Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF,...
Replace with description of the skill and when Claude should use it.
Comprehensive React and Vite SPA performance, architecture, and deployment guidelines. Use this skill when building, reviewing, or refactoring React applications built with Vite (SPA). Covers...
Conducts comprehensive frontend design reviews covering UI/UX design quality, design system validation, accessibility compliance, responsive design patterns, component library architecture, and...
|
SSH remote access patterns and utilities. Connect to servers, manage keys, tunnels, and transfers.
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor -...
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4,...
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.
Creates high-quality technical documentation including API documentation, user guides, tutorials, architecture documents, README files, release notes, and technical specifications. Produces clear,...
Generates well-structured git commit messages following conventional commit standards and best practices. Creates clear, descriptive commits with proper type prefixes (feat, fix, docs, refactor,...
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or...
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+...
智能变更日志生成器 - 自动分析Git提交历史，生成符合规范的CHANGELOG.md。支持语义化版本管理、多种输出格式、增量更新和GitHub/GitLab集成。
Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Claude Code...
Guides database migration projects including engine changes (MySQL to PostgreSQL, Oracle to PostgreSQL, SQL Server to PostgreSQL), version upgrades, cloud migrations (on-premise to RDS/Cloud...
Provides comprehensive KeyCloak administration guidance including realm management, user/group administration, client configuration, authentication flows, identity brokering, authorization...
Deploy and manage Vercel projects, domains, environment variables, and serverless functions using the `vercel` CLI.
Find opportunities to improve web application code using TanStack libraries (Query, Table, Form, Router, etc.). Avoid man-with-hammer syndrome by applying TanStack after vanilla implementation works.
|