2,295 agent tools in this category, ranked by GitHub stars for now. Hands-on test results will replace this ranking as they finish.
The three most-starred tools here. Not tested together yet.
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and
npx skills add anthropics/skills --skill academy-guideReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER —
npx skills add anthropics/skills --skill claude-apiUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
| Tool | Stars | Last update | License | |
|---|---|---|---|---|
| academy-guide Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutor SkillOfficial · AnthropicInstall · skills CLI | 194,218 | — | ||
| claude-api Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. SkillOfficial · AnthropicInstall · skills CLI | 194,218 | — | ||
| open-webui User-friendly AI Interface (Supports Ollama, OpenAI API, ...) MCP server | 158,670 | — | ||
| ccs-align Run the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations through search → timeline → g SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| mode-creator Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Teleg SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| gemini-cli An open-source AI agent that brings the power of Gemini directly into your terminal. MCP server | 108,834 | — | ||
| html-ppt-hermes-cyber-terminal OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck SkillInstall · skills CLI | 107,550 | Apache-2.0 | ||
| html-ppt-presenter-mode OpenDesign live demo: from a one-line prompt to runnable design in a single session — the flow, live. Built as a decision-grade AI literacy deck for d SkillInstall · skills CLI | 107,550 | Apache-2.0 | ||
| html-ppt-tech-sharing OpenDesign internals: how the agent stream, sandbox, and artifacts work — an engineering deep-dive talk. Built as a decision-grade AI literacy deck fo SkillInstall · skills CLI | 107,550 | Apache-2.0 | ||
| OmniRoute Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Work MCP server | 87,505 | — | ||
| ai-ml-api-automation Automate AI ML API tasks via Rube MCP (Composio). Always search tools first for current schemas. SkillInstall · skills CLI | 79,451 | — | ||
| anthropic-administrator-automation Automate Anthropic Admin tasks via Rube MCP (Composio). Always search tools first for current schemas. SkillInstall · skills CLI | 79,451 | — | ||
| anthropic_administrator-automation Automate Anthropic Admin tasks via Rube MCP (Composio): API keys, usage, workspaces, and organization management. Always search tools first for curren SkillInstall · skills CLI | 79,451 | — | ||
| bigml-automation Automate Bigml tasks via Rube MCP (Composio). Always search tools first for current schemas. SkillInstall · skills CLI | 79,451 | — | ||
| claid-ai-automation Automate Claid AI tasks via Rube MCP (Composio). Always search tools first for current schemas. SkillInstall · skills CLI | 79,451 | — | ||
| convolo-ai-automation Automate Convolo AI tasks via Rube MCP (Composio). Always search tools first for current schemas. SkillInstall · skills CLI | 79,451 | — | ||
| customgpt-automation Automate Customgpt tasks via Rube MCP (Composio). Always search tools first for current schemas. SkillInstall · skills CLI | 79,451 | — | ||
| datarobot-automation Automate Datarobot tasks via Rube MCP (Composio). Always search tools first for current schemas. SkillInstall · skills CLI | 79,451 | — | ||
| extracta-ai-automation Automate Extracta AI tasks via Rube MCP (Composio). Always search tools first for current schemas. SkillInstall · skills CLI | 79,451 | — | ||
| deepspot-m Generates transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Used for predicted log1p-CPM expression from 224x224 SkillInstall · skills CLI | 57,090 | MIT | ||
| diffdock Predicts protein-small-molecule binding poses with DiffDock and DiffDock-L from PDB or sequence plus SMILES/SDF/MOL2. Covers batch docking, pose triag SkillInstall · skills CLI | 57,090 | MIT | ||
| esm Uses the Biohub esm Python SDK for ESM3 protein generation, ESMC embeddings, and ESMFold2 all-atom folding. Applies to local model inference and Biohu SkillInstall · skills CLI | 57,090 | MIT | ||
| genomic-intelligence Predicts regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language m SkillInstall · skills CLI | 57,090 | MIT | ||
| hugging-science Discovers and evaluates scientific datasets, models, methodology posts, and Spaces through the Hugging Science catalog. Used when selecting scientific SkillInstall · skills CLI | 57,090 | MIT | ||
| shap Explain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature attributions SkillInstall · skills CLI | 57,090 | MIT | ||
| stable-baselines3 Trains and evaluates single-agent reinforcement learning with Stable Baselines3 (PPO, SAC, DQN, TD3, DDPG, A2C), Gymnasium custom environments, vector SkillInstall · skills CLI | 57,090 | MIT | ||
| transformers Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and mult SkillInstall · skills CLI | 57,090 | MIT | ||
| waypoint-bio Supports work with Outpost Bio's open microbiome foundation models - the Waypoint checkpoints (Waypoint-6m, Waypoint-45m, Waypoint-170m), the Atlas pr SkillInstall · skills CLI | 57,090 | MIT | ||
| LocalAI LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. MCP server | 50,368 | — | ||
| advanced-evaluation Design LLM-as-judge rubrics, direct scores and pairwise comparisons. Use for judge models, evals, position bias and calibration against human labels. SkillInstall · skills CLI | 49,672 | MIT | ||
| ai-wrapper-product Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc. ) into focused tools people will pay for. Not just "ChatGPT but different" - pr SkillInstall · skills CLI | 49,672 | MIT | ||
| azure-ai-openai-dotnet Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcri SkillInstall · skills CLI | 49,672 | MIT | ||
| hugging-face-evaluation Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial A SkillInstall · skills CLI | 49,672 | MIT | ||
| langfuse Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangCha SkillInstall · skills CLI | 49,672 | MIT | ||
| llm-app-patterns Architecture and integration sketches for LLM applications, with explicit retrieval, tool, privacy and verification boundaries. SkillInstall · skills CLI | 49,672 | MIT | ||
| mcp-builder Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP ser SkillInstall · skills CLI | 49,672 | MIT | ||
| mcp-tool-developer Build Model Context Protocol (MCP) servers and tools from scratch. Full-stack MCP development with TypeScript/Python, testing, deployment, and registr SkillInstall · skills CLI | 49,672 | MIT | ||
| prompt-caching Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) SkillInstall · skills CLI | 49,672 | MIT | ||
| prompt-engineering Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting stra SkillInstall · skills CLI | 49,672 | MIT | ||
| rag-engineer Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization SkillInstall · skills CLI | 49,672 | MIT | ||
| rag-implementation RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval o SkillInstall · skills CLI | 49,672 | MIT | ||
| agent-sdk-dev Development kit for working with the Claude Agent SDK PluginAnthropic marketplace | 47,064 | Apache-2.0 | ||
| kong 🦍 The API and AI Gateway MCP server | 44,378 | — | ||
| checkpoint-promotion Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after a training run produces a checkpo SkillInstall · skills CLI | 42,495 | MIT | ||
| dataset-curation Prepare, format, and validate datasets for supervised fine-tuning and preference training. Use when converting raw data into training format, applying SkillInstall · skills CLI | 42,495 | MIT | ||
| eval-harness-first Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Us SkillInstall · skills CLI | 42,495 | MIT | ||
| evaluation-methodology PluginEval quality methodology, covering dimensions, rubrics, and scoring formulas. Use this skill when understanding how plugin quality is measured, SkillInstall · skills CLI | 42,495 | MIT | ||
| finetuning-method-selection Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model. Use when start SkillInstall · skills CLI | 42,495 | MIT | ||
| grpo-rlvr-training Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmic SkillInstall · skills CLI | 42,495 | MIT | ||
| llm-evaluation Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM per SkillInstall · skills CLI | 42,495 | MIT | ||
| lora-qlora-recipes Configure LoRA and QLoRA supervised fine-tuning with current best-practice hyperparameters. Use when writing or reviewing a LoRA/QLoRA training config SkillInstall · skills CLI | 42,495 | MIT | ||
| ml-pipeline-workflow Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, SkillInstall · skills CLI | 42,495 | MIT | ||
| preference-optimization Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO. Use when preference pairs or thumbs-up/down feedback exist, when choosin SkillInstall · skills CLI | 42,495 | MIT | ||
| quantized-export Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8. Use after a checkpoint p SkillInstall · skills CLI | 42,495 | MIT | ||
| rag-implementation Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-gro SkillInstall · skills CLI | 42,495 | MIT | ||
| recsys-pipeline-architect Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework populari SkillInstall · skills CLI | 42,495 | MIT | ||
| spark-environment-setup Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX S SkillInstall · skills CLI | 42,495 | MIT | ||
| spark-memory-thermal-ops Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when SkillInstall · skills CLI | 42,495 | MIT | ||
| spark-training-gotchas Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs belo SkillInstall · skills CLI | 42,495 | MIT | ||
| trace-to-training-data Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failure examples exist and need to bec SkillInstall · skills CLI | 42,495 | MIT | ||
| vision-sft Fine-tune vision-language models (VLMs) with supervised learning on image+text data. Use when adapting a VLM to a visual domain or task, configuring f SkillInstall · skills CLI | 42,495 | MIT | ||
| ai-prompt-engineering-safety-review Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectivene SkillInstall · skills CLI | 41,140 | MIT | ||
| arize-ai-provider-integration Creates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features. Supports a SkillInstall · skills CLI | 41,140 | MIT | ||
| arize-annotation Creates and manages annotation configs (categorical, continuous, freeform label schemas) and annotation queues (human review workflows) on Arize. Appl SkillInstall · skills CLI | 41,140 | MIT | ||
| arize-evaluator Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks SkillInstall · skills CLI | 41,140 | MIT | ||
| arize-experiment Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing result SkillInstall · skills CLI | 41,140 | MIT | ||
| arize-instrumentation Adds Arize AX tracing to an LLM application for the first time. Follows a two-phase agent-assisted flow to analyze the codebase then implement instrum SkillInstall · skills CLI | 41,140 | MIT | ||
| arize-prompt-optimization Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performanc SkillInstall · skills CLI | 41,140 | MIT | ||
| arize-trace Downloads, exports, and inspects existing Arize traces and spans to understand what an LLM app is doing or debug runtime issues. Covers exporting trac SkillInstall · skills CLI | 41,140 | MIT | ||
| create-llms Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/ SkillInstall · skills CLI | 41,140 | MIT | ||
| integrate-context-matic Discovers and integrates third-party APIs using the context-matic MCP server. Uses `fetch_api` to find available API SDKs, `ask` for integration guida SkillInstall · skills CLI | 41,140 | MIT | ||
| java-mcp-server-generator Use this skill when the user wants to create a Model Context Protocol (MCP) server in Java or in a Spring Boot app. Also use it when the user wants AI SkillInstall · skills CLI | 41,140 | MIT | ||
| mcp-cli Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP serve SkillInstall · skills CLI | 41,140 | MIT | ||
| detecting-data-and-model-poisoning Identify poisoned training data and backdoored ML models across the pipeline using IBM's Adversarial Robustness Toolbox (activation clustering, spectr SkillInstall · skills CLI | 36,105 | Apache-2.0 | ||
| detecting-indirect-prompt-injection Detect and defend against indirect prompt injection hidden in web pages, documents, and images consumed by an agent, via content extraction (HTML/PDF/ SkillInstall · skills CLI | 36,105 | Apache-2.0 | ||
| agents-langchain Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integratio SkillInstall · skills CLI | 33,495 | MIT | ||
| agents-llamaindex Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector in SkillInstall · skills CLI | 33,495 | MIT | ||
| ai-product 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 covers LLM SkillInstall · skills CLI | 33,495 | MIT | ||
| ai-wrapper-product Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - pro SkillInstall · skills CLI | 33,495 | MIT | ||
| claude-code-guide Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and SkillInstall · skills CLI | 33,495 | MIT | ||
| distributed-training-accelerate Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic de SkillInstall · skills CLI | 33,495 | MIT | ||
| distributed-training-deepspeed Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention SkillInstall · skills CLI | 33,495 | MIT | ||
| distributed-training-megatron-core Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parame SkillInstall · skills CLI | 33,495 | MIT | ||
| distributed-training-pytorch-fsdp Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2 SkillInstall · skills CLI | 33,495 | MIT | ||
| distributed-training-pytorch-lightning High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scale SkillInstall · skills CLI | 33,495 | MIT | ||
| distributed-training-ray-train Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tunin SkillInstall · skills CLI | 33,495 | MIT | ||
| emerging-techniques-knowledge-distillation Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performanc SkillInstall · skills CLI | 33,495 | MIT | ||
| emerging-techniques-long-context Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-1 SkillInstall · skills CLI | 33,495 | MIT | ||
| emerging-techniques-model-merging Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-sp SkillInstall · skills CLI | 33,495 | MIT | ||
| emerging-techniques-model-pruning Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving SkillInstall · skills CLI | 33,495 | MIT | ||
| emerging-techniques-moe-training Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs SkillInstall · skills CLI | 33,495 | MIT | ||
| emerging-techniques-speculative-decoding Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1. SkillInstall · skills CLI | 33,495 | MIT | ||
| evaluation-bigcode-evaluation-harness Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, compari SkillInstall · skills CLI | 33,495 | MIT | ||
| evaluation-lm-evaluation-harness Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, SkillInstall · skills CLI | 33,495 | MIT | ||
| evaluation-nemo-evaluator Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable SkillInstall · skills CLI | 33,495 | MIT | ||
| fine-tuning-axolotl Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support SkillInstall · skills CLI | 33,495 | MIT | ||
| fine-tuning-llama-factory Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support SkillInstall · skills CLI | 33,495 | MIT | ||
| fine-tuning-peft Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when SkillInstall · skills CLI | 33,495 | MIT | ||
| fine-tuning-unsloth Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization SkillInstall · skills CLI | 33,495 | MIT | ||
