Agent skills · AI, RAG & memory

50 listings on this page, in order of arrival. Each one has its own page with README, repository facts and source links.

multimodal-whisper ★ 30,576
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification
openai-docs ★ 30,576
"Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: C
optimization-awq ★ 30,576
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7
optimization-bitsandbytes ★ 30,576
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
optimization-flash-attention ★ 30,576
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers wi
optimization-gptq ★ 30,576
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you
parallel-agents ★ 30,576
Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analys
post-training-grpo-rl-training ★ 30,576
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
post-training-simpo ★ 30,576
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0).
post-training-slime ★ 30,576
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom
post-training-trl-fine-tuning ★ 30,576
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimiz
post-training-verl ★ 30,576
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or ot
prompt-caching ★ 30,576
"Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: pro
prompt-engineer ★ 30,576
"Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and pr
prompt-engineering ★ 30,576
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prom
prompt-engineering-dspy ★ 30,576
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Sta
prompt-engineering-guidance ★ 30,576
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workf
prompt-engineering-instructor ★ 30,576
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type sa
prompt-engineering-patterns ★ 30,576
"Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability."
prompt-library ★ 30,576
"Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refineme
rag-chroma ★ 30,576
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata.
rag-engineer ★ 30,576
"Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval o
rag-faiss ★ 30,576
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and vari
rag-implementation ★ 30,576
"Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag, retrieval
rag-pinecone ★ 30,576
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering
rag-qdrant ★ 30,576
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast neares
rag-sentence-transformers ★ 30,576
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering,
safety-alignment-constitutional-ai ★ 30,576
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision,
safety-alignment-llamaguard ★ 30,576
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, subst
safety-alignment-nemo-guardrails ★ 30,576
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination
tokenization-huggingface-tokenizers ★ 30,576
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and
tokenization-sentencepiece ★ 30,576
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB
voice-agents ★ 30,576
"Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognit
voice-ai-development ★ 30,576
"Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice ag
ai-product ★ 30,576
"Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill c
ai-wrapper-product ★ 30,576
"Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but diffe
brand-guidelines-anthropic ★ 30,576
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use
brand-guidelines-community ★ 30,576
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use
imagegen ★ 30,576
"Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background remo
c-pro ★ 30,576
"Write efficient C code with proper memory management, pointer"
claude-api ★ 30,576
"Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migratin
cocoindex ★ 30,576
Comprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write
mcp-builder ★ 30,576
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-design
mcp-integration ★ 30,576
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model
senior-prompt-engineer ★ 30,576
World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Cla
tdd-orchestrator ★ 30,576
Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven deve
doordash-order-ledger ★ 30,576
Accountability layer for agent-driven DoorDash ordering. Works with the doordash-audit-log hook (which appends every dd-cli invocation to an
brand-guidelines ★ 30,576
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use
internal-comms-anthropic ★ 30,576
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use
session-handoff ★ 30,576
"Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context s