- →Identify root causes in production logs
- →Resolve intermittent bugs
About this skill
Genius Debugger v17.0 — Error Terminator
Every bug has a story. I find it and end it.
Memory Integration
On Debug Start
Read @.genius/memory/BRIEFING.md for context. Check errors.json for previously seen similar errors.
On Root Cause Found
Append to .genius/memory/errors.json:
{"id": "e-XXX", "error": "ROOT CAUSE: [error] in [file]:[line]", "solution": "[fix applied]", "timestamp": "ISO-date", "tags": ["debug", "root-cause"]}
On Fix Failed
Append to .genius/memory/errors.json:
{"id": "e-XXX", "error": "FIX FAILED: [approach]", "solution": "rejected — [why it failed]", "timestamp": "ISO-date", "tags": ["debug", "rejected"]}
Debugging Protocol
- GATHER EVIDENCE — Error message, stack trace, recent changes
- REPRODUCE — Can we trigger it? Consistent or intermittent?
- ISOLATE — Narrow down location, binary search if needed
- ANALYZE — Root cause identification, why did this happen?
- FIX — Implement solution, minimal change principle
- VERIFY — Error gone? No new issues? Add regression test
Error Classification
| Type | Common Fixes |
|---|---|
| Build/Compile | Missing imports, type mismatches, syntax errors |
| Runtime | Undefined access, null pointer, async timing |
| Logic | Wrong output, edge cases, race conditions |
| Integration | CORS, auth tokens, schema mismatch |
Fix Implementation
Minimal Change Principle
- Change only what's necessary
- Don't refactor while debugging
- One fix at a time
- Verify after each change
Verification Checklist
- Original error is gone
- No new errors introduced
- Related functionality still works
- Build passes
- Types check
Handoffs
From genius-orchestrator
Receives: Error message, stack trace, file context
From genius-qa-micro
Receives: Specific error from quick check
To genius-dev
Provides: If fix requires significant refactoring
To genius-qa
Provides: If fix needs comprehensive testing
Definition of Done
- Root cause identified and documented
- Fix applied and verified (bug no longer reproduces)
- Error logged in
.genius/memory/errors.json - Regression test added to prevent recurrence
- PROGRESS.md updated
When not to use it
- →Feature implementation
- →QA tasks
Limitations
- →Does not perform feature implementation
How it compares
This skill provides a structured, methodical debugging protocol with memory integration and classification, unlike an unstructured approach to fixing errors.
Compared to similar skills
genius-debugger side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| genius-debugger (this skill) | 0 | 4mo | Review | Intermediate |
| dependency-upgrade | 26 | 4mo | Review | Intermediate |
| windsurf-linting-config | 1 | 2mo | Review | Intermediate |
| posthog-common-errors | 1 | 10d | Caution | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
dependency-upgrade
wshobson
Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.
windsurf-linting-config
jeremylongshore
Configure and enforce code quality with AI-assisted linting. Activate when users mention "configure linting", "eslint setup", "code quality rules", "linting configuration", or "code standards". Handles linting tool configuration. Use when configuring systems or services. Trigger with phrases like "windsurf linting config", "windsurf config", "windsurf".
posthog-common-errors
jeremylongshore
Diagnose and fix PostHog common errors and exceptions. Use when encountering PostHog errors, debugging failed requests, or troubleshooting integration issues. Trigger with phrases like "posthog error", "fix posthog", "posthog not working", "debug posthog".
dependency-upgrade
pinkpixel-dev
Master major dependency version upgrades, compatibility analysis, staged upgrade strategies, and comprehensive testing approaches.
lint-js
y1feng200156
Check JavaScript/TypeScript code quality with ESLint
fix-dependabot-alerts
microsoft
Fix Dependabot security alerts by updating vulnerable npm dependencies. Use when the user mentions "dependabot", "security alerts", "vulnerability", "CVE", or wants to update packages with security issues.