| gemini Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring l SkillInstall · skills CLI | 33,495 | MIT | ||
| gemini-api-agent-platform 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/TS, Go, J SkillInstall · skills CLI | 33,495 | MIT | ||
| inference-serving-llama-cpp Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when C SkillInstall · skills CLI | 33,495 | MIT | ||
| inference-serving-sglang Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflow SkillInstall · skills CLI | 33,495 | MIT | ||
| inference-serving-tensorrt-llm Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when SkillInstall · skills CLI | 33,495 | MIT | ||
| inference-serving-vllm Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference lat SkillInstall · skills CLI | 33,495 | MIT | ||
| llm-ops LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA SkillInstall · skills CLI | 33,495 | MIT | ||
| model-architecture-litgpt Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model SkillInstall · skills CLI | 33,495 | MIT | ||
| model-architecture-mamba State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware- SkillInstall · skills CLI | 33,495 | MIT | ||
| model-architecture-nanogpt Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpat SkillInstall · skills CLI | 33,495 | MIT | ||
| model-architecture-rwkv RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux SkillInstall · skills CLI | 33,495 | MIT | ||
| model-architecture-torchtitan Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek SkillInstall · skills CLI | 33,495 | MIT | ||
| multimodal-clip OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M SkillInstall · skills CLI | 33,495 | MIT | ||
| multimodal-llava Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA l SkillInstall · skills CLI | 33,495 | MIT | ||
| multimodal-segment-anything Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as pr SkillInstall · skills CLI | 33,495 | MIT | ||
| multimodal-stable-diffusion State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, perfor SkillInstall · skills CLI | 33,495 | MIT | ||
| multimodal-whisper OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six mode SkillInstall · skills CLI | 33,495 | MIT | ||
| openai-docs Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Respo SkillInstall · skills CLI | 33,495 | MIT | ||
| optimization-awq Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on SkillInstall · skills CLI | 33,495 | MIT | ||
| optimization-bitsandbytes 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 SkillInstall · skills CLI | 33,495 | MIT | ||
| optimization-flash-attention Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long se SkillInstall · skills CLI | 33,495 | MIT | ||
| optimization-gguf GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing SkillInstall · skills CLI | 33,495 | MIT | ||
| optimization-gptq Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× me SkillInstall · skills CLI | 33,495 | MIT | ||
| optimization-hqq Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, SkillInstall · skills CLI | 33,495 | MIT | ||
| post-training-grpo-rl-training Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training SkillInstall · skills CLI | 33,495 | MIT | ||
| post-training-miles Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, ne SkillInstall · skills CLI | 33,495 | MIT | ||
| post-training-openrlhf High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO- SkillInstall · skills CLI | 33,495 | MIT | ||
| post-training-simpo Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No refere SkillInstall · skills CLI | 33,495 | MIT | ||
| post-training-slime Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data gener SkillInstall · skills CLI | 33,495 | MIT | ||
| post-training-torchforge Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstract SkillInstall · skills CLI | 33,495 | MIT | ||
| post-training-trl-fine-tuning Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and SkillInstall · skills CLI | 33,495 | MIT | ||
| post-training-verl Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL alg SkillInstall · skills CLI | 33,495 | MIT | ||
| rag-sentence-transformers Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrie SkillInstall · skills CLI | 33,495 | MIT | ||
| safety-alignment-constitutional-ai Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF SkillInstall · skills CLI | 33,495 | MIT | ||
| safety-alignment-llamaguard Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, sel SkillInstall · skills CLI | 33,495 | MIT | ||
| safety-alignment-nemo-guardrails NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, SkillInstall · skills CLI | 33,495 | MIT | ||
| tokenization-huggingface-tokenizers Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram al SkillInstall · skills CLI | 33,495 | MIT | ||
| tokenization-sentencepiece Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), SkillInstall · skills CLI | 33,495 | MIT | ||
| cognee-integrations Use when the user wants to connect cognee to external services — switching LLM or embedding providers (OpenAI, Azure, Gemini, Anthropic, Ollama, OpenR SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| gws-modelarmor Google Model Armor: Filter user-generated content for safety. SkillInstall · skills CLI | 32,308 | Apache-2.0 | ||
| gws-modelarmor-create-template Google Model Armor: Create a new Model Armor template. SkillInstall · skills CLI | 32,308 | Apache-2.0 | ||
| gws-modelarmor-sanitize-prompt Google Model Armor: Sanitize a user prompt through a Model Armor template. SkillInstall · skills CLI | 32,308 | Apache-2.0 | ||
| gws-modelarmor-sanitize-response Google Model Armor: Sanitize a model response through a Model Armor template. SkillInstall · skills CLI | 32,308 | Apache-2.0 | ||
| add-atomic-chat-tool Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API. SkillInstall · skills CLI | 31,114 | MIT | ||
| add-codex Use Codex (OpenAI's codex app-server) as a full agent provider — planning, tool orchestration, MCP tools, server-side history, session resume — alongs SkillInstall · skills CLI | 31,114 | MIT | ||
| add-cursor Use Cursor (local Agent SDK) as a full agent provider — planning, tool orchestration, MCP tools, session resume — alongside or instead of Claude. Curs SkillInstall · skills CLI | 31,114 | MIT | ||
| add-ollama-provider Route a NanoClaw agent group to a local Ollama model instead of the Anthropic API. Ollama speaks the Anthropic API natively (v1/messages), so no provi SkillInstall · skills CLI | 31,114 | MIT | ||
| add-ollama-tool Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library. SkillInstall · skills CLI | 31,114 | MIT | ||
| add-opencode Use OpenCode as an agent provider. OpenRouter, OpenAI, Google, DeepSeek, etc. via OpenCode config — not the Anthropic Agent SDK. Per group via `ncl gr SkillInstall · skills CLI | 31,114 | MIT | ||
| chief-ai-officer-advisor Use for AI strategy decisions: API vs fine-tune vs build, EU AI Act or US state risk classification, when self-hosting pays off, or AI hiring order. R SkillInstall · skills CLI | 29,773 | MIT | ||
| claude-coach Use when the user wants to get better at using Claude ('coach me', 'teach me Claude tricks', 'make me a power user'). Rates their prompts with prompt_ SkillInstall · skills CLI | 29,773 | MIT | ||
| kubernetes-operator Use when building a Kubernetes operator or CRD (controller-runtime, kubebuilder, operator-sdk, KOPF), before writing the controller. Validates CRDs wi SkillInstall · skills CLI | 29,773 | MIT | ||
| llm-cost-optimizer Use whenever an LLM feature is being built or its costs come up (model choice, prompt caching, token limits, per-feature spend). Sets routing, caching SkillInstall · skills CLI | 29,773 | MIT | ||
| prompt-governance Use when prompts run in production and need versioning, a registry, A/B tests, regression checks or an eval pipeline. Sets up the release process for SkillInstall · skills CLI | 29,773 | MIT | ||
