debug
Debug helps you trace application issues methodically from symptom to root cause using structured log analysis, error parsing, and hypothesis testing. It enforces a disciplined four-phase workflow: investigate the error completely, analyze patterns in working code, form and test a single hypothesis, then implement the fix—preventing the common trap of patching symptoms instead of solving underlying problems.
Debug skill systematically traces application errors to their root cause through structured investigation and hypothesis testing.
AI-generated summary based on this skill's SKILL.md
Install
softspark/ai-toolkit/debug · repository language: Python
git clone https://github.com/softspark/ai-toolkit
cp -r ai-toolkit/app/skills/debug ~/.claude/skills/debugnpx skillfed install softspark/ai-toolkit/debugFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I debug an error in my application?
Debug guides you through a structured four-phase workflow: first, investigate the error completely by collecting logs and stack traces; second, analyze patterns in working code to understand context; third, form and test a single hypothesis before applying any fix; finally, implement the solution. This methodical approach helps you trace from symptom to root cause rather than patching surface symptoms.
How does Debug help trace where my code is failing?
Debug enforces systematic error investigation by parsing logs and stack traces to identify exact failure points. It helps you map the error path through your application, understand the sequence of events leading to the failure, and distinguish between where the symptom appears versus where the actual problem originates—critical for fixing the root cause rather than masking the issue.
What's the best way to reproduce an intermittent bug?
Debug emphasizes forming and testing debugging hypotheses before applying fixes. For intermittent bugs, this means collecting detailed logs across multiple occurrences, identifying common patterns, and designing targeted tests to reproduce the issue deterministically. Once you can reliably trigger the bug, you can confidently validate your fix without guessing.
How can Debug help with service health and connectivity issues?
Debug supports checking service health and diagnosing connectivity or performance problems by helping you systematically collect and analyze logs from all affected services. You can trace request flows across service boundaries, identify where connections fail or degrade, and test hypotheses about network, configuration, or resource constraints before implementing corrections.
What prevents Debug users from just patching symptoms?
Debug's disciplined workflow enforces root-cause thinking by requiring you to complete the investigation and analysis phases before forming a hypothesis. This structure prevents the common trap of applying quick fixes to visible symptoms. By insisting on understanding the underlying problem first, Debug helps you implement lasting solutions that don't create new bugs downstream.
Can Debug help with debugging logs and stack traces?
Yes. Debug specializes in parsing error logs and stack traces to identify failure points. It helps you extract meaningful patterns from raw log data, correlate events across multiple log sources, and follow stack traces back through your application layers to pinpoint where execution went wrong—essential for understanding complex multi-component failures.
SKILL.md
rendered from the published skill — quoted content, verbatim
Debug Helper
$ARGUMENTS
Systematic debugging for application issues.
Project context
- Recent logs: !
docker compose logs --tail 20 2>/dev/null || tail -20 logs/*.log 2>/dev/null || echo "no-logs-found"
Automated Error Parsing
Pipe error output through the error parser for structured diagnosis:
# Pipe from failing command
your_command 2>&1 | python3 "$(dirname "$0")/scripts/error-parser.py"
# Or from a log file
cat /var/log/app/error.log | python3 scripts/error-parser.py
The script outputs JSON with: - language: detected language (python/node/go/php) - error_type: extracted error class (e.g., ModuleNotFoundError) - message: the error message text - category: classification (import, reference, type, connection, timeout, memory, permission, syntax) - stack_frames: parsed file/line/function from the stack trace -
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 2 files
app/skills/debug/SKILL.md
app/skills/debug/scripts/error-parser.py