vc-debug

Diagnose bugs and system failures through root-cause analysis before applying fixes.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/HyuseCS/project-c --skill vc-debug-hyusecs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vc-debug
Source: https://github.com/HyuseCS/project-c/tree/main/.claude/skills/vc-debug
Command: npx skills add https://github.com/HyuseCS/project-c --skill vc-debug-hyusecs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? It prevents wasted time and new bugs caused by guessing at fixes, enforcing root-cause investigation before any code change for bugs, test failures, CI failures, and performance issues. ## Core Features & Use Cases - Systematic Debugging Framework: Four-phase process (root cause investigation, pattern analysis, hypothesis testing, implementation) with red-flag detection for guess-and-check behavior. - System-Level Investigation: Five-step methodology for server incidents, CI/CD pipeline failures via the gh CLI, log correlation, and database performance diagnostics. - Verification Gate: Iron law requiring fresh command output as evidence before any completion claim, plus frontend visual verification via Chrome MCP or browser automation fallback. - Use Case: When a GitHub Actions build fails but passes locally, use this Skill to collect failed job logs, correlate environment differences, trace the root cause, fix at the source, and verify with fresh test output. ## Quick Start Ask the AI to debug the failing test or error you are seeing and find its root cause before fixing it.

Frequently Asked Questions about vc-debug

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I debug a test failure systematically instead of guessing?

Follow the four-phase framework: investigate the root cause first, analyze patterns against working code, test a single hypothesis with a minimal change, then implement one fix. Never attempt fixes before completing root cause investigation.

How to find which test is polluting shared state or creating files?

Use the included find-polluter.sh bisection script with the polluted path and a test file pattern. It runs tests one by one and stops at the first test that creates the unwanted file or directory.

How do I debug GitHub Actions CI failures that pass locally?

Use the gh CLI to list runs and fetch failed job logs with gh run view --log-failed. Compare environment differences such as versions, OS, and env vars, then correlate timestamps across log sources to identify the trigger.

Can this skill verify frontend UI changes visually?

Yes, it detects frontend file changes and uses Chrome MCP tools to navigate, screenshot, and check console errors. If Chrome MCP is unavailable, it falls back to a browser automation skill, and skips verification entirely for non-frontend work.

When should I not use a quick fix for a bug?

Avoid quick fixes whenever the root cause is unknown, since random changes create new bugs. If three fix attempts have failed, stop and question the underlying architecture instead of trying another patch.