| senior-computer-vision Computer vision models: object detection, segmentation, training a custom model, and optimizing or deploying inference (YOLO, DETR, SAM, ONNX, TensorR SkillInstall · skills CLI | 29,773 | MIT | ||
| senior-ml-engineer Use for putting ML models or LLM features into production: deployment, MLOps, drift monitoring, RAG pipelines, LLM API cost and retries. Deploys with SkillInstall · skills CLI | 29,773 | MIT | ||
| chatgpt-apps Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design too SkillInstall · skills CLI | 28,730 | — | ||
| python-sdk The official Python SDK for Model Context Protocol servers and clients MCP server | 24,865 | — | ||
| bigquery-ai-ml Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform SkillInstall · skills CLI | 24,146 | Apache-2.0 | ||
| developing-genkit-dart Provides guidance on developing AI-powered applications using the Genkit Dart SDK. Use when the user asks to build AI agents in Dart, use Genkit flows SkillInstall · skills CLI | 24,146 | Apache-2.0 | ||
| developing-genkit-go Provides guidance on developing AI-powered applications using Genkit in Go. Use when the user asks to build AI features, agents, flows, or tools in Go SkillInstall · skills CLI | 24,146 | Apache-2.0 | ||
| developing-genkit-js Provides guidance on developing AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or SkillInstall · skills CLI | 24,146 | Apache-2.0 | ||
| gemini-api Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform. Guides the u SkillInstall · skills CLI | 24,146 | Apache-2.0 | ||
| gemini-live-api Generates a Gemini LiveAPI client service class in the user's chosen programming language. Use when the user wants to build, scaffold, or integrate a SkillInstall · skills CLI | 24,146 | Apache-2.0 | ||
| gke-inference Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE SkillInstall · skills CLI | 24,146 | Apache-2.0 | ||
| litert-google-tensor Compiles LiteRT (.tflite) models ahead-of-time for Google Tensor TPUs (Tensor G5 on Pixel 10, Tensor G6 on Pixel 11) locally on Linux x86_64 or on Goo SkillInstall · skills CLI | 24,146 | Apache-2.0 | ||
| rocketride-server High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8 MCP server | 20,037 | — | ||
| auto-review-loop-llm Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto re SkillInstall · skills CLI | 19,162 | MIT | ||
| auto-review-loop-minimax Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with SkillInstall · skills CLI | 19,162 | MIT | ||
| paper-write Draft LaTeX paper section by section from an outline. Use when user says \"写论文\", \"write paper\", \"draft LaTeX\", \"开始写\", or wants to generate LaTe SkillInstall · skills CLI | 19,162 | MIT | ||
| advanced-evaluation This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias m SkillInstall · skills CLI | 18,347 | MIT | ||
| book-sft-pipeline This skill should be used for book-to-SFT pipelines: ePub extraction, literary segmentation, author-voice dataset construction, style-transfer trainin SkillInstall · skills CLI | 18,347 | MIT | ||
| comprehensive-research-agent Ensure thorough validation, error recovery, and transparent reasoning in research tasks with multiple tool calls SkillInstall · skills CLI | 18,347 | MIT | ||
| codex-chatgpt-web Use ChatGPT Web (including Pro) as a native model in Codex — with context, tools, streaming and images, without using Codex quota. MCP server | 15,729 | — | ||
| awq-quantization Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on SkillInstall · skills CLI | 14,526 | MIT | ||
| constitutional-ai Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF SkillInstall · skills CLI | 14,526 | MIT | ||
| distributed-llm-pretraining-torchtitan Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek SkillInstall · skills CLI | 14,526 | MIT | ||
| evaluating-code-models Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, compari SkillInstall · skills CLI | 14,526 | MIT | ||
| evaluating-llms-harness Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, SkillInstall · skills CLI | 14,526 | MIT | ||
| fine-tuning-with-trl Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and SkillInstall · skills CLI | 14,526 | MIT | ||
| gguf-quantization GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing SkillInstall · skills CLI | 14,526 | MIT | ||
| gptq Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× me SkillInstall · skills CLI | 14,526 | MIT | ||
| grpo-rl-training Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training SkillInstall · skills CLI | 14,526 | MIT | ||
| hqq-quantization Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, SkillInstall · skills CLI | 14,526 | MIT | ||
| huggingface-tokenizers Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram al SkillInstall · skills CLI | 14,526 | MIT | ||
| implementing-llms-litgpt Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model SkillInstall · skills CLI | 14,526 | MIT | ||
| knowledge-distillation Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performanc SkillInstall · skills CLI | 14,526 | MIT | ||
| langchain Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integratio SkillInstall · skills CLI | 14,526 | MIT | ||
| llama-cpp Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when C SkillInstall · skills CLI | 14,526 | MIT | ||
| llamaguard Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, sel SkillInstall · skills CLI | 14,526 | MIT | ||
| llamaindex Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector in SkillInstall · skills CLI | 14,526 | MIT | ||
| long-context Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-1 SkillInstall · skills CLI | 14,526 | MIT | ||
| mamba-architecture State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware- SkillInstall · skills CLI | 14,526 | MIT | ||
| miles-rl-training Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, ne SkillInstall · skills CLI | 14,526 | MIT | ||
| model-merging Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-sp SkillInstall · skills CLI | 14,526 | MIT | ||
| model-pruning Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving SkillInstall · skills CLI | 14,526 | MIT | ||
| moe-training Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs SkillInstall · skills CLI | 14,526 | MIT | ||
| nanogpt Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpat SkillInstall · skills CLI | 14,526 | MIT | ||
| nemo-curator GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heu SkillInstall · skills CLI | 14,526 | MIT | ||
| nemo-evaluator-sdk Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable SkillInstall · skills CLI | 14,526 | MIT | ||
| nemo-guardrails NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, SkillInstall · skills CLI | 14,526 | MIT | ||
| nnsight-remote-interpretability Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to ru SkillInstall · skills CLI | 14,526 | MIT | ||
| openrlhf-training High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO- SkillInstall · skills CLI | 14,526 | MIT | ||
| optimizing-attention-flash Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long se SkillInstall · skills CLI | 14,526 | MIT | ||
| peft-fine-tuning Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when SkillInstall · skills CLI | 14,526 | MIT | ||
| prompt-guard Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). M SkillInstall · skills CLI | 14,526 | MIT | ||
| pyvene-interventions Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal SkillInstall · skills CLI | 14,526 | MIT | ||
| quantizing-models-bitsandbytes 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 SkillInstall · skills CLI | 14,526 | MIT | ||
| ray-data Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, T SkillInstall · skills CLI | 14,526 | MIT | ||
| rwkv-architecture RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux SkillInstall · skills CLI | 14,526 | MIT | ||
