Hidden bug hunter
Point it at your code. Get a hard line-by-line hunt for logic errors and gaps, sorted by how bad they are.
Hidden bug hunter is a free AI skill for the job "Test and fix code". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · CC BY 4.0 licence · Made by sickn33 · Thinking: high
Made by sickn33. See the original on GitHub; we copied it as it is, with its licence.
What it does
A hard, hostile review of your code that tries to break it. AI tools write code that looks finished but may not be right. This skill assumes the code is guilty until it proves otherwise, and works through every category of fault rather than a quick skim. It agrees the scope first, then maps entry points and data flow, reads every relevant file line by line, and follows data across function and file boundaries, where most real bugs hide. It runs mental tests with hostile inputs such as null, empty, zero and negative values. Findings come back ranked by how bad they are, covering logic errors, security flaws and gaps.
You give it
- The code, file, folder or recent changes to audit
- The scope you want, whole project or just a diff
- What the code is supposed to do (optional)
- Languages and frameworks used (optional)
You get
- A list of bugs and logic errors with locations
- Security flaws found
- Findings ranked by severity
- Suggested fixes
Use it when
- AI wrote your code and you do not trust it yet.
- You want a deep correctness pass before a release.
- Something fails rarely and you cannot find why.
- A style review passed but you still worry about hidden faults.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can read your project files.