From qe-framework
Parses error messages, traces execution through stack traces, correlates logs to identify failure points, and applies systematic hypothesis-driven debugging. Use for investigating errors, analyzing stack traces, finding root causes, or troubleshooting crashes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/qe-framework:Qdebugging-wizardThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Expert debugger applying systematic methodology to isolate and resolve issues in any codebase.
Expert debugger applying systematic methodology to isolate and resolve issues in any codebase.
Load detailed guidance based on context:
| Topic | Reference | Load When |
|---|---|---|
| Debugging Tools | references/debugging-tools.md | Setting up debuggers by language |
| Common Patterns | references/common-patterns.md | Recognizing bug patterns |
| Strategies | references/strategies.md | Binary search, git bisect, time travel |
| Quick Fixes | references/quick-fixes.md | Common error solutions |
| Systematic Debugging | references/systematic-debugging.md | Complex bugs, multiple failed fixes, root cause analysis |
Python (pdb)
python -m pdb script.py # launch debugger
# inside pdb:
# b 42 — set breakpoint at line 42
# n — step over
# s — step into
# p some_var — print variable
# bt — print full traceback
JavaScript (Node.js)
node --inspect-brk script.js # pause at first line, attach Chrome DevTools
# In Chrome: open chrome://inspect → click "inspect"
# Sources panel: add breakpoints, watch expressions, step through
Git bisect (regression hunting)
git bisect start
git bisect bad # current commit is broken
git bisect good v1.2.0 # last known good tag/commit
# Git checks out midpoint — test, then:
git bisect good # or: git bisect bad
# Repeat until git identifies the first bad commit
git bisect reset
Go (delve)
dlv debug ./cmd/server # build & attach
# (dlv) break main.go:55
# (dlv) continue
# (dlv) print myVar
When debugging, provide:
// DEBUG: <what fails> — checking <hypothesis>
// Expected: <what should happen>
// Actual: <what we observe>
// Evidence: <log line, stack frame, test case>
console.log, print(), or debugger in commitsWrong: Shotgun debugging (changing multiple things, hoping one works) Correct: Change one variable; verify hypothesis; revert if wrong
Wrong: No reproduction steps documented Correct: Written steps: "1. Create user X; 2. POST /api/...; 3. Observe error"
Wrong: Fixing symptoms (hiding error) instead of root cause Correct: Trace back: does auth fail upstream, or just error handling?
Wrong: Debug code left in production (console.log, debugger) Correct: Use CI to block commits with debug statements
Wrong: Assuming single cause when multiple bugs exist Correct: Fix one, run full test suite, document each separately
npx claudepluginhub inho-team/qe-framework --plugin qe-frameworkCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.