| sentence-transformers Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrie SkillInstall · skills CLI | 14,526 | MIT | ||
| sentencepiece Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), SkillInstall · skills CLI | 14,526 | MIT | ||
| serving-llms-vllm Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference lat SkillInstall · skills CLI | 14,526 | MIT | ||
| sglang Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflow SkillInstall · skills CLI | 14,526 | MIT | ||
| simpo-training Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No refere SkillInstall · skills CLI | 14,526 | MIT | ||
| slime-rl-training Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data gener SkillInstall · skills CLI | 14,526 | MIT | ||
| sparse-autoencoder-training Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable featu SkillInstall · skills CLI | 14,526 | MIT | ||
| speculative-decoding Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1. SkillInstall · skills CLI | 14,526 | MIT | ||
| tensorrt-llm Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when SkillInstall · skills CLI | 14,526 | MIT | ||
| torchforge-rl-training Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstract SkillInstall · skills CLI | 14,526 | MIT | ||
| training-llms-megatron Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parame SkillInstall · skills CLI | 14,526 | MIT | ||
| transformer-lens-interpretability Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and a SkillInstall · skills CLI | 14,526 | MIT | ||
| unsloth Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization SkillInstall · skills CLI | 14,526 | MIT | ||
| verl-rl-training Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL alg SkillInstall · skills CLI | 14,526 | MIT | ||
| minimax-multimodal-toolkit Use mmx to generate text, images, video, and speech, and to transcribe audio, via the MiniMax AI platform. Use when the user wants to create media con SkillInstall · skills CLI | 13,830 | MIT | ||
| typescript-sdk The official TypeScript SDK for Model Context Protocol servers and clients MCP server | 13,770 | — | ||
| gateway A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API. MCP server | 13,380 | — | ||
| fine-tuning-expert Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, prepa SkillInstall · skills CLI | 12,355 | MIT | ||
| rag-architect Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pi SkillInstall · skills CLI | 12,355 | MIT | ||
| fastapi_mcp Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth! MCP server | 12,031 | — | ||
| GhidraMCP MCP Server for Ghidra MCP server | 11,932 | — | ||
| pal-mcp-server The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as MCP server | 11,839 | — | ||
| CodeBurn AI coding spend, tokens and plan quotas across Claude Code, Codex, Cursor and 40+ more tools MCP serverGitHub-verified authorLocal · npm | 11,784 | MIT | ||
| hf-cli Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging F SkillInstall · skills CLI | 11,341 | Apache-2.0 | ||
| hf-mcp Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use G SkillInstall · skills CLI | 11,341 | Apache-2.0 | ||
| hf-mem Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub SkillInstall · skills CLI | 11,341 | Apache-2.0 | ||
| huggingface-best Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by SkillInstall · skills CLI | 11,341 | Apache-2.0 | ||
| huggingface-community-evals Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing SkillInstall · skills CLI | 11,341 | Apache-2.0 | ||
| huggingface-llm-trainer Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SkillInstall · skills CLI | 11,341 | Apache-2.0 | ||
| huggingface-local-models Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, SkillInstall · skills CLI | 11,341 | Apache-2.0 | ||
| huggingface-skills Build, train, evaluate, and use open source AI models, datasets, and spaces. PluginAnthropic marketplace | 11,341 | Apache-2.0 | ||
| huggingface-tool-builder Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially u SkillInstall · skills CLI | 11,341 | Apache-2.0 | ||
| huggingface-trackio Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostic SkillInstall · skills CLI | 11,341 | Apache-2.0 | ||
| huggingface-vision-trainer Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT SkillInstall · skills CLI | 11,341 | Apache-2.0 | ||
| train-sentence-transformers Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, c SkillInstall · skills CLI | 11,341 | Apache-2.0 | ||
| transformers-js Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, SkillInstall · skills CLI | 11,341 | Apache-2.0 | ||
| trl-training Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging trainin SkillInstall · skills CLI | 11,341 | Apache-2.0 | ||
| mcp-use The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents. MCP server | 10,965 | — | ||
| litert-lm Builds an Android app that runs an open text LLM on the device, on the CPU or the GPU, with the LiteRT-LM Kotlin API (com.google.ai.edge.litertlm:lite SkillInstall · skills CLI | 10,503 | Apache-2.0 | ||
| litert-runtime Configures and implements LiteRT (.tflite) on-device inference on Android in Kotlin using the CompiledModel API on CPU and GPU. Use this skill for any SkillInstall · skills CLI | 10,503 | Apache-2.0 | ||
| ml-kit-genai-prompt-api Analyzes Android codebases to implement ML Kit GenAI Prompt API. Use this skill to send natural language requests on-device to Gemini Nano, use struct SkillInstall · skills CLI | 10,503 | Apache-2.0 | ||
| add-byok-provider Add or maintain a built-in BYOK media provider in the OpenMotion repository, including official API research, credentials, model discovery, generation SkillInstall · skills CLI | 9,863 | Apache-2.0 | ||
| modelcontextprotocol Specification and documentation for the Model Context Protocol MCP server | 9,692 | — | ||
| bifrost Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, MCP server | 9,556 | — | ||
| expert-prompt-migrator 将任意专家/角色提示词规范化为可移植格式并迁移到任意 AI（DeepSeek、豆包、Kimi、Claude、Ollama 等）的实用工具。内置「清理平台语法 / 单专家单任务 / 补背景信息」三大原则、五段式提示词结构、迁移自检清单，以及 6 个原创领域专家示例（文案/简历/数据/法律/财务/英语） SkillInstall · skills CLI | 9,543 | — | ||
| mcp-go A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools. MCP server | 9,238 | — | ||
| ai-shaped-readiness-advisor Assess whether your product work is AI-first or AI-shaped. Use when evaluating AI maturity and choosing the next team capability to build. SkillInstall · skills CLI | 8,014 | — | ||
| ljg-word Deep-dive English word mastery tool. Deconstructs a single English word into core semantics and epiphany. Use when user asks to explain/master a speci SkillInstall · skills CLI | 7,740 | MIT | ||
| ljg-writes 写作引擎。把一个观点写成可理解、可迁移、经得住反例的 1000-1500 字中文文章。USE WHEN 写文章 OR 优化思想内容 OR 展开观点 OR 改写成逻辑递进的中文。NOT FOR 普通摘要、事实查询或结构风洞（用 ljg-structure）。 SkillInstall · skills CLI | 7,740 | MIT | ||
| ai-visibility-audit Audit how visible your brand is inside AI answers (ChatGPT, Claude, Gemini, Perplexity, AI Overviews). Claude builds a prompt panel for your category, SkillInstall · skills CLI | 7,542 | — | ||
| brand-answer-monitoring Track how AI assistants describe your brand over time and catch wrong, outdated, or damaging claims. Claude builds your monitoring prompt set, compare SkillInstall · skills CLI | 7,542 | — | ||
| citation-source-gap-finder Find the exact pages AI assistants cite when answering questions in your category, and identify which ones you can get into. Claude clusters the cited SkillInstall · skills CLI | 7,542 | — | ||
| content-aeo-optimizer Rewrite existing pages so AI assistants can extract, quote, and cite them. Claude restructures your content into answer-ready blocks — direct answers, SkillInstall · skills CLI | 7,542 | — | ||
| 0g-compute 0G Compute Network guide for decentralized AI inference, fine-tuning, and GPU services. Covers chatbots, image generation, speech-to-text, SDK integra SkillInstall · skills CLI | 7,120 | — | ||
