talktofigma-desktop-mcp
Bridge Figma designs with AI assistants using TalkToFigma Desktop via Model Context Protocol
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-22 00:14
Design & creation
20,546 results
design-md-convention
Convention DESIGN.md pour design systems AI-friendly. Use when setting up a new project UI, documenting design tokens, or generating UI consistent with a…
nano-banana-pro-image-gen
Image generation skill, to be used when the user needs to generate images, visual infographics, create images, or edit/modify/adjust existing images. Based on China's APIYI proxy site (https://api.apiyi.com/)的NanoBananaPro模型的图片生成服务，无需访问外网。支持10种宽高比的图片比例（`1:1`、`16:9`、`9:16`、`4:3`、`3:4`、…
image-assistant
Image Assistant - Turn article/module content into 16:9 infographic prompts with a unified style, few words, and high readability; first decide "how many images are needed + what each one covers", then compress copy and metaphors, and finally output image generation prompts ready to copy and iterate on.
product-mockup
Product mockups and showcases: photoreal product/packaging scenes via Gemini 3.1 Flash image editing, and pixel-exact device frames (phone, laptop, browser)…
pptx-design-styles
Use this skill whenever creating PPTX slides, presentations, or decks with any of these 30 modern design styles: Glassmorphism, Neo-Brutalism, Bento Grid, Dark…
svg-illustrations
Expert knowledge for creating hand-drawn style SVG illustrations. Activate when creating custom diagrams, working with illustration components, or needing…
context-engine
Load shared marketing context: brand profile, benchmarks, compliance rules, specs. "load my brand context"
language-config
Configure brand languages: secondary languages, do-not-translate terms, locale formats. "never translate our product name"
narrative-tracker
Track the brand narrative in AI engines against desired positioning, flag misstatements. "is AI misrepresenting our brand"
save-knowledge
Save one piece of brand knowledge to persistent memory with dedup and tags. "store this competitor intel"
amz-customer-question-mining
Mine the Customer Questions tab of a listing for unanswered buyer intent. Generates branded answers to publish, then feeds the recurring question themes back…
event-modeling
Event modeling facilitation for discovering and designing event-sourced systems using a structured 9-step workflow. Use when modeling domain workflows,…
static-web-artifacts-builder
Build self-contained static HTML artifacts opened in a browser: interactive diagrams, dashboards, infographics. Pure HTML5+CSS3+inline SVG, zero toolchain.…
audit-ui
Audits web UI quality across accessibility, interaction, forms, typography, navigation, layout, performance, motion, and microcopy. Use when reviewing or…
image-edit
Compatible with existing `image-edit` name and direct CLI invocation image editing Skill. New base image editing, redrawing, blending, or derivative requests are preferentially routed by image-to-image; when the user explicitly specifies image-edit, this Skill is still used. It reads Meitu credentials, invokes the local `meitu` CLI, and sends the input image and prompt to…
event-driven-architecture
Event-driven architecture patterns with event sourcing, CQRS, and message-driven communication. Use when designing distributed systems, microservices…
minimax-h3-video-prompt
Based on the user's creative goals and image, video, and audio reference materials, first match the correct model capabilities of MiniMax H3, then generate and review video prompts that can be used directly. For text-to-video, first-frame/last-frame image-to-video, multimodal reference generation, reference video motion or camera movement transfer, local video editing, character and product consistency control, advertising, e-commerce, narrative, animation, games, MV, Vlog, visual packaging, UI…
penpot-audit-accessibility
Audit a Penpot design against WCAG 2.1/2.2 AA (optionally AAA) and produce a structured severity report: color contrast, touch/target sizes, text alternatives,…
cicd-pipeline-qe-orchestrator
Orchestrate quality engineering across CI/CD pipeline phases. Use when designing test strategies, planning quality gates, or implementing…
figma-bridge-html-export
Transform Figma designs into LLM-friendly HTML/CSS for AI-assisted development
system-design
Guide architectural design decisions for software systems. Use this skill when designing new systems, evaluating architecture trade-offs, or creating technical…
srt-hyperframes-editorial-video
SRT subtitle-driven HyperFrames + GSAP generation of Editorial-style videos. When the user says "create an Editorial animation based on an SRT subtitle file", or the user says "create an Editorial video" and provides an SRT subtitle file, use this skill"
bmad-ux
Solutioning-phase UX planning skill (optional; activate when the project has a UI). Produces TWO planning documents: DESIGN.md (the visual system — design…