Skip to content

Getting started

Skills are markdown instructions the agent reads when your task matches their description. They keep behavior consistent: when to align, when to test, when to file issues, and what not to do.

Where skills live

  • In Cursor: .cursor/skills/<name>/SKILL.md, skills/<name>/, or paths you configure.
  • On this site: Browse the Skills catalog—each skill has its own page under Skills in the sidebar.

How to invoke a skill

Use an @mention in chat so the agent loads the right skill before writing code or tests.

Minimal pattern

@tdd — Public API: createCheckout(cart). First behavior: happy path succeeds.

The agent should confirm the behavior list, then write one failing test, then minimal code.

Choose a workflow

flowchart LR A[New idea / PRD] --> B{Artifact?} B -->|Local plan| C[prd-to-plan] B -->|GitHub issues| D[to-issues] A --> E[grill-me] F[Unfamiliar repo] --> G[inherited-codebase-onboarding] H[Bug] --> I[triage-issue] J[Implement slice] --> K[aligned-implementation + tdd]

Rules that work well

  1. One anchor per thread — issue number, plan section, or pasted scope block; avoid mixing unrelated features.
  2. Approve before RED — for aligned-implementation and tdd, settle the public API and “done for this thread” before the first failing test.
  3. Vertical slices — each PR or thread should deliver something end-to-end and demoable, not “all models then all controllers.”
  4. Escalate with the right skill — tangled code → improve-codebase-architecture or request-refactor-plan; Neon egress → neon-postgres-egress-optimizer.

Next steps