| altllm-portal-api-keys Use this skill when the user asks to list, create, inspect, update, disable, re-enable, or revoke AltLLM Portal API keys for external agents or applic SkillInstall · skills CLI | 7,120 | — | ||
| altllm-portal-auth Use this skill when the user asks to log in or out with a wallet session, fetch a wallet sign-in challenge, verify an externally signed challenge, or SkillInstall · skills CLI | 7,120 | — | ||
| altllm-portal-cli Use this umbrella skill when the request spans multiple AltLLM Portal CLI domains, or when you need to navigate the local altllm CLI in this repositor SkillInstall · skills CLI | 7,120 | — | ||
| antseed-connect Connect coding agents, AI SDKs, and LLM tools to the AntSeed buyer proxy. Use when configuring Claude Code, Codex, OpenCode, Pi, OpenClaw, Hermes, Gen SkillInstall · skills CLI | 7,120 | — | ||
| chaingpt Build with the ChainGPT Web3 AI developer platform. Full API/SDK reference and project scaffolding for: Web3 AI Chatbot & LLM, AI NFT Generator, Smart SkillInstall · skills CLI | 7,120 | — | ||
| near-ai-cloud NEAR AI Cloud private inference and verification. Use when integrating NEAR AI Cloud API for verifiable private AI inference, verifying model or gatew SkillInstall · skills CLI | 7,120 | — | ||
| gemini-notebook-mcp-cli Programmatic access to Gemini Notebook - via command-line interface (CLI), Model Context Protocol (MCP) server, and AI agent skills. MCP server | 6,512 | — | ||
| add-provider Add a DeepChat LLM provider through explicit reviewed source changes. Use when a developer asks Codex to add a provider, provider profile, upstream pr SkillInstall · skills CLI | 6,390 | Apache-2.0 | ||
| deepchat 🐬DeepChat - A smart assistant that connects powerful AI to your personal world MCP server | 6,390 | Apache-2.0 | ||
| deepchat-cli Use DeepChat's bundled CLI control plane for model inference, image/video/speech generation, transcription, OCR, artifact inspection, public configura SkillInstall · skills CLI | 6,390 | Apache-2.0 | ||
| deepchat-sdd Use before substantial DeepChat code, configuration, documentation, test, build, feature, issue, refactor, or architecture changes that need a durable SkillInstall · skills CLI | 6,390 | Apache-2.0 | ||
| lemonade Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg MCP server | 6,212 | — | ||
| technology-selection Guides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET, Microsoft.Extensions.AI (MEAI), Microsoft A SkillInstall · skills CLI | 6,155 | MIT | ||
| improve-claude-md improve a CLAUDE.md file using <important if> blocks to improve instruction adherence SkillInstall · skills CLI | 5,773 | MIT | ||
| building-python-mcp-servers Builds robust Python MCP (Model Context Protocol) servers with FastMCP — tool design, error contracts, event-loop-safe blocking work, subprocess/CLI w SkillInstall · skills CLI | 5,372 | MIT | ||
| Pollinations Access Pollinations models and API capabilities through agent tools. MCP serverGitHub-verified authorRemoteSign-in needed | 5,294 | MIT | ||
| yichen-chatgpt-web-research Use the user's already signed-in official ChatGPT website account, especially GPT-5.5 Pro / ChatGPT Pro, to perform product research, market research, SkillInstall · skills CLI | 5,261 | — | ||
| yichen-codex-chatgpt Use the signed-in ChatGPT website in Chat UI Pro mode, never Work mode, to research, architect, and review one local project through a configured Secu SkillInstall · skills CLI | 5,261 | — | ||
| yichen-grok-consult Consult or search with xAI Grok from a GPT-led Codex conversation without switching the main model. Use when the user asks Grok to answer, review, cha SkillInstall · skills CLI | 5,261 | — | ||
| mcp Google 💚 MCP MCP server | 4,709 | — | ||
| deep-research Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server. MCP server | 4,686 | — | ||
| gemini-api-cli Call the Gemini API from the shell with gemini-api. Use for media generation (images, TTS, music, video), file and YouTube analysis, audio/video trans SkillInstall · skills CLI | 4,482 | Apache-2.0 | ||
| gemini-api-dev Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video gen SkillInstall · skills CLI | 4,482 | Apache-2.0 | ||
| gemini-live-api-dev Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) t SkillInstall · skills CLI | 4,482 | Apache-2.0 | ||
| gemini-omni-flash-api Use this skill for generative video editing, text-to-video, image- and video-referenced video generation, first-frame-to-video, first-and-last-frame t SkillInstall · skills CLI | 4,482 | Apache-2.0 | ||
| codex-subagent Launch OpenAI Codex CLI as a subagent (ChatGPT subscription auth, no API key). Use when delegating a self-contained coding task to Codex from another SkillInstall · skills CLI | 4,309 | MIT | ||
| fable-safe-prompt Make minimal prompt edits to reduce false-positive refusals from Fable. Use only when the user explicitly invokes /fable-safe-prompt. SkillInstall · skills CLI | 4,309 | MIT | ||
| kimi-review Launch an independent Kimi K3.1 Pro Max code review and return it verbatim, falling back across harnesses and routes until one works. Use for /kimi-re SkillInstall · skills CLI | 4,309 | MIT | ||
| muse-review Launch an independent Meta Muse Wonder Max code review through Pi and OpenRouter, and return it verbatim. Use for /muse-review, or when the user or an SkillInstall · skills CLI | 4,309 | MIT | ||
| openrouter Design, build, debug, and optimize OpenRouter API integrations. Use for any OpenRouter API work, including models, reasoning, routing, media, tools, s SkillInstall · skills CLI | 4,309 | MIT | ||
| total-review Run five independent max-effort reviews (Fable 5.1, Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, Muse Wonder), merge their findings, and fix only what the user SkillInstall · skills CLI | 4,309 | MIT | ||
| setup-pstack Configure which models pstack uses per role. Detects available models and writes the current runtime's override sheet. Use for /setup-pstack, "configu SkillInstall · skills CLI | 4,298 | MIT | ||
| dual-axis-skill-reviewer Review skills in any project using a dual-axis method: (1) deterministic code-based checks (structure, scripts, tests, execution safety) and (2) LLM d SkillInstall · skills CLI | 4,283 | MIT | ||
| edge-hint-extractor Extract edge hints from daily market observations and news reactions, with optional LLM ideation, and output canonical hints.yaml for downstream conce SkillInstall · skills CLI | 4,283 | MIT | ||
| edge-signal-aggregator Aggregate and rank signals from multiple edge-finding skills (edge-candidate-agent, theme-detector, sector-analyst, institutional-flow-tracker) into a SkillInstall · skills CLI | 4,283 | MIT | ||
| edge-strategy-reviewer Critically review strategy drafts from edge-strategy-designer for edge plausibility, overfitting risk, sample size adequacy, and execution realism. Us SkillInstall · skills CLI | 4,283 | MIT | ||
| exposure-coach Generate a one-page Market Posture summary with net exposure ceiling, growth-vs-value bias, participation breadth, and new-entry-allowed vs cash-prior SkillInstall · skills CLI | 4,283 | MIT | ||
| ftd-detector Detects Follow-Through Day (FTD) signals for market bottom confirmation using William O'Neil's methodology. Dual-index tracking (S&P 500 + NASDAQ) wit SkillInstall · skills CLI | 4,283 | MIT | ||
| futures-position-sizer Calculate contract-based futures position sizes from a direction, entry, and stop-loss, using verified per-symbol contract specs (multiplier, tick siz SkillInstall · skills CLI | 4,283 | MIT | ||
| ibd-distribution-day-monitor Detect IBD-style Distribution Days for QQQ/SPY (close down at least 0.2% on higher volume), track 25-session expiration and 5% invalidation, count d5/ SkillInstall · skills CLI | 4,283 | MIT | ||
| institutional-flow-tracker Use this skill to track institutional investor ownership changes and portfolio flows using 13F filings data. Analyzes hedge funds, mutual funds, and o SkillInstall · skills CLI | 4,283 | MIT | ||
