292 boosters for "data" — open source, verified from GitHub, ready to install
ALWAYS use when: creating/editing marimo notebooks, working with any .py file containing @app.cell decorators, building reactive Python notebooks, doing exploratory data analysis in notebook form, converting Jupyter (.ipynb) to marimo, or when user mentions "marimo", "reactive notebook", or asks for an interactive Python notebook. Covers marimo CLI (edit, run, convert, export), UI components (mo.ui.*), layout functions, SQL integration, caching, state management, and wigglystuff widgets. If a task involves notebooks and Python, invoke this skill first.
A pattern detection skill that determines whether specific entities, conditions, or signals exist in data sources, returning binary presence/absence results with confidence scores. Useful for developers building search, validation, and anomaly detection features into Claude-powered applications.
Research people and companies, add to CRM database with smart linking
Analyze, review, and provide recommendations for distributed system designs. Use when: (1) Reviewing existing system architectures for gaps or improvements, (2) Analyzing system designs for scalability, reliability, or performance issues, (3) Providing recommendations on load balancing, caching, databases, sharding, replication, messaging, rate limiting, authentication, resilience, or monitoring, (4) Assessing trade-offs in system design decisions, (5) Creating system design review documents with gaps and recommendations. Triggers: "review my system design", "analyze this architecture", "what are the gaps", "system design recommendations", "scalability review", "reliability analysis".
Ray is an expert booster for Apache Ray distributed computing that helps developers convert Python code to Ray workloads, debug applications, and optimize performance across Ray's ecosystem (Core, Data, Train, Serve, Tune). Ideal for ML engineers and Python developers scaling computations from single machines to clusters.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
A practical guide to Supervised Fine-Tuning using SFTTrainer and Unsloth optimizations, enabling developers to efficiently adapt pre-trained LLMs for instruction-following with 2x faster training. Ideal for ML engineers building custom instruction-tuned models and reasoning systems.
Use this skill for analysis-only work and fresh workflow bootstrap. In this repository, use the repo-root wrapper: Run outside sandboxed environments by default. Do not first attempt the Playwright crawl inside the sandbox and then retry after it is intercepted.
"name": "webflow-mcp-server", "bin": "dist/index.js", "start": "concurrently \"npm run dev:local\" \"npm run inspector:local\"",
"name": "@paretools/jvm", "version": "0.16.1", "mcpName": "io.github.Dave-London/pare-jvm",
Nuxt SEO is a meta-module that streamlines SEO configuration, sitemap generation, OG image creation, and structured data management for Nuxt applications. Developers building Nuxt sites need this to ensure proper search engine visibility and social media optimization.
"name": "claude-seo-assistant", "description": "权威性 SEO 助手工具，支持 Next.js 项目的元数据优化、结构化数据、内容审计、客座博客搜索、站外 SEO 和本地 SEO 分析", "author": "Claude Code SEO Team",
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Swift MCP Server provides structured access to Swift build, test, and package manager data for AI agents, enabling seamless integration with Claude, Cursor, and Copilot for iOS/macOS development workflows.
"name": "xiaohongshu-skills", "email": "xiaoluopupu@gmail.com" "description": "Complete Xiaohongshu (Little Red Book) operations skills library - 144 skills covering content creation, account management, community engagement, data analytics, e-commerce conversion, platform rules, tools ecosystem, ma
This skill encodes the complete design specification for professional business presentations — a consultant-grade PowerPoint framework based on McKinsey design principles. It includes: All specifications have been refined through iterative production feedback to ensure visual consistency, profession
An MCP server that enables Claude to maintain persistent long-term and short-term memory across conversations using a local SQLite database. Developers and AI agents benefit from enhanced context retention and conversation continuity.
is discouraged in new packages and tolerated in existing packages. The SDK aims to minimize third-party dependencies. Table-driven tests are preferred for API client methods:
AniList MCP Server enables Claude to access AniList's anime and manga database through the Model Context Protocol, allowing developers and anime enthusiasts to integrate rich AniList data into AI-powered applications.
A Cursor IDE rule set that enforces consistent Rust coding standards, project structure, and architectural patterns for the LLML library. Developers working on LLML in Cursor will benefit from automated guidance on module organization, naming conventions, and API design.
A Cursor IDE rule set that enforces idiomatic Elixir coding standards and best practices, including functional programming patterns, code style conventions, and test structure guidelines. Beneficial for Elixir developers using Cursor who want consistent, high-quality code generation.
Generate professional-grade structured project Wiki to directory. 1. 完整可运行：包含 import、初始化、调用、结果处理 2. 覆盖导出接口：每个主要导出 API 至少 1 个示例
日本政府のオープンデータに MCP サーバー（）経由でアクセスする。 で を使う。 は SSE 非対応のため不可。
Read and follow in the repository root.
