NLP

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Prepares meeting materials by gathering context from Notion, enriching with Claude research, and creating both an internal pre-read and external agenda saved to Notion. Helps you arrive prepared with comprehensive background and structured meeting docs.

Fetch and analyze Sentry issues, events, transactions, and logs. Helps agents debug errors, find root causes, and understand what happened at specific times.

Local speech-to-text with the Whisper CLI (no API key).

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for creating new documents, modifying content, working with tracked changes, or adding comments.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Generate images using the Jimeng API based on text prompts. Use this skill when users request AI-generated images from the Jimeng (即梦AI) service, artwork, illustrations, or visual content creation. Supports text-to-image and image-to-image generation with customizable ratios and resolutions.

在多轮对话和多 Agent 协作场景下，帮助模型管理指令、项目状态和长上下文。通过外部文档与会话笔记实现可控的“记忆”、指令冲突检测和高质量交接。适用于任务跨多次调用、跨 Agent、需要稳定行为规范时使用。

Handle template comparison and optimization workflows including backup detection, smart merging, and update completion reporting. Enhanced with Context7 MCP for up-to-date documentation.

Enterprise Cloudflare Edge Platform with AI-powered edge computing architecture, Context7 integration, and intelligent global orchestration for scalable modern applications

Enterprise systematic code review orchestrator with TRUST 5 principles, multi-language support, Context7 integration, AI-powered quality checks, SOLID principle validation, security vulnerability detection, and maintainability analysis across 25+ programming languages; activates for code reviews, quality standard validation, TRUST 5 enforcement, architectural audits, and automated review automation

Enterprise-grade Context7 MCP integration patterns for language-specific documentation access with real-time library resolution and intelligent caching

Enterprise Cloudflare Edge Platform with AI-powered edge computing architecture, Context7 integration, and intelligent global orchestration for scalable modern applications

Enterprise Programming Languages Foundation with AI-powered language selection, Context7 integration, and intelligent multi-language orchestration for optimal technology choices

AI-powered enterprise refactoring with Context7 integration, automated code transformation, Rope pattern intelligence, and technical debt quantification across 25+ programming languages

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Enterprise Claude Code context window optimization with 2025 best practices: aggressive clearing, memory file management, MCP optimization, strategic chunking, and quality-over-quantity principles for 200K token context windows.