Skills · category
AI & agents skills and plugins
Public Claude skills and plugins for ai & agents, each with Waxell's security verdict and the findings behind it.
- 9,580 reviewed
- 8,092 no issues
- 1,316 to review
- 130 high risk
1,451 resultsAI & agents
peft-fine-tuningorchestra-researchParameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU… Review findingsAI & agentsResearch14k- unslothorchestra-researchExpert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization High riskAI & agentsResearch14k
- nnsight-remote-interpretabilityorchestra-researchProvides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when… Review findingsAI & agentsResearch14k
- pyvene-interventionsorchestra-researchProvides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when… Review findingsAI & agentsResearch14k
- sparse-autoencoder-trainingorchestra-researchProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into… Review findingsAI & agentsResearch14k
- transformer-lens-interpretabilityorchestra-researchProvides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via… Review findingsAI & agentsResearch14k
- grpo-rl-trainingorchestra-researchExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training No issuesAI & agentsResearch14k
- miles-rl-trainingorchestra-researchProvides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with… No issuesAI & agentsResearch14k
- openrlhf-trainingorchestra-researchHigh-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray,… No issuesAI & agentsResearch14k
- simpo-trainingorchestra-researchSimple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval… Review findingsAI & agentsResearch14k
- slime-rl-trainingorchestra-researchProvides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing… No issuesAI & agentsResearch14k
- torchforge-rl-trainingorchestra-researchProvides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean… No issuesAI & agentsResearch14k
- fine-tuning-with-trlorchestra-researchFine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward… Review findingsAI & agentsResearch14k
- verl-rl-trainingorchestra-researchProvides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or… Review findingsAI & agentsResearch14k
- constitutional-aiorchestra-researchAnthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with… No issuesAI & agentsResearch14k
- llamaguardorchestra-researchMeta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons,… Review findingsAI & agentsResearch14k
- nemo-guardrailsorchestra-researchNVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking,… Review findingsAI & agentsResearch14k
- huggingface-accelerateorchestra-researchSimplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP.… Review findingsAI & agentsResearch14k
- deepspeedorchestra-researchExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam,… Review findingsAI & agentsResearch14k
- training-llms-megatronorchestra-researchTrains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training… Review findingsAI & agentsResearch14k
- pytorch-fsdp2orchestra-researchAdds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed… No issuesAI & agentsResearch14k
- pytorch-lightningorchestra-researchHigh-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal… Review findingsAI & agentsResearch14k
- ray-trainorchestra-researchDistributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in… Review findingsAI & agentsResearch14k
- lambda-labs-gpu-cloudorchestra-researchReserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH… High riskAI & agentsResearch14k
- modal-serverless-gpuorchestra-researchServerless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management,… Review findingsAI & agentsEngineering14k
- skypilot-multi-cloud-orchestrationorchestra-researchMulti-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across… Review findingsAI & agentsResearch14k
- awq-quantizationorchestra-researchActivation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models… Review findingsAI & agentsResearch14k
- quantizing-models-bitsandbytesorchestra-researchQuantizes 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… Review findingsAI & agentsResearch14k
- optimizing-attention-flashorchestra-researchOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers… Review findingsAI & agentsResearch14k
- gguf-quantizationorchestra-researchGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or… Review findingsAI & agentsResearch14k
- hqq-quantizationorchestra-researchHalf-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing… Review findingsAI & agentsData & analytics14k
- evaluating-code-modelsorchestra-researchEvaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code… Review findingsAI & agentsEngineering14k
- nemo-evaluator-sdkorchestra-researchEvaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when… Review findingsAI & agentsEngineering14k
- llama-cpporchestra-researchRuns LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel… No issuesAI & agentsResearch14k
- sglangorchestra-researchFast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding,… Review findingsAI & agentsResearch14k
- tensorrt-llmorchestra-researchOptimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs… No issuesAI & agentsResearch14k
- mlfloworchestra-researchTrack ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow -… Review findingsAI & agentsResearch14k
- weights-and-biasesorchestra-researchTrack ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model… Review findingsAI & agentsResearch14k
- evolving-ai-agentsorchestra-researchProvides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when… Review findingsAI & agentsResearch14k
- faissorchestra-researchFacebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and… Review findingsAI & agentsResearch14k
- pineconeorchestra-researchManaged vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata… Review findingsAI & agentsResearch14k
- qdrant-vector-searchorchestra-researchHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast… Review findingsAI & agentsResearch14k
- dspyorchestra-researchBuild complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy -… Review findingsAI & agentsResearch14k
- outlinesorchestra-researchGuarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers,… Review findingsAI & agentsResearch14k
- audiocraft-audio-generationorchestra-researchPyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music… Review findingsAI & agentsImages, video & audio14k
- blip-2-vision-languageorchestra-researchVision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question… Review findingsAI & agentsResearch14k
- cliporchestra-researchOpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval.… Review findingsAI & agentsResearch14k
- segment-anything-modelorchestra-researchFoundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or… Review findingsAI & agentsResearch14k
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF