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.

1. remotion-captions ★ 4,487
   Transcribing, displaying and animating captions
2. prompt-optimizer ★ 986
   Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates. Use when asked
3. llm-application-dev ★ 1,137
   Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatb
4. brainiall-diarized-transcription
   Transcribe an explicitly authorized local Brazilian Portuguese or Spanish audio or video file with the metered BRAINIALL API, speaker diariz
5. deep-research ★ 417
   Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literatur
6. elevenlabs ★ 417
   Convert documents and text to audio using ElevenLabs text-to-speech. Use this skill when the user wants to create a podcast, narrate a docum
7. google-tts ★ 417
   Convert documents and text to audio using Google Cloud Text-to-Speech. Use this skill when the user wants to: narrate a document, read aloud
8. imagen ★ 417
   Generate images using Google Gemini's image generation capabilities. Use this skill when the user needs to create, generate, or produce imag
9. solve ★ 7
   Route a goal through acc's scored-memory loop via acc_act(runtime="solve"); deliberate any returned brain_frame and submit via continue.
10. openai-docs ★ 25,414
    Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date offic
11. speech ★ 25,414
    Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the Ope
12. transcribe ★ 25,414
    Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video
13. memory-search ★ 30,576
    Search conversation history and semantic memory to recall previous discussions, decisions, and context. Use when the user asks to "search me
14. agent-memory-mcp ★ 30,576
    A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
15. agent-memory-systems ★ 30,576
    "Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agen
16. agent-tool-builder ★ 30,576
    "Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinat
17. agents-crewai ★ 30,576
    Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on compl
18. agents-langchain ★ 30,576
    Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+
19. agents-llamaindex ★ 30,576
    Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features
20. ai-agents-architect ★ 30,576
    "Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration
21. computer-use-agents ★ 30,576
    "Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers An
22. context-window-management ★ 30,576
    "Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window,
23. conversation-memory ★ 30,576
    "Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, rem
24. crewai ★ 30,576
    "Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and go
25. distributed-training-accelerate ★ 30,576
    Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Au
26. distributed-training-ray-train ★ 30,576
    Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparam
27. emerging-techniques-long-context ★ 30,576
    Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long docume
28. emerging-techniques-model-merging ★ 30,576
    Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending
29. emerging-techniques-model-pruning ★ 30,576
    Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining,
30. emerging-techniques-moe-training ★ 30,576
    Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost red
31. evaluation-lm-evaluation-harness ★ 30,576
    Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparin
32. fine-tuning-axolotl ★ 30,576
    Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
33. fine-tuning-llama-factory ★ 30,576
    Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
34. fine-tuning-peft ★ 30,576
    Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU mem
35. fine-tuning-unsloth ★ 30,576
    Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
36. gemini ★ 30,576
    Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis r
37. gemini-api-agent-platform ★ 30,576
    Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK for enterprise AI applications. Covers SDK usage (Python, JS
38. gepetto ★ 30,576
    Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning feature
39. inference-serving-llama-cpp ★ 30,576
    Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs,
40. inference-serving-tensorrt-llm ★ 30,576
    Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H
41. inference-serving-vllm ★ 30,576
    Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inf
42. langfuse ★ 30,576
    "Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration w
43. llm-app-patterns ★ 30,576
    "Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use
44. llm-evaluation ★ 30,576
    "Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing."
45. llm-ops ★ 30,576
    "LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquitet
46. model-architecture-litgpt ★ 30,576
    Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need c
47. model-architecture-mamba ★ 30,576
    State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with
48. model-architecture-torchtitan ★ 30,576
    Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1
49. multimodal-clip ★ 30,576
    OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Train
50. multimodal-stable-diffusion ★ 30,576
    State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text promp