hoavdc/CodexKit / skills/codexkit-bug-hunt
codexkit-bug-hunt
VerifiedReproduce, isolate, patch, and verify defects with explicit expected-versus-observed behavior.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.9 KB |
| agents/openai.yaml | config | 181 B |
| examples/common-mistakes.md | markdown | 805 B |
| examples/good-output.md | markdown | 828 B |
| verification/checklist.md | markdown | 1.3 KB |
examples/common-mistakes.md
View on GitHub# Common Mistakes — Bug Hunt
> Anti-patterns to watch for when using the Bug Hunt skill.
## 1. Fixing without reproducing
**What goes wrong:** Guessing the cause and shipping a change — may fix the symptom but miss the real problem
**How to fix it:** Always reproduce first. If you can't reproduce, document exactly what you tried.
## 2. Scope creep in bug fix
**What goes wrong:** Refactoring adjacent code, adding features, or cleaning up unrelated tech debt in the bug fix PR
**How to fix it:** Bug fix PRs should be minimal. Create separate issues for cleanup work.
## 3. Verification by absence
**What goes wrong:** 'I can't reproduce it anymore' as proof of fix, without confirming the mechanism
**How to fix it:** Write a failing test first, then make it pass. The test is the proof.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |