Skills · category
Engineering skills and plugins
Public Claude skills and plugins for engineering, each with Waxell's security verdict and the findings behind it.
- 11,535 reviewed
- 8,333 no issues
- 2,885 to review
- 229 high risk
2,738 resultsEngineering
nanogptorchestra-researchEducational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By… Review findingsEngineeringResearch14k- huggingface-tokenizersorchestra-researchFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece,… Review findingsEngineeringResearch14k
- llama-factoryorchestra-researchExpert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support No issuesEngineeringResearch14k
- pyvene-interventionsorchestra-researchProvides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when… Review findingsEngineeringResearch14k
- llamaguardorchestra-researchMeta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons,… Review findingsEngineeringResearch14k
- prompt-guardorchestra-researchMeta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast… Review findingsEngineeringResearch14k
- huggingface-accelerateorchestra-researchSimplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP.… Review findingsEngineeringResearch14k
- pytorch-lightningorchestra-researchHigh-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal… Review findingsEngineeringResearch14k
- modal-serverless-gpuorchestra-researchServerless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management,… Review findingsEngineeringResearch14k
- gguf-quantizationorchestra-researchGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or… Review findingsEngineeringResearch14k
- gptqorchestra-researchPost-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when… Review findingsEngineeringResearch14k
- ml-training-recipesorchestra-researchBattle-tested PyTorch training recipes for all domains, LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics,… No issuesEngineeringResearch14k
- evaluating-code-modelsorchestra-researchEvaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code… Review findingsEngineeringAI & agents14k
- evaluating-llms-harnessorchestra-researchEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality,… Review findingsEngineeringResearch14k
- nemo-evaluator-sdkorchestra-researchEvaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when… Review findingsEngineeringResearch14k
- tensorrt-llmorchestra-researchOptimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs… No issuesEngineeringResearch14k
- serving-llms-vllmorchestra-researchServes LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing… Review findingsEngineeringResearch14k
- mlfloworchestra-researchTrack ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow -… Review findingsEngineeringResearch14k
- tensorboardorchestra-researchVisualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with… Review findingsEngineeringData & analytics14k
- autogpt-agentsorchestra-researchAutonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent… No issuesEngineeringResearch14k
- langchainorchestra-researchFramework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google),… Review findingsEngineeringResearch14k
- qdrant-vector-searchorchestra-researchHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast… Review findingsEngineeringResearch14k
- dspyorchestra-researchBuild complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy -… Review findingsEngineeringResearch14k
- guidanceorchestra-researchControl LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step… Review findingsEngineeringResearch14k
- instructororchestra-researchExtract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type… Review findingsEngineeringResearch14k
- outlinesorchestra-researchGuarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers,… Review findingsEngineeringResearch14k
- langsmith-observabilityorchestra-researchLLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against… Review findingsEngineeringResearch14k
- phoenix-observabilityorchestra-researchOpen-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed… Review findingsEngineeringResearch14k
- fine-tuning-openvla-oftorchestra-researchFine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation,… Review findingsEngineeringResearch14k
- knowledge-distillationorchestra-researchCompress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with… Review findingsEngineeringResearch14k
- model-mergingorchestra-researchMerge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by… Review findingsEngineeringProductivity14k
- speculative-decodingorchestra-researchAccelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing… Review findingsEngineeringResearch14k
- ara-compilerorchestra-researchCompiles any research input: PDF papers, GitHub repositories, experiment logs, code directories, or raw notes, into a complete… No issuesEngineeringResearch14k
- ara-research-managerorchestra-researchRecords research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract… No issuesEngineeringResearch14k
pr-reviewminimax-aiReview pull requests for the MiniMax Skills repository. Use when reviewing PRs, validating new skill submissions, or checking existing… No issuesEngineeringLegal & compliance14k- slide-making-skillminimax-aiImplement single-slide PowerPoint pages with PptxGenJS. Use when writing or fixing slide JS files: dimensions, positioning,… Review findingsEngineeringDocuments14k
- minimax-skillsminimax-aiMiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal… Review findingsEngineeringDocuments14k
- buddy-singsminimax-aiUse when user wants their Claude Code pet (/buddy) to sing a song. Triggers on any request that combines the concept of their Claude Code… Review findingsEngineeringImages, video & audio14k
- flutter-devminimax-aiFlutter cross-platform development guide covering widget patterns, Riverpod/Bloc state management, GoRouter navigation, performance… No issuesEngineeringDesign14k
- frontend-devminimax-aiFull-stack frontend development combining premium UI design, cinematic animations, AI-generated media assets, persuasive copywriting, and… Review findingsEngineeringImages, video & audio14k
- fullstack-devminimax-aiFull-stack backend architecture and frontend-backend integration guide. TRIGGER when: building a full-stack app, creating REST API with… No issuesEngineeringDesign14k
- ios-application-devminimax-aiiOS application development guide covering UIKit, SnapKit, and SwiftUI. Includes touch targets, safe areas, navigation patterns, Dynamic… No issuesEngineeringDesign14k
- minimax-docxminimax-aiProfessional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from… No issuesEngineeringDocuments14k
- mmx-climinimax-aiUse mmx to generate text, images, video, speech, and music via the MiniMax AI platform. Use when the user wants to create media content,… Review findingsEngineeringImages, video & audio14k
- react-native-devminimax-aiReact Native and Expo development guide covering components, styling, animations, navigation, state management, forms, networking,… High riskEngineeringDesign14k
web-design-engineerconardliBuild or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks,… No issuesEngineeringDesign14k
angular-architectjeffallanGenerates Angular 17+ standalone components, configures advanced routing with lazy loading and guards, implements NgRx state management,… No issuesEngineeringWriting & content12k- api-designerjeffallanUse when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invoke for resource modeling,… No issuesEngineeringDesign12k
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