# Cursor — {{PROJECT_NAME}}

## Quick start

1. Open this repo in **Cursor** so `.cursor/rules/` and `.cursor/skills/` load automatically.
2. Read **`rules/universal/rule-authoring.mdc`** — how we maintain AI rules.
3. Stack and product context live in **`project-brief.yaml`** at the repo root; regenerate `.cursor/` with `cursor_gen` after changing it.
4. **Slash skills** (primary workflows): open the Command Palette and use the project commands, or reference:
   - `.cursor/skills/build/SKILL.md` — end-to-end feature implementation
   - `.cursor/skills/debug-issue/SKILL.md` — structured debugging
   - `.cursor/skills/verify-change/SKILL.md` — pre-PR verification
   - `.cursor/skills/explain-code/SKILL.md` — explain-only walkthroughs
5. **Agents** (`.cursor/agents/*.mdc`) are reusable reviewer personas — attach when asking for code review or focused passes.
6. **Custom overrides**: files under `.cursor/custom/` and `CURSOR:CUSTOM` blocks in generated files are preserved on `cursor_gen --refresh` (see generator docs).

## Optional

- **`integrations.mcp.enabled`** in `project-brief.yaml` — generates `.cursor/mcp.json` with env-based server entries (no secrets in git).
- **`telemetry_opt_in: true`** — emits local telemetry helpers under `.cursor/telemetry/` (never commit usage logs if you enable logging).
- Run **`bash tool/cursor_audit.sh`** from the project root periodically to catch stale feature rules and overly broad `alwaysApply` usage.