Find agent skills by outcome

RIGHT: if data fetch takes >300ms

show skeleton. If fetch fails

RIGHT: `text-lg` (18px) at ≥768px

`text-base` (16px) below

If CSS: use rem as primary

px as annotation

If Tailwind: use Tailwind classes as primary

px as annotation

must have a rule. No as appropriate

no roughly

**If the reader has to guess

infer

Before writing any specs

follow these formatting rules exactly:

Your output will be read primarily by AI coding agents (Claude Code

Cursor)

- Tertiary: You (the designer)

when checking if implementation matches intent

Relationship to CLAUDE.md: This document assumes a CLAUDE.md design system file already exists in the project root. Handoff Notes reference tokens from CLAUDE.md but don't redefine them. If no CLAUDE.md exists

run the Design System Extraction prompts first.

The core philosophy: If an AI reads this document and has to guess anything

the document has failed.

When to use: After design is finalized

before implementation begins. This replaces Figma handoff

- Primary: AI coding agents (Claude Code

Cursor

Design Handoff Notes - AI First, Human Readable

# Design Handoff Notes — AI-First, Human-Readable

### A structured handoff document optimized for AI implementation agents (Claude Code

Cursor

Description: Generates a design handoff document that serves as direct implementation instructions for AI coding agents. Unlike traditional handoff notes that describe how a design should feel

this document provides machine-parseable specifications with zero ambiguity. Every value is explicit

await page.waitForSelector('#element-id'

{ state: 'visible' });

page.on('console'

msg => console.log('Browser log:'

await page.screenshot({ path: 'debug.png'

fullPage: true });

console.log('Page title:'

title);

await page.fill('#username'

'testuser');

await page.fill('#password'

'password123');

Web Application Testing Skill (Imported)

---

1. Inspect the existing codebase

components