- Home
- Skills
- Mobile Development
- Figma Layout Audit for Flutter
Figma Layout Audit for Flutter
Proves a Flutter screen matches Figma: a Dart helper dumps every painted text from the live widget tree, scripts check them and the images.
$19
Works with the AI Agents you already use
Figma Layout Audit for Flutter
Example session with this skill installed
Check the login screen against the Figma frame 100:200 before I commit.
- Read your context and instructions
- Compiled the figma layout audit
- Generated the UI component
mismatch login :: login/title [Buy now] size 44 != 48; fill #FFFFFF != #FFF4D6 ambiguous login :: login/continue [Continue] 100:215: 36 #FFFFFF #1A3C7A/4; 100:231: 28 #9AA4B2 -/None texts 23: ambiguous 1, mismatch 1, ok 21; dynamic without a check 0 problem assets/images/badge.png 200x90 cropped: PNG 200x90 is smaller than the Figma render bounds 212x104 png 6: ok 5, problem 1 Fixed the title size and color, pointed the Continue button at layer 100:215, re-exported the cropped sprite by its render bounds. Second run: texts 23: ok 23; png 6: ok 6. Both reports exit with code 0.
badge.png
TSX · React component
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Design QA for Flutter that ends in two reports with exit code 0 instead of "looks fine to me". The values come from the render tree, after themes, `DefaultTextStyle`, text scaling and transforms. **How it works** 1. Two read-only scripts dump the text layers and layer sizes of the Figma frames through the official Figma MCP server. 2. `layout_rows.dart` is copied into the app and called from a widget test or a debug build: `dumpRows('login')` writes one row per painted text with the rendered size, color, stroke and position. Paths are built from your `ValueKey`s. 3. `audit_labels.py` matches every text to a Figma layer and compares size (3% tolerance), fill, outline color and outline width. `audit_pngs.py` checks changed PNG files for cropped art, opaque edges and sizes that no Figma layer has, including `@2x`, `2.0x/` and Android density variants. 4. Every row that is not `ok` is fixed or gets a recorded decision (who, when, why) in `map.json`. Both reports must exit with code 0. 5. `compare_element.py` compares composite elements (button frame, plate, text) with the Figma frame pixel by pixel and builds an app / Figma / difference panel. **What you get**: SKILL.md with the 9-step order and the traps, reference docs for formats and statuses, the Dart helper with a widget test template, Python scripts with no dependencies besides Pillow. Texts filled by code are flagged until they are checked with 3 or more value lengths.
Needs the official Figma MCP server with view access to the file. PNG only: JPG, WebP, vector files and 9-patch are not checked. Gradient fills are compared by size only. Text drawn on a canvas (`CustomPaint`) and editable field content are not collected. Widget tests use the square test font, so text positions are approximate unless real fonts are loaded. No localisation keys: texts with digits must be marked as checked or static.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 4 days ago
Requires
Permissions
File Scopes
The scripts make no network requests. Figma is read through your own Figma MCP connection.