ardot-design-core

Orchestrates canvas design workflows on the Ardot MCP server with schema rules and validation tiers.

68|25|Updated Jul 24, 2026
One-click install
npx skills add https://github.com/rojim666/SztuCode --skill ardot-design-core-rojim666
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ardot-design-core
Source: https://github.com/rojim666/SztuCode/tree/main/py-runtime/src/sztu_code/core/prompts/workbuddy/skills/ardot-design-core
Command: npx skills add https://github.com/rojim666/SztuCode --skill ardot-design-core-rojim666

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Designing on the Ardot canvas requires strict adherence to a node schema, tool-call sequencing, and layout rules that are easy to get wrong. This Skill provides the shared foundational workflow, hard rules, and validation patterns so every Ardot design task (UI screens, slides, posters, design-to-code) follows a consistent, correct process. ## Core Features & Use Cases - Standard 8-Step Workflow: Enforces file-open gating, parallel state reads, style-guide search/build, batched edits (max 25 ops), and tiered validation for every canvas task. - Design Rules & Schema Reference: Ships the single source of truth for coordinates, flexbox layout, text, colors, tables, images, effects, SVG icons, and troubleshooting. - Composite Visual Effects: Provides ready-made recipes for glassmorphism, neon glow, metallic, glow border, iridescent, and neumorphism effects. - Use Case: When asked to create a landing page on the Ardot canvas, the agent follows Step 0-8: open/create the file, build a style guide, locate available space, execute batch_edit operations section by section, and validate with tiered screenshot/layout checks. ## Quick Start Ask the agent to create a new Ardot design, for example: create a landing page for a coffee brand on the Ardot canvas, and it will pair this core workflow with the matching domain skill.

Frequently Asked Questions about ardot-design-core

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a design on the Ardot canvas?▼

Follow the standard workflow: ensure a design file is open with create_design or open_design, read existing state, build or search a style guide, locate available space, then execute batch_edit operations in sections and validate with tiered screenshot and layout checks.

What is batch_edit and how many operations can it run?▼

batch_edit executes insert, copy, update, move, delete, and image-generation operations in one call on the Ardot canvas. Keep each call to a maximum of 25 operations and split larger designs into logical sections; on failure the whole batch rolls back.

Does this skill work alone for UI or poster design?▼

No. This is the shared base skill and must be paired with a domain skill such as ardot-ui-design, ardot-slides, ardot-poster, livestream-poster, or ardot-design-to-code, which supplies the deliverable-specific guidelines.

Can this skill export PowerPoint .pptx files?▼

No. The skill explicitly excludes PowerPoint .pptx output; that is handled by the separate pptx skill. This skill only manipulates the Ardot design canvas through ardot MCP tools.

Why is my text invisible or overflowing on the canvas?▼

Text nodes have no color by default, so you must set the fill property. Overflow usually comes from width set to hug_contents; use fill_container or a fixed width so the text wraps within its bounding box.

How are images added to Ardot design nodes?▼

Images are applied as fills via the G() operation, either as AI-generated images from a descriptive prompt or as gray placeholder boxes with a short label. Each node may receive exactly one G() call; never retry generation on the same node.