AI Agent Rules Generator
Generate CLAUDE.md, AGENTS.md, .cursor/rules/*.mdc, and .github/copilot-instructions.md from one form. Multi-agent. Strictness swaps.
Related prompts
- gemini
GEMINI.md Template — Project Context for Gemini CLI
A copy-pasteable GEMINI.md template for Google Gemini CLI. Covers the GEMINI.md vs AGENTS.md precedence rule and the hierarchical context loading order.
- codex
Codex AGENTS.md Template — Project Context for OpenAI Codex
A copy-pasteable AGENTS.md template for OpenAI Codex. No frontmatter (Codex requirement). Tech stack, commands, conventions, output format — for Vite projects.
- cursor
Cursor Rules Template — .cursor/rules/*.mdc with Valid YAML Frontmatter
A copy-pasteable .cursor/rules/*.mdc template for Cursor IDE. Includes the required description / globs / alwaysApply frontmatter — not deprecated .cursorrules.
- claude-code
Vite CLAUDE.md Template — Project Rules for Claude Code
A copy-pasteable CLAUDE.md template for Vite + React + TypeScript projects, optimized for Claude Code. Stack-aware. Verified against current Anthropic guidance.
Related skills
- agent-agnostic
Andrej Karpathy Coding — Spec-Then-Run-Don't-Imagine
Karpathy's coding mental model for working with LLMs: small steps, evals over hopes, prefer dumb code, run-don't-imagine when in doubt.
- agent-agnostic
GSD Core — Discuss-Plan-Execute-Verify Loop
GSD methodology distilled: one phase at a time, locked decisions never relitigated, REQ-IDs map every requirement to a phase row.
- agent-agnostic
Matt Pocock Core Skill - Grill, Context, TDD, Refactor
Matt Pocock skill distillation: grill first, name the domain, run red-green-refactor loops, zoom out, and pay down design debt.
- claude-code
Superpower Core — Read-Plan-Run-Report Discipline
Anthropic's Superpower discipline distilled: read before edit, plan before write, run before claim done, report failures instead of papering over them.