Skills
Hand-authored skill bodies for AI coding agents — drop into .claude/skills/ (Claude Code), .cursor/rules/ (Cursor), or Codex equivalents. Each skill is a self-contained .md you paste once and forget.
- agent-agnostic 2026-05-09
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 2026-05-09
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 2026-05-09
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 2026-05-09
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.