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...
Analyzes legacy PL/I (Programming Language One) programs to assist with migration to modern Java applications. Extracts business logic, data structures, procedure definitions, and file operations...
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track...
Provides comprehensive KeyCloak administration guidance including realm management, user/group administration, client configuration, authentication flows, identity brokering, authorization...
Jeffrey Emanuel's multi-agent implementation workflow using NTM, Agent Mail, Beads, and BV. The execution phase that follows planning and bead creation. Includes exact prompts used.
深度调研的多Agent编排工作流：把一个调研目标拆成可并行子目标，用 Claude Code 非交互模式（`claude -p`）运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付"成品报告文件路径 +...
Control WezTerm terminal emulator via CLI. Manage panes, tabs, workspaces, and execute commands in running terminals.
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory...
Comprehensive backend development workflow that orchestrates expert analysis, architecture design, implementation, and deployment using the integrated toolset. Handles everything from API design...
The philosophy and practical benefits of agent fungibility in multi-agent software development. Why homogeneous, interchangeable agents outperform specialized role-based systems at scale.
Refactor CLAUDE.md files to follow progressive disclosure principles. Use when CLAUDE.md is too long or disorganized.
Provides comprehensive DevOps guidance including CI/CD pipeline design, infrastructure as code (Terraform, CloudFormation, Bicep), container orchestration (Docker, Kubernetes), deployment...
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with...
Conducts comprehensive backend design reviews covering API design quality, database architecture validation, microservices patterns assessment, integration strategies evaluation, security design...
Process and analyze massive documents (PDF, Word, HTML, JSON, Markdown) that exceed context limits. Use when a document is too large to fit in context, when you need to search large files, find...
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring...
GitHub CLI - manage repositories, issues, pull requests, actions, releases, and more from the command line.
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture...
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
Comprehensive guide for using Local Skills MCP - creating skills in the right locations, understanding skill directories, setup, and configuration. Use when creating new skills, deciding where to...