ツール

Figma's official skill collection: implement designs as code, map components with Code Connect, generate design-system libraries from code, and build screens and FigJam diagrams on the canvas. Needs the Figma MCP server; canvas writes are in beta and currently free.

Figma's official skill that teaches agents to run Plugin API scripts via use_figma, creating and editing nodes, components, variables and auto layout directly on the canvas. Load it before any use_figma call. Needs a Figma account and the remote MCP server.

Figma's official skill: the agent writes Mermaid, then uses the Figma MCP to build flowcharts and sequence, state, Gantt and ER diagrams in FigJam for you to tweak by hand. Unsupported types like pie charts and mind maps are flagged upfront. Needs a Figma account and the remote MCP server.

Figma's official plugin: connects the remote Figma MCP server and bundles skills for design-to-code, Code Connect, and generating designs and libraries, letting agents read design context and write to the canvas. Needs a Figma account; Starter plans and View/Collab seats get 6 calls a month.

Figma's official skill for building FigJam boards through the Figma MCP: sticky notes, sections, connectors, shapes and tables for brainstorms, retros and meetings. Needs a Figma account, the remote MCP server and the figma-use skill; canvas writes are free in beta; usage pricing is planned.

Builds editable Figma designs on the canvas from screens, modals or sidebars in your code, or from a text description, reusing components and variables from the file's published design system first. Maintained by Figma; needs the remote Figma MCP server and the figma-use skill.

Unofficial Intercom CLI built with Printing Press, covering the full REST API: sync conversations and contacts for offline search, bulk-tag conversations about one incident, see customer overviews and SLA reports, and pull or push help articles. US, EU and AU regions; needs an access token.

Self-hostable long-term memory for agents, offering MCP, a REST API and a web dashboard: semantic search, knowledge graph and automatic memory consolidation. Embeddings are computed locally; choose SQLite, Cloudflare or Milvus as the backend.

Breaks reference UIs you like (screenshots, images or URLs) into a structured design DNA JSON covering design tokens, overall style and visual effects, then builds new pages from your content in that style. Installing needs Node.js; no API key required.

Command-line tool for inspecting, compressing and optimizing glTF/GLB 3D models, with Draco and Meshopt mesh compression, texture resizing and WebP/KTX2 compression; a single optimize command handles it all.

SDK and CLI for reading, editing and optimizing glTF 2.0 3D models: one optimize command does it all, or run Draco and Meshopt geometry compression, texture resizing and WebP or KTX2 compression separately. Suits game and web 3D assets.

Fetches US, Hong Kong and China A-share stock data with zero runtime dependencies: real-time quotes, daily, weekly and monthly candles and search as JSON, falling back across Tencent, Sina and Eastmoney sources. Also runs as an MCP server. Unofficial public APIs, no stability guarantee.

A three-stage workflow for math modeling contests like MCM/ICM and CUMCM: analysis, solving and plotting in Python or MATLAB, and a Word (optionally LaTeX) paper, with stage-check subagents and OpenAlex plus AnySearch literature search. Generated papers are for reference only.

Higgsfield's official skills: generate images, video and voiceover from a single prompt for product shots, e-commerce hero images, YouTube thumbnails, brand guidelines and narrated explainers. Requires the Higgsfield CLI and a signed-in account; generations use account credits.

Generates product shots, marketing posters and illustrations, removes or swaps backgrounds, upscales and makes videos, with 1,400+ prompt templates and parallel variations. Cloud use needs a MeiGen account and paid credits; the npm version can use OpenAI-compatible APIs or local ComfyUI.

Recommends daily papers from arXiv and Semantic Scholar by research interest, reads them and writes illustrated Obsidian notes and a paper graph; can also search venues like CVPR and NeurIPS. Needs Python 3, Obsidian, a vault path and an interests config; the web app needs an Anthropic API key.

From Harvard Medical School's Zitnik Lab: one MCP connecting 1,000+ scientific tools and databases for drugs and targets, genes and proteins, clinical trials, FDA data and PubMed, for biomedical and drug research. Runs with uv; some sources need API keys; medical conclusions need expert review.

MathWorks' official server that lets agents start your local MATLAB, write and run scripts and unit tests, and check code style and potential errors, for computing, simulation and data analysis. Needs a licensed MATLAB R2021a+ and the downloaded server binary.

Econometrician Pedro Sant'Anna's academic Claude Code setup (fork the repo to use it): Beamer/Quarto lecture slides, paper review and mock refereeing, R/Python analysis and replication packages, with specialist subagents and quality gates. Needs Git and Python; slides need XeLaTeX and Quarto.

Figma's official CLI that links Figma design-system components to real components in your code, so Dev Mode and the Figma MCP show production snippets instead of generated examples. Needs Node.js 18+, a Figma Organization or Enterprise plan, a full Design or Dev Mode seat and an access token.

User research skill: drafts research plans, screeners and interview guides, and turns transcripts into reports with coding tables, personas and priorities, no account needed. AI-moderated interviews, surveys and recruiting real or synthetic participants need a Cookiy AI account, billed per use.

Uses the Qdrant vector database as a semantic memory layer for agents: store information and retrieve it by meaning, connecting to a remote instance or a local path, with FastEmbed generating embeddings by default. Maintained by Qdrant.

From product photos and a brief, plans a full e-commerce visual set (main images, Amazon/Shopify detail pages, social promos, livestream scenes) with briefs and image prompts, using 25 scene templates and a consistent style. Renders with an OpenAI-compatible image API key; needs Python 3.10+.

Connects LLMs to ROS and ROS 2 robots: publish and subscribe to topics, call services and actions, set parameters, and read sensor and robot state, without changing robot code. The robot side needs rosbridge running.