Herramientas

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.

Built by Callstack from The Ultimate Guide to React Native Optimization: diagnoses dropped frames, slow startup, bundle size, memory leaks, unnecessary re-renders and janky animations, across both JS and native iOS/Android.

Lets agents drive WinDbg's CDB/KD to analyze crash dumps, debug user-mode processes remotely and debug kernels, and triage many dumps in a batch. Windows only; requires WinDbg or Debugging Tools for Windows.

Fixes spacing and full-width/half-width punctuation in mixed CJK and English text, understanding 28+ file types including Markdown, YAML and strings and comments in source code. Lint mode outputs a diff or JSON for CI checks on localized copy.

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.

Uses unified rule files in a .rulesync directory as the source to generate rules, MCP, commands, subagents, skills and hooks configs for dozens of AI coding tools including Claude Code, Cursor, Copilot and Codex. Can also import existing configs or convert directly between tools.

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.

Motion design skill built on the ideas of design engineers Emil Kowalski, Jakub Krehel and Jhey Tompkins: builds animated UI components for your project type, or audits existing animations in an HTML report with looping demos. Use in a coding agent on a local frontend project.

Condenses verbose xcodebuild and swift test output into concise build errors, warnings and test results, so agents read less log noise. Can generate JUnit reports and works with CI such as GitHub Actions; runs on macOS and Linux.

Sets up and audits i18n for React, Next.js and Vue apps: replaces hard-coded strings with message keys, checks that English and Chinese keys are complete and consistent, and verifies plurals and date and number formats, with a key audit script. Needs a local codebase and Python.

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.

Crawls an entire site, counts words and keywords per page, and checks technical SEO such as titles, meta descriptions, image alt text, H1s and social tags. Outputs JSON by default or an HTML report for agents to act on. Needs Python; the optional AI content review needs an API key.

Searches 200,000+ icons from 150+ libraries such as Lucide and Material Design, suggests icons by use case, and returns SVG or React, Vue and other component code, or writes them into your icon file. Handy for AI-built pages and UI prototypes. No account or API key; needs Node.js.

Gives agents controlled access to MySQL: list databases and tables, inspect schemas and sample data, and run SQL, with multi-database mode, SSL and SSH tunnels. Configure your own database user, ideally with least privilege.

Free two-way Figma MCP that needs no paid Dev Mode seat: turns designs into code that fits your existing project, or builds pages and components on the canvas from a description, with data staying on your machine. Needs Node.js 20.19+, the Figma desktop app and the companion plugin.

Pulls new papers from Hugging Face Daily Papers and arXiv, scores them by research area into a recommendation page, and writes deep-read Obsidian notes for key ones; can also batch-read Zotero collections. Needs Python 3, Obsidian and poppler; copy the whole skills folder per the README.

MathWorks' official toolkit for reading, building, modifying and testing Simulink models via the MATLAB MCP server, with skills for control design, Simscape, code generation and compliance checks. Needs licensed MATLAB R2023a+ and Simulink; run the official installer in MATLAB first.

LangChain's official skill collection: framework selection, quickstarts, middleware, persistence, human-in-the-loop approval, RAG and eval design across LangChain, LangGraph and Deep Agents, in Python and TypeScript. Also installable as a Claude Code plugin. Still in early development.

Lets agents build Xcode projects and drive the iOS Simulator: 29 scripts cover building and testing, semantic navigation and taps via the accessibility tree, screenshot diffs and device lifecycle, with compact token-saving output. Needs macOS, Xcode and idb.

Plugin marketplace from obra, author of Superpowers: includes the superpowers engineering workflow, episodic-memory for searching past sessions, superpowers-chrome for browser control, elements-of-style writing guidance and more.

Connects agents to live Jupyter notebooks: read, write, insert and execute cells and read multimodal outputs like charts, for interactive data analysis. Bring your own JupyterLab or JupyterHub; open source, maintained by Datalayer.

MathWorks' official toolkit: set up the MCP server via the MATLAB installer so agents can run code, run tests and do static checks; domain skill sets for signal processing, controls, statistics and machine learning install as Claude Code plugins. Needs MATLAB R2021a+.

Microsoft's official local MCP server for creating and editing Power BI semantic model tables, measures and relationships in natural language, running and validating DAX queries, and bulk renaming and translation. Connects to Power BI Desktop, Fabric or PBIP files; in public preview.

The standard machine translation scorer: computes BLEU, chrF and TER with significance tests and downloads public test sets such as WMT, to compare engines or prompts. Needs Python 3.9+ and reference translations; automatic metrics are a rough screen, so final copy still needs human review.