luan/debugging
skills/debugging/SKILL.md
Systematic root cause investigation before proposing fixes. Triggers: bugs, test failures, unexpected behavior, 'why is this failing', 'not working', 'broken'.
$ install --global
skillsauthnpx skillsauth add luan/dot-claude debuggingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 23, 2026, 12:22 PM24.7s1 file scanned
SKILL.md
- name:
- debugging
- description:
- Systematic root cause investigation before proposing fixes. Triggers: bugs, test failures, unexpected behavior, 'why is this failing', 'not working', 'broken'.
Systematic Debugging
Fixing without understanding creates new bugs. Investigate first, fix second.
Phase 1: Investigate
- Read errors — stack traces, line numbers, exact messages
- Reproduce — exact steps. Intermittent? Log at component boundaries.
- Check recent changes —
git diff, new deps - Trace data flow from symptom to source
Phase 2: Compare
- Find working examples in codebase
- Read reference implementation fully
- Diff all differences — deps, config, assumptions
Phase 3: Hypothesize + Test
- Form hypothesis: "X causes this because Y"
- Oracle test (when useful): Compare against known-good baseline — available worktree (
git worktree list, detached HEAD = available), reference impl, or reduced test case. Only create new worktrees for non-obvious multi-component bugs. Return to detached HEAD when done. - 3+ plausible hypotheses → parallelize. Spawn one subagent per hypothesis (each traces one, reports evidence for/against). Sequential testing wastes cycles when each test is slow.
- Smallest possible change to test. One variable at a time.
- Confirmed → Phase 4. Refuted → new hypothesis (3rd+ → parallelize per step 3)
Dead end: 3 hypotheses all fail → re-enter Phase 1 with broader scope. Still stuck → escalate as architectural.
Phase 4: Fix
- Write failing test that reproduces the bug
- Single fix — one change
- Verify — test passes, no regressions
- Fix fails? < 3 attempts → Phase 1. >= 3 → architectural issue
3+ Fixes = Architectural Problem
Repeated patches without root cause understanding signal a design problem. Tactical fixes compound debt and mask the real issue.
STOP. Discuss with human before more fixes.
Red Flags → Back to Phase 1
- Proposing fixes before tracing data flow
- "It's probably X" without evidence
- Multiple changes at once (shotgun debugging)
- "Quick fix for now" / "Just try changing X"
- Skipping or deleting tests
Related Skills
luan/sym
tools
VerifiedTrustedCommunity
Tree-sitter indexed code navigator (ct sym CLI). Use INSTEAD OF Read/Grep/Glob/Bash when exploring existing code, understanding how something works, locating a symbol, tracing the call graph up (impact) or down (trace), finding implementations of an interface, scoping a diff to one symbol, or preparing to edit code you have not read yet. Triggers: 'how does X work', 'explain this class/file/symbol', 'walk me through X', 'what does X do', 'where is X defined', 'who calls X', 'what does X call', 'find implementations of', 'what breaks if I change X', 'outline this file', 'map imports', 'show me this symbol', exploring unfamiliar repo, tracing call graph, scoping diff to a symbol, preparing to edit code I haven't read, about to Read a file over ~500 lines to understand it. Do NOT use for: writing new code from scratch, editing prose or config, running tests, or when a stack trace already names the file and line.
4SKILL.mdUpdated Apr 22, 2026
luan/vibe
development
VerifiedTrustedCommunity
Fully autonomous development workflow from prompt to commit. Chains spec → develop → review → commit. Triggers: /vibe, 'vibe this', 'autonomous workflow', 'just do it all', 'build this end-to-end', 'full pipeline', 'handle everything'.
4SKILL.mdUpdated Apr 21, 2026
luan/vault-sweep
development
VerifiedTrustedCommunity
Comprehensive vault maintenance — cross-references blueprints against codebase state to produce a maintenance plan: archive consumed artifacts, audit docs for staleness, propose new docs for undocumented stable systems. Triggers: 'vault sweep', 'sweep the vault', 'clean up vault', 'vault maintenance', 'what can we archive', 'audit blueprints', 'vault hygiene', 'blueprint cleanup'. Use whenever the user wants a holistic view of vault health rather than archiving a single artifact (that's /archive). Also use when the user asks what's stale, what needs docs, or whether artifacts can be cleaned up.
4SKILL.mdUpdated Apr 21, 2026
luan/test-plan
development
VerifiedTrustedCommunity
Analyze current diff, classify changes by risk, and produce structured manual test plan. Triggers: 'test plan', 'what should I test', 'manual testing', 'verification steps', 'QA checklist'. Exits early for trivial changes. Do NOT use when: writing automated tests — use /develop with TDD. Do NOT use when: reviewing code quality — use /crit instead.
4SKILL.mdUpdated Apr 21, 2026