AI & LLM Tools
Harness the power of language models in your workflow
Explore 100 curated ai & llm tools skills for Claude Code and Codex CLI. Each skill enhances your development workflow.
Browse 100 AI & LLM Tools Skills
Skill Writer
Guide users through creating Agent Skills for Claude Code
Claude Opus 4 5 Migration
Migrate prompts and code from Claude Sonnet 4
Mcp Builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact...
Web Artifacts Builder
Suite of tools for creating elaborate, multi-component claude
Workflow Interactive Dev
用于开发 FastGPT 工作流中的交互响应。详细说明了交互节点的架构、开发流程和需要修改的文件。
Create Skill File
Guides Claude in creating well-structured SKILL
Langchain Architecture
Design LLM applications using the LangChain framework with agents, memory, and tool integration p...
Llm Evaluation
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human...
Prompt Engineering Patterns
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and contr...
Rag Implementation
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and...
Skill Developer
Create and manage Claude Code skills following Anthropic best practices
Developer Growth Analysis
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and ...
Skill Share
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seam...
Mcp Builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact...
Artifacts Builder
Suite of tools for creating elaborate, multi-component claude
Connect
Connect Claude to any app
Connect Apps
Connect Claude to external apps like Gmail, Slack, GitHub
Openai Knowledge
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streamin...
Test Coverage Improver
Improve test coverage in the OpenAI Agents Python repository: run `make coverage`, inspect covera...
Senior Prompt Engineer
World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, a...
Nowait Reasoning Optimizer
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs
Generate Image
Generate or edit images using AI models (FLUX, Gemini)
Perplexity Search
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM an...
Whisper
OpenAI's general-purpose speech recognition model
Guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce str...
Quantizing Models Bitsandbytes
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss
Sglang
Fast structured generation and serving for LLMs with RadixAttention prefix caching
Serving Llms Vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching
Simpo Training
Simple Preference Optimization for LLM alignment
Peft Fine Tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods
Evaluating Llms Harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag)
Langsmith Observability
LLM observability platform for tracing, evaluation, and monitoring
Langchain
Framework for building LLM-powered applications with agents, chains, and RAG
Blip 2 Vision Language
Vision-language pre-training framework bridging frozen image encoders and LLMs
Training Llms Megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parall...
Llama Cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware
Speculative Decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decodin...
Llama Factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8...
Implementing Llms Litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, ...
Openrlhf Training
High-performance RLHF framework with Ray+vLLM acceleration
Fine Tuning With Trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for prefer...
Awq Quantization
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accura...
Tensorrt Llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency
Llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering
Axolotl
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KT...
Llamaindex
Data framework for building LLM applications with RAG
Nemo Curator
GPU-accelerated data curation for LLM training
Nemo Guardrails
NVIDIA's runtime safety framework for LLM applications
Autogpt Agents
Autonomous AI agent platform for building and deploying continuous agents
Model Pruning
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT
Hqq Quantization
Half-Quadratic Quantization for LLMs without calibration data
Clip
OpenAI's model connecting vision and language
Gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss
Instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions aut...
Phoenix Observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring
Nanogpt
Educational GPT implementation in ~300 lines
Mcp Builder
Build MCP (Model Context Protocol) servers that give Claude new capabilities
Hooks Automation
Automated coordination, formatting, and learning from Claude Code operations using intelligent ho...
Skill Builder
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and...
Handoff
Hand off to a fresh Claude session
Claude Code Guide
Claude Code 高级开发指南 - 全面的中文教程，涵盖工具使用、REPL 环境、开发工作流、MCP 集成、高级模式和最佳实践。适合学习 Claude Code 的高级功能和开发技巧。
Claude Cookbooks
Claude AI cookbooks - code examples, tutorials, and best practices for using Claude API
Claude Skills
Claude Skills meta-skill: extract domain material (docs/APIs/code/specs) into a reusable Skill (S...
Advanced Evaluation
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs"...
Project Development
This skill should be used when the user asks to "start an LLM project", "design batch pipeline", ...
Agent Builder
Use when creating, improving, or troubleshooting Claude Code subagents
Creating Skills
Use when creating new Claude Code skills or improving existing ones - ensures skills are discover...
Generate Image
Generate or edit images using AI models (FLUX, Gemini)
Hypogenic
Automated LLM-driven hypothesis generation and testing on tabular datasets
Perplexity Search
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM an...
V3 Cli Modernization
CLI modernization and hooks system enhancement for claude-flow v3
V3 Security Overhaul
Complete security architecture overhaul for claude-flow v3
V3 Mcp Optimization
MCP server optimization and transport layer enhancement for claude-flow v3
V3 Ddd Architecture
Domain-Driven Design architecture for claude-flow v3
V3 Core Implementation
Core module implementation for claude-flow v3
Creating Agent Skills
Expert guidance for creating, writing, and refining Claude Code Skills
Gemini Imagegen
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro)
Nano Banana Pro
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro)
Coding Agent
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic ...
Openai Whisper
Local speech-to-text with the Whisper CLI (no API key)
Openai Image Gen
Batch-generate images via OpenAI Images API
Openai Whisper Api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper)
Gemini
Gemini CLI for one-shot Q&A, summaries, and generation
Model Usage
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the...
Patterns
Design patterns for the Langroid multi-agent LLM framework
Docetl
Build and run LLM-powered data processing pipelines with DocETL
Agentica Prompts
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
Agentica Claude Proxy
Guide for integrating Agentica SDK with Claude Code CLI proxy
Sub Agents
Create and configure Claude Code sub-agents with custom prompts, tools, and models
Skill Developer
Meta-skill for creating and managing Claude Code skills
Braintrust Analyze
Analyze Claude Code sessions via Braintrust
Braintrust Tracing
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
Cli Reference
Claude Code CLI commands, flags, headless mode, and automation patterns
Hook Developer
Complete Claude Code hooks reference - input/output schemas, registration, testing patterns
Llm Tuning Patterns
LLM Tuning Patterns
Slash Commands
Create and use Claude Code slash commands - quick prompts, bash execution, file references
Trace Claude Code
Automatically trace Claude Code conversations to Braintrust for observability
Agentica Server
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
Claude Code Analyzer
Analyzes Claude Code usage patterns and provides comprehensive recommendations
Gpt5 Consultant
Use this skill when stuck in circular debugging, when solutions aren't working despite multiple a...
How to Install AI & LLM Tools Skills
All skills in this collection can be installed through Claude's Settings. Navigate to Settings → Capabilities → Upload skill to add any skill to your workflow. Learn more.
This collection includes 100 community-curated skills for ai & llm tools workflows.