Total 34,574 skills
Showing 12 of 34574 skills
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.
Build with Firebase Authentication - email/password, OAuth providers, phone auth, and custom tokens. Use when: setting up auth flows, implementing sign-in/sign-up, managing user sessions, protecting routes, or troubleshooting auth/invalid-credential, auth/popup-closed, auth/user-not-found, or token refresh errors. Prevents 12 documented errors.
Turn ideas into fully formed designs and specs through natural collaborative dialogue. Use when planning new features, designing architecture, or making significant changes to the codebase.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Use when investigating errors, analyzing stack traces, or finding root causes of unexpected behavior. Invoke for error investigation, troubleshooting, log analysis, root cause analysis.
Semantic search skill using Exa API for embeddings-based search, similar content discovery, and structured research. Use when you need semantic search, find similar pages, or category-specific searches. Triggers: exa, semantic search, find similar, research paper, github search, 语义搜索, 相似内容
Deploy Django on Google App Engine Standard with Cloud SQL PostgreSQL. Covers Unix socket connections, Cloud SQL Auth Proxy for local dev, Gunicorn configuration, and production-ready settings. Use when: deploying Django to App Engine, configuring Cloud SQL PostgreSQL, setting up Unix socket connections, or troubleshooting "No such file or directory", "connection refused", or "FATAL: password authentication failed".
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.
General Correctness rules, Rust patterns, comments, avoiding over-engineering. When writing code always take these into account
Foundational plotting library. Create line plots, scatter, bar, histograms, heatmaps, 3D, subplots, export PNG/PDF/SVG, for scientific visualization and publication figures.
Use when building JavaScript applications with modern ES2023+ features, async patterns, or Node.js development. Invoke for vanilla JavaScript, browser APIs, performance optimization, module systems.