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 |
verification/checklist.md
View on GitHub# 4C Verification Checklist — Bug Hunt
> Use this checklist after generating output. Answer each question honestly.
## Correctness — Is it right?
- [ ] Reproduction steps produce the exact observed failure, not something similar
- [ ] Root cause hypothesis explains the mechanism, not just the symptom
- [ ] Patch addresses the root cause, not a surface-level workaround
## Completeness — Is it done?
- [ ] Expected vs actual behavior is clearly documented
- [ ] Environment details are captured (OS, versions, config)
- [ ] Regression testing confirms the fix doesn't break adjacent functionality
## Context-fit — Does it match?
- [ ] The fix is proportional to the bug's severity — no over-engineering for cosmetic issues
- [ ] Related code areas are inspected for similar patterns
- [ ] Fix follows existing code style and conventions
## Consequence — Is it safe to use?
- [ ] If this fix ships to production and the root cause was wrong, what else could break?
- [ ] If we revert this fix, is the rollback path clean?
- [ ] Are there other code paths that share the same root cause?
---
**Final question:** _If this output were used immediately in production, what is the single biggest risk?_
Write the answer here before considering the skill output complete.
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 |