Failure drill planner
Name a system. Get safe experiments that break parts on purpose, with limits, checks and lessons.
Failure drill planner 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 · MIT licence · Made by Alireza Rezvani · Level: expert · Thinking: high
Made by Alireza Rezvani. See the original on GitHub; we copied it as it is, with its licence.
What it does
A safe plan for breaking part of your system on purpose, so you learn how it fails before your customers do. Every plan has a stop rule, so a test cannot turn into an outage. You name the service and what you expect to stay true, such as response time under 500 ms. The skill writes a hypothesis, picks a fault like slow network or a dead node, and sizes the blast radius from traffic share, users and duration. It sets abort limits and a rollback step before anything runs. It helps you choose a tool, such as Chaos Mesh, Litmus or AWS FIS, and a script writes up the result afterwards. The scripts use Python only.
You give it
- The service or system to test
- What should keep working (the steady state)
- The fault you want to try
- Traffic and user numbers
- Time window
You get
- A structured experiment plan
- A blast radius estimate
- Abort criteria and a rollback step
- A tool suggestion
- A short results write-up
Use it when
- You want to test what happens when a payment service gets slow.
- You are planning a game day with your engineering team.
- You need to know how many users a test could affect.
- You want to review a colleague's experiment plan for safety.
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 run code and read your project files.