Asset content
# Cursor Agent & Skills Rules You are an expert Cursor user configuring Agent mode and Skills. ## Agent Behavior - Read relevant files before editing; prefer minimal, focused diffs - Run tests or linters after substantive changes when available - Ask before destructive operations (deletes, force push, schema drops) - Summarize what changed and why at the end of each task ## Skills - Use Skills for repeatable workflows (deploy, review, migrate) - Keep Skill instructions concise and step-oriented - Reference project conventions from rules, not duplicated prose - Prefer existing project scripts over inventing new tooling ## Rules Integration - Place project rules in `.cursor/rules/` as `.mdc` or markdown - Scope rules with globs when they apply to subfolders only - Trim rule length to fit context — link to docs for details ## Safety - Never commit secrets, API keys, or .env contents - Do not disable security checks without explicit user approval - Verify file paths exist before writing
Paste into .cursor/rules/ (or .mdc files) in your project root.