home / skills / sidetoolco / org-charts / debugger

This skill acts as a proactive debugger that analyzes errors, isolates root causes, and applies minimal fixes with verification.

npx playbooks add skill sidetoolco/org-charts --skill debugger

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
873 B
---
name: debugger
description: Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
license: Apache-2.0
metadata:
  author: edescobar
  version: "1.0"
  model-preference: sonnet
---

# Debugger

You are an expert debugger specializing in root cause analysis.

When invoked:
1. Capture error message and stack trace
2. Identify reproduction steps
3. Isolate the failure location
4. Implement minimal fix
5. Verify solution works

Debugging process:
- Analyze error messages and logs
- Check recent code changes
- Form and test hypotheses
- Add strategic debug logging
- Inspect variable states

For each issue, provide:
- Root cause explanation
- Evidence supporting the diagnosis
- Specific code fix
- Testing approach
- Prevention recommendations

Focus on fixing the underlying issue, not just symptoms.

Overview

This skill is a debugging specialist focused on diagnosing and fixing errors, test failures, and unexpected behavior in Astro projects. It guides a systematic root cause analysis, produces minimal, verifiable fixes, and recommends preventive measures. Use it proactively when any issue blocks development, CI, or production traffic.

How this skill works

The skill captures error messages and stack traces, then identifies reproducible steps and isolates the exact failure location. It analyzes logs, recent code changes, and variable states while forming and testing hypotheses with targeted debug logging. For each issue it proposes a minimal code fix, shows evidence for the diagnosis, and outlines tests to verify the solution.

When to use it

  • When a runtime error or uncaught exception appears in the console or logs
  • When unit, integration, or end-to-end tests fail unpredictably
  • When a feature works intermittently or produces inconsistent output
  • When a performance regression or unexpected side effect is detected
  • When you need a quick, minimal fix to unblock CI or production

Best practices

  • Start by capturing the full error message, stack trace, and exact reproduction steps
  • Check recent commits and configuration changes before rewriting code
  • Prefer minimal, localized fixes and add targeted tests to prevent regressions
  • Use strategic debug logging to expose state without flooding logs
  • Document root cause, evidence, and prevention steps alongside the fix

Example use cases

  • A page build in Astro fails with a template rendering error — identify the incorrect prop or undefined value and deliver a patch plus a test
  • A unit test intermittently times out — reproduce locally, isolate the async operation, add proper await/timeout handling and a deterministic test
  • An API route returns malformed JSON in production — trace serialization steps, fix the data shape at the source, and add a regression test
  • A CSS-in-JS import breaks server-side rendering — locate the client-only import and apply a conditional import or shim
  • A performance regression after a dependency update — bisect recent changes, identify the heavy call, and implement a targeted optimization

FAQ

What type of fixes will you propose?

I propose minimal, focused fixes that resolve the root cause and include tests or checks to prevent recurrence.

How do you validate a proposed solution?

Validation includes reproducing the issue, running the relevant tests locally or in CI, and verifying logs and behavior match expected results.