Agent skill

error-detective

Systematic debugging and error resolution using the TRACE framework (Trace, Read, Analyze, Check, Execute). Use when debugging errors, analyzing stack traces, investigating failures, root cause analysis, or troubleshooting production issues.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill error-detective-autumnsgrove-claudeskills-2 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 17 KB
Bundled scripts: none
Path: skills/analysis/error-detective-autumnsgrove-claudeskills-2/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Error Detective - Systematic Debugging and Error Resolution ## Overview Error Detective is a comprehensive debugging skill that applies systematic methodologies to identify, analyze, and resolve errors efficiently. Using the TRACE framework and structured analysis techniques, this skill guides you through debugging from initial error discovery to verified resolution. ## Core Capabilities ### Stack Trace Analysis - Parse and interpret stack traces across multiple languages - Identify root cause vs. symptom errors - Extract relevant file paths and line numbers - Understand call chains and error propagation ### Error Pattern Recognition - Categorize errors by type (syntax, runtime, logic, integration) - Identify common error patterns and anti-patterns - Recognize framework-specific errors - Map errors to likely root causes ### Root Cause Analysis - Distinguish between symptoms and underlying issues - Follow error chains to original source - Identify environmental vs. code issues - Detect configuration and dependency problems ### Debugging Workflow Management - Structured investigation process - Hypothesis generation and testing - Iterative refinement of understanding - Documentation

What's inside
Steps it walks through
  1. Overview
  2. Core Capabilities
  3. Stack Trace Analysis
  4. Error Pattern Recognition
  5. Root Cause Analysis
  6. Debugging Workflow Management
  7. The TRACE Framework
  8. T - Trace the Error
  9. R - Read the Error Message
  10. A - Analyze the Context
  11. C - Check for Root Cause
  12. E - Execute the Fix
  13. Debugging Workflow
  14. Initial Assessment (5 minutes)
Ships with 1 file
  • metadata.json
Commands it runs
Parse stack trace from file
python scripts/debug_helper.py parse-trace error.log
Extract error patterns
python scripts/debug_helper.py analyze-log application.log
Start debug session (creates log)
python scripts/debug_helper.py session start "Login error investigation"
Add notes to session
python scripts/debug_helper.py session note "Tested with different users - same error"
Close session with solution
python scripts/debug_helper.py session close "Fixed: Added null check for user.profile"
More from claude-skill-registry
All skills →
About this skill
What does the error-detective skill do?

Systematic debugging and error resolution using the TRACE framework (Trace, Read, Analyze, Check, Execute). Use when debugging errors, analyzing stack traces, investigating failures, root cause analysis, or troubleshooting production issues.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill error-detective-autumnsgrove-claudeskills-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going