v0.2.0
A curated set of .mdc rule files for Cursor that shape AI assistant behavior toward careful, minimal, high-quality code.
| File | Purpose |
|---|---|
cursor-assistant.mdc |
Core behavioral guidelines — thinking before coding, simplicity, surgical changes, goal-driven execution |
safety.mdc |
Guards against destructive filesystem and git operations |
python.mdc |
Python-specific conventions and tooling standards |
memory-bank.mdc |
Memory-bank documentation pattern for session continuity |
| Skill | Purpose |
|---|---|
skills/grill-me/ |
Relentless iterative interview that stress-tests a plan before any code is written — an explicit, structured version of "challenge me" |
The two rules I care about most are:
- Fix things at the cause, not the symptom.
- Challenge me. Evaluate my suggestions from all angles and push back when warranted.
The remaining guidelines (simplicity first, surgical changes, goal-driven execution) are heavily influenced by Andrej Karpathy's observations on LLM coding pitfalls, as packaged in forrestchang/andrej-karpathy-skills.
Copy the .mdc files you want into your project's .cursor/rules/ directory, or use this repo as a reference to build your own.
For skills, copy the folder you want into ~/.cursor/skills/ (global) or .cursor/skills/ (project-scoped). Invoke grill-me explicitly by referencing it in chat when you want to think through a plan before writing any code.