toolkit/packages/skills/design-md/SKILL.md
Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files
npx skillsauth add stevengonsalvez/agents-in-a-box design-mdInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
4 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are an expert Design Systems Lead. Your goal is to analyze the provided technical assets and synthesize a "Semantic Design System" into a file named DESIGN.md.
This skill helps you create DESIGN.md files that serve as the "source of truth" for prompting Stitch to generate new screens that align perfectly with existing design language. Stitch interprets design through "Visual Descriptions" supported by specific color values.
The DESIGN.md file will serve as the "source of truth" for prompting Stitch to generate new screens that align perfectly with the existing design language. Stitch interprets design through "Visual Descriptions" supported by specific color values.
To analyze a Stitch project, you must retrieve screen metadata and design assets using the Stitch MCP Server tools:
Namespace discovery: Run list_tools to find the Stitch MCP prefix. Use this prefix (e.g., mcp_stitch:) for all subsequent calls.
Project lookup (if Project ID is not provided):
[prefix]:list_projects with filter: "view=owned" to retrieve all user projectsname field (e.g., projects/13534454087919359824)Screen lookup (if Screen ID is not provided):
[prefix]:list_screens with the projectId (just the numeric ID, not the full path)name fieldMetadata fetch:
[prefix]:get_screen with both projectId and screenId (both as numeric IDs only)screenshot.downloadUrl - Visual reference of the designhtmlCode.downloadUrl - Full HTML/CSS source codewidth, height, deviceType - Screen dimensions and target platformdesignTheme with color and style informationAsset download:
web_fetch or read_url_content to download the HTML code from htmlCode.downloadUrlscreenshot.downloadUrl for visual referenceProject metadata extraction:
[prefix]:get_project with the project name (full path: projects/{id}) to get:
designTheme object with color mode, fonts, roundness, custom colorsname field in the JSON)Evaluate the screenshot and HTML structure to capture the overall "vibe." Use evocative adjectives to describe the mood (e.g., "Airy," "Dense," "Minimalist," "Utilitarian").
Identify the key colors in the system. For each color, provide:
Convert technical border-radius and layout values into physical descriptions:
rounded-full as "Pill-shaped"rounded-lg as "Subtly rounded corners"rounded-none as "Sharp, squared-off edges"Explain how the UI handles layers. Describe the presence and quality of shadows (e.g., "Flat," "Whisper-soft diffused shadows," or "Heavy, high-contrast drop shadows").
# Design System: [Project Title]
**Project ID:** [Insert Project ID Here]
## 1. Visual Theme & Atmosphere
(Description of the mood, density, and aesthetic philosophy.)
## 2. Color Palette & Roles
(List colors by Descriptive Name + Hex Code + Functional Role.)
## 3. Typography Rules
(Description of font family, weight usage for headers vs. body, and letter-spacing character.)
## 4. Component Stylings
* **Buttons:** (Shape description, color assignment, behavior).
* **Cards/Containers:** (Corner roundness description, background color, shadow depth).
* **Inputs/Forms:** (Stroke style, background).
## 5. Layout Principles
(Description of whitespace strategy, margins, and grid alignment.)
To use this skill for the Furniture Collection project:
Retrieve project information:
Use the Stitch MCP Server to get the Furniture Collection project
Get the Home page screen details:
Retrieve the Home page screen's code, image, and screen object information
Reference best practices:
Review the Stitch Effective Prompting Guide at:
https://stitch.withgoogle.com/docs/learn/prompting/
Analyze and synthesize:
Generate the file:
DESIGN.md in the project directorydocumentation
Report reflect drain spend over a time window — tokens split by cached (cache_read), uncached writes (cache_creation), and io (input+output), with a $ estimate, grouped by day / outcome / model / transcript. Reads the drainer's cost log and surfaces outlier runs and cache-reuse health (the 41.5M-token failure mode = low cache reuse + high cache writes). Use to answer "what is reflection costing me" for the last day / week.
development
Show fleet status — every claude session running on the host, merged across ainb + claude-peers broker + background jobs. Use when you need to enumerate sessions before composing an action, see which sessions have a peer registered (broker-routable) vs tmux-only, check the `summary` of each session, or pipe the list into jq for filtering. Default output: text table. Pass --format json for LLM consumption.
testing
Ordered multi-step prompts to fleet targets, ack-gated between steps via JSONL assistant-turn-end detection. Use for cycles like disconnect→reconnect→verify, or any flow where step N+1 requires step N to have completed first. The skill BLOCKS until each target's transcript shows the next assistant turn finishing OR per-step timeout fires (default 300s).
development
Center control panel — enumerate every claude session that is blocked waiting on something: a user answer (AskUserQuestion fired), an API error retry, an idle assistant turn-end with no follow-up, or an explicit WAITING: marker. Returns rich JSON with signal kind + context per session. Use this when you've stepped away from the fleet and want one place to see everything that wants your attention and answer it.