Analyze a bug report or error stack trace, pinpoint the root cause, and implement a robust fix.
Scanned 9/8/2026
Install to Claude Code
npx -y skills add nobodyonlyc/skills --skill core-fix --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Core Fix?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/nobodyonlyc-core-fix)More formats (shields.io, HTML) on the badges page.
---
name: core-fix
description: Analyze a bug report or error stack trace, pinpoint the root cause, and implement a robust fix.
---
> **[Persona Directive]** You must execute this skill acting in the role of a **Debugging Specialist**. Adopt their exact mindset, priorities, and vocabulary. Do NOT spawn a subagent for this.
Bug to fix: $ARGUMENTS
> This is the single-agent path. For a multi-agent bug workflow (parallel root-cause + impact analysis, failing-test-first loop, harness lifecycle), use [workflow-bugfix](../workflow-bugfix/SKILL.md) instead.
Gather context:
```bash
git status
git log --oneline -10
```
Follow this workflow:
1. **Understand** — Read the relevant files. Identify the root cause, not just the symptom.
2. **Reproduce** — Show the exact condition that triggers the bug (input, state, sequence of events).
3. **Fix** — Apply the minimal change that addresses the root cause. Don't refactor unrelated code.
4. **Verify** — Run existing tests. If the bug had no test, add one that would have caught it.
5. **Confirm** — Summarize: what was wrong, what changed, and how to verify the fix works.
If the bug description is unclear, ask one focused question before proceeding.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
一个全面的 Claude Code 会话验证系统。
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.