| kanchi-dividend-review-monitor Monitor dividend portfolios with Kanchi-style forced-review triggers (T1-T5) and convert anomalies into OK/WARN/REVIEW states without auto-selling. Us SkillInstall · skills CLI | 4,283 | MIT | ||
| kanchi-dividend-sop Convert Kanchi-style dividend investing into a repeatable US-stock operating procedure. Use when users ask for かんち式配当投資, dividend screening, dividend SkillInstall · skills CLI | 4,283 | MIT | ||
| kanchi-dividend-us-tax-accounting Provide US dividend tax and account-location workflow for Kanchi-style income portfolios. Use when users ask about qualified vs ordinary dividends, 10 SkillInstall · skills CLI | 4,283 | MIT | ||
| macro-regime-detector Detect structural macro regime transitions (1-2 year horizon) using cross-asset ratio analysis. Analyze RSP/SPY concentration, yield curve, credit con SkillInstall · skills CLI | 4,283 | MIT | ||
| manifoldbt-backtester Runs a declarative strategy spec over OHLCV bars with the manifoldbt Rust engine, pairs the fill log into round trips, and emits the eight inputs the SkillInstall · skills CLI | 4,283 | MIT | ||
| market-breadth-analyzer Quantifies market breadth health using TraderMonty's public CSV data. Generates a 0-100 composite score across 6 components (100 = healthy). No API ke SkillInstall · skills CLI | 4,283 | MIT | ||
| market-top-detector Assesses heuristic market top risk using O'Neil Distribution Days, Minervini Leading Stock Deterioration, and Monty Defensive Sector Rotation. Generat SkillInstall · skills CLI | 4,283 | MIT | ||
| Rapid-MLX Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable to MCP server | 4,145 | — | ||
| accelerated-computing-cudf Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable seman SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| boltz2-nim Use Boltz2 NIM for biomolecular structure prediction and binding affinity. Invoke for Boltz2, protein structures, protein-ligand/DNA/RNA complexes, SM SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| codonfm-embed Validate coding-sequence CSVs, extract public CodonFM/Encodon embeddings, and choose checkpoints for downstream property modeling. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| codonfm-finetune Fine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning. Use when a SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| codonfm-score Validate, prepare, or run public CodonFM Encodon masked-codon variant scoring and review compatibility of its scoring workflows. Use only when the use SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| codonfm-setup Set up the public CodonFM v1 repository and download public Encodon checkpoints. Use for requests to build or launch the CodonFM development container SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| complexa-evaluate-pdbs Agent runbook for evaluating an existing PDB directory through the separately installed first-party Proteina-Complexa CLI. Use to refold or score desi SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| complexa-sweep Agent runbook for Proteina-Complexa parameter sweeps through the separately installed first-party CLI and config generator. Use for cartesian-product SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| complexa-target Add, edit, inspect, or validate Proteina-Complexa target definitions for protein binders, ligand binders, and AME motif scaffolding. Use for target re SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| cuequivariance Use when defining cuEquivariance groups and irreps, building equivariant tensor products, or validating segmented polynomials with NumPy. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| cuequivariance-jax Use when writing or debugging cuEquivariance JAX polynomials, irrep dictionaries, Flax NNX layers, or CPU/CUDA execution and layouts. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| cuequivariance-torch Use when building or debugging cuEquivariance PyTorch tensor products or equivariant GNNs, especially CPU references, layouts, indexing, and gradients SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| diffdock-nim Run DiffDock molecular docking via NVIDIA NIM to predict small-molecule binding poses against protein targets. Use for DiffDock, molecular docking, li SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| digital-health-clinical-asr-build Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use /digital-h SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| digital-health-clinical-asr-eval Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva- SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| digital-health-clinical-asr-finetune Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT f SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| digital-health-clinical-asr-setup Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| drug-discovery-pipeline NOTE: molecule and target inputs and your NGC_API_KEY are transmitted to external NVIDIA-hosted API endpoints on every call. Use local NIM containers SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| evo2-nim Generate and analyze DNA sequences using NVIDIA's Evo 2 BioNeMo NIM microservice. Use for Evo2/Evo 2, DNA generation, genomic sequence generation, hos SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| genmol-nim Generate novel drug-like molecules using the GenMol NIM microservice. Use for de novo generation, scaffold decoration, motif extension, lead optimizat SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| isaac-cable-insertion-policy-training Set up the standalone IsaacLabTraining package from NVIDIA-ISAAC-ROS/isaac_ros_manipulation, then launch, monitor, resume, evaluate, and tune DisplayP SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| jetson-inference-mem-tune Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| jetson-llm-benchmark Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| jetson-llm-serve Stand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on older Orin. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| medtech-model-evidence-export Exports sanitized metadata, parameters, reproducibility details, quality metrics, and optional review artifacts from Medical AI inference runs or evid SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-activation-recompute Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. Use for activatio SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-cpu-offloading Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridD SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-cuda-graphs Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-expert-parallel-overlap Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and fl SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-hierarchical-context-parallel Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-megatron-fsdp Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-memory-tuning Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation recomput SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-moe-comm-overlap MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-moe-dispatcher-selection Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-moe-hardware-configs Representative, point-in-time MoE training playbooks by hardware and model family. Use them as candidate seeds, then revalidate the exact runtime, sem SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-moe-long-context Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Q SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-moe-optimization-workflow Evidence-gated workflow for MoE performance optimization in Megatron Bridge. Covers measurement contracts, the Three Walls framework, parallel folding SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-moe-vlm-training Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-parallelism-strategies Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combine SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-sequence-packing Validate and use packed sequences and long-context training in Megatron-Bridge, including offline LLM packing, collate-time VLM packing, Energon onlin SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-perf-tp-dp-comm-overlap Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verificati SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-recipe-recommender Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemo-mbridge-resiliency Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemotron-asr-finetune Orchestration skill for NVIDIA Nemotron Speech (Riva) / NeMo ASR domain and language adaptation. Given a goal like "improve/fine-tune ASR for my domai SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemotron-customize Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoMod SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemotron-policy-generator Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotr SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemotron-retrieval-recipes Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemotron-speech Routes NVIDIA Nemotron Speech (Formerly Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nemotron-voice-agent-builder Create, refine, or fix NVIDIA voice agents (Cascaded or Omni) with Pipecat or LiveKit. Use when building, scaffolding, or iterating on a real-time voi SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nv-generate-mr-brain-finetune Used for finetuning NV-Generate-CTMR MR-Brain v1 for T1, T2, FLAIR, SWI, or MRA data from a NIfTI datalist. Not for clinical or production data approv SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nv-generate-vae-finetune Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists. Not for clinical or production data approval. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nv-reason-ct Run NV-Reason-CT inference on user-provided 3D NIfTI chest or abdominal CT volumes for engineering and research workflows. Not for diagnosis, treatmen SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nv-reason-cxr Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests. Not for diagnosis or clinical reporting. SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nv-segment-ct-finetune Runs standard or fixed-channel softmax finetuning of NV-Segment-CT VISTA3D on CT NIfTI image/label datasets, with optional MONAI-native MLflow trackin SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nvidia-skill-finder Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, soft SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| nvidia-skills Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, an PluginAnthropic marketplace | 3,954 | Apache-2.0 | ||
| agentica-claude-proxy Guide for integrating Agentica SDK with Claude Code CLI proxy SkillInstall · skills CLI | 3,949 | MIT | ||
| agentica-server Agentica server + Claude proxy setup - architecture, startup sequence, debugging SkillInstall · skills CLI | 3,949 | MIT | ||
| braintrust-analyze Analyze Claude Code sessions via Braintrust SkillInstall · skills CLI | 3,949 | MIT | ||
| braintrust-tracing Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging SkillInstall · skills CLI | 3,949 | MIT | ||
| cli-reference Claude Code CLI commands, flags, headless mode, and automation patterns SkillInstall · skills CLI | 3,949 | MIT | ||
| math Unified math capabilities - computation, solving, and explanation. I route to the right tool. SkillInstall · skills CLI | 3,949 | MIT | ||
| trace-claude-code Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical t SkillInstall · skills CLI | 3,949 | MIT | ||
| cs-foundations Master discrete mathematics, logic, formal proofs, and computational thinking. Build the mathematical foundation for all computer science. SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| dialectic Minimal compatibility wrapper for vibe Dialectic Mode (multi-perspective design analysis). SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| LQF_Machine_Learning_Expert_Guide LQF Machine Learning Expert Guide - Routed skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on: machine learning, modeling, p SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| MCP Integration 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 Context P SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| prompt-lookup Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, ret SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| pymc-bayesian-modeling Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic p SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| pytorch-lightning Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelin SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| senior-computer-vision World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOL SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| senior-data-scientist World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expertise in Python (NumPy, Pandas SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| senior-ml-engineer World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deplo SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| shap Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model prediction SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| stable-baselines3 Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| timesfm-forecasting Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor r SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| torch-geometric Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| transformers This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal task SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| umap-learn UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMA SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| java-sdk The official Java SDK for Model Context Protocol servers and clients. Maintained in collaboration with Spring AI MCP server | 3,768 | — | ||
| scenario Use when connecting an AI agent to Scenario (scenario.com) through MCP, or when a task involves generating images, video, 3D, audio, sprites, textures SkillInstall · skills CLI | 3,764 | MIT | ||
| scenario-model-comparison Use when comparing Scenario models on the same brief through MCP: a bake-off with shared prompts and inputs, cost, generation time and quality measure SkillInstall · skills CLI | 3,764 | MIT | ||
| scenario-model-training Use when generated assets must keep a consistent style, character, or product look and references stop scaling, or when a user asks to train a custom SkillInstall · skills CLI | 3,764 | MIT | ||
| scenario-moderation Use when a Scenario generation is blocked, refused, or returns a moderation or sensitive-content error, when a video is rejected after rendering or it SkillInstall · skills CLI | 3,764 | MIT | ||
| scenario-quality-gate Use when a generated Scenario image needs a quality check or a brand-brief compliance verdict before it ships: pass/warn/fail scoring, on-brand review SkillInstall · skills CLI | 3,764 | MIT | ||
| scenario-refine-loop Use when a Scenario output must be checked and improved rather than accepted first roll: iterating a generation until it matches the brief, fixing a b SkillInstall · skills CLI | 3,764 | MIT | ||
| pinme-llm Use this skill when a PinMe project (Worker TypeScript) needs to call OpenRouter-backed LLM APIs, including models, chat/completions, streaming, or Op SkillInstall · skills CLI | 3,760 | MIT | ||
| hexanon-x402-apis Pay-per-call access to the Hexanon family of eight x402 APIs for autonomous agents — no signup, no API keys, USDC on Base. Covers US/Canada vehicle & SkillInstall · skills CLI | 3,743 | MIT |
Filters apply to the top 400 of 2,295 tools by stars. Full list for agents: ai-models.json