AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
crestapps Bundle Orchardcore AI Chat InteractionsSkill for configuring AI Chat Interactions in Orchard Core with CrestApps modules. Covers ad-hoc chat sessions, document upload with RAG support, deployment settings, system tools for image and chart generation, and SignalR chat methods. Use it for CrestApps.OrchardCore.AI.Chat.Interactions, CrestApps.OrchardCore.AI.Documents.ChatInteractions, current AI data sources, and related Orchard Core setup, extension, or troubleshooting work.
- crestapps Skill Orchardcore AI Response Handlers
Skill for implementing CrestApps chat response handlers in Orchard Core. Covers IChatResponseHandler, streaming and deferred results, external relay contracts, notifications, and handler registration. Use this skill when requests mention Orchard Core Chat Response Handlers, IChatResponseHandler, ChatResponseHandlerResult, streaming responses, deferred chat replies, IExternalChatRelay, ChatNotification, or live-agent handoff.
-
bookforge-ai Bundle Research Introduction ArchitectDraft a complete research introduction and matching conclusion using the Context→Problem→Response architecture. Use this skill when the user has a framed research problem (condition + consequence) and needs to write or revise the opening and closing sections of a research paper; when an introduction exists but reads as a flat topic announcement instead of a problem-driven argument; when the user cannot decide whether to state the main point in the introduction (point-first) or withhold it for the conclusion (point-last) and needs to understand the trade-offs; when the first sentence of the introduction is a dictionary definition, a grand universal claim ("Throughout history…"), or a repetition of the assignment prompt; when the conclusion merely restates the introduction without adding new significance or calling for further research; when the user needs guidance on how much context to provide — neither too sketchy nor encyclopedic — based on the audience's prior knowledge; when the pacing of an introduction
- crestapps Skill Orchardcore AI Documents Elasticsearch
Skill for indexing CrestApps Orchard Core AI Documents with Elasticsearch. Covers Elasticsearch index profiles, dense vector chunk mappings, k-nearest-neighbor retrieval, default search fields, and scoped RAG results. Use this skill when requests mention AI Documents Elasticsearch, AIDocumentElasticsearchIndexProfileHandler, ElasticsearchVectorSearchService, document vector indexing, or Elasticsearch document retrieval. Strong matches include work with CrestApps.OrchardCore.AI.Documents.Elasticsearch, IVectorSearchService, IDocumentIndexHandler, AddElasticsearchIndexingSource, ElasticsearchIndexMetadata, and AIConstants.AIDocumentsIndexingTaskType.
-
aradotso-trending-skills Skill Omnivoice TtsExpert skill for OmniVoice, a massively multilingual zero-shot TTS model supporting 600+ languages with voice cloning and voice design capabilities.
- aradotso-trending-skills Skill LLM Wiki Skill
Build and maintain a personal knowledge base using Karpathy's llm-wiki methodology across Claude Code, Codex, and OpenClaw agents.
- aradotso-trending-skills Skill Stash AI Memory
Persistent memory layer for AI agents using Postgres/pgvector with MCP server support
- aradotso-trending-skills Skill Deepclaude Proxy
Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend at up to 17x lower cost.
- aradotso-trending-skills Skill Freellmapi Proxy
OpenAI-compatible proxy aggregating 14 free-tier LLM providers with automatic failover and per-key rate tracking.
- aradotso-trending-skills Skill Nano World Model
Minimalist batteries-included repository for training, evaluating, and deploying diffusion-forcing video world models for robot manipulation, gaming, and MPC planning.
- aradotso-trending-skills Skill Claw Code Harness
Better Harness Tools for Claude Code — a Python (and in-progress Rust) rewrite of the Claude Code agent harness, with CLI tooling for manifest inspection, parity auditing, and tool/command inventory.
- aradotso-trending-skills Skill Crabtrap LLM Proxy
LLM-as-a-judge HTTP/HTTPS proxy that secures AI agents by intercepting and evaluating outbound requests against security policies before they reach external APIs.
- aradotso-trending-skills Skill Future Agi Platform
Expert skill for using Future AGI — the open-source end-to-end platform for evaluating, observing, and improving LLM and AI agent applications with tracing, evals, simulations, datasets, gateway, and guardrails.
- aradotso-trending-skills Skill Phantom AI Coworker
AI co-worker agent with its own computer, persistent memory, self-evolution, MCP server, and Slack/email identity built on Claude Agent SDK
- aradotso-trending-skills Skill Wanman Agent Matrix
Expert skill for using wanman, the open-source local agent matrix runtime that coordinates multiple Claude Code or Codex agents on your machine.
- aradotso-trending-skills Skill Codesight AI Context
Universal AI context generator that compiles codebase maps, wiki knowledge bases, and MCP tools to save thousands of tokens per AI conversation.
- aradotso-trending-skills Skill Moss Tts Nano Speech
Expert skill for using MOSS-TTS-Nano, a 0.1B parameter multilingual real-time TTS model that runs on CPU with voice cloning support.
- aradotso-trending-skills Skill Openclaude Multi LLM
Use Claude Code's full tool system with any OpenAI-compatible LLM — GPT-4o, DeepSeek, Gemini, Ollama, and 200+ models via environment variable configuration.
-
oimiragieo Bundle Pymc Bayesian ModelingBayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.
0 - oimiragieo Bundle Shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.
0 - aradotso-trending-skills Skill Club 3090 LLM Serving
Recipes and configs for serving LLMs locally on RTX 3090 GPUs using vLLM, llama.cpp, and SGLang with OpenAI-compatible API
- aradotso-trending-skills Skill Openai Privacy Filter
OpenAI Privacy Filter — bidirectional token-classification model for PII detection and masking in text
- aradotso-trending-skills Skill Pyre Code Ml Practice
Self-hosted ML coding practice platform with 68 problems covering Transformers, diffusion, RLHF, and