Create a Claude Skill for Debugging Production Errors & Stack Traces
Generate a SKILL.md that equips Claude with a systematic root-cause analysis workflow to isolate, reproduce, and fix production bugs safely.
System Directive • Copy and Paste Below
You are an expert in Software Reliability Engineering and Claude Code Skill development. Create a production-grade Claude Skill named `production-debugger` defined in a standard `SKILL.md` document. ### SKILL SPECIFICATIONS: - Environment & Stack: [APPLICATION_STACK] - Error Tracking Tool (Sentry, Datadog, CloudWatch, Loggly): [ERROR_TRACKING_TOOL] - Target Repository Root: [REPO_ROOT] ### REQUIRED SKILL.MD WORKFLOW & DIRECTIVES: 1. **YAML Frontmatter**: Define `name: production-debugger` and an actionable `description` that triggers when an error log, stack trace, or incident report is provided. 2. **Phase 1: Diagnostic Triangulation**: - Parse stack trace, extract exact filename, line number, and function frame. - Inspect local git commit history and recent diffs in the affected module. - Identify variable states, null/undefined dereferences, or concurrency race conditions. 3. **Phase 2: Reproduction Harness**: - Formulate a minimal failing unit test or reproduction script that isolates the defect. - Verify that the test fails consistently with the same error signature. 4. **Phase 3: Surgical Remediation**: - Apply the minimal viable fix without refactoring unrelated code. - Add defensive assertions, boundary guards, and proper fallback values. 5. **Phase 4: Regression & Blast Radius Verification**: - Run the reproduction test and confirm it passes. - Execute the full test suite to guarantee zero regressions. - Check upstream and downstream callers for secondary impact. 6. **Phase 5: Post-Mortem & Prevention Summary**: - Explain root cause, trigger conditions, fix summary, and long-term prevention recommendations. Generate the complete `SKILL.md` ready to be added to the Claude skills directory.
Customization & Placeholders
Enter your application stack and monitoring tools. The prompt outputs a battle-tested debugging skill with regression verification workflows.
Example Input Values
Stack: Node.js 22 + TypeScript + PostgreSQL + Redis, Monitoring: Sentry, Target Repo: ./backend
Expected Output Structure
A complete SKILL.md specifying error parsing, reproduction harness creation, defensive patching, and blast radius auditing.
AI Systems Maintenance & Support
Qubenix ensures continuous business reliability with proactive system monitoring, automated error recovery, and robust infrastructure.
More Prompts in Claude Development Toolkit
Generate a Production-Ready CLAUDE.md for an Existing Repository
Inspect an existing codebase and generate a comprehensive, accurate CLAUDE.md with project architecture, build commands, and coding conventions.
Create a Professional design.md Specification from Current Website
Inspect an existing web application or website and extract a complete, structured design.md with design tokens, typography, and component specs.
Create a Reusable Claude Skill for React & Next.js Development
Generate a fully conformant SKILL.md for React and Next.js development that enforces type safety, component modularity, and zero-re-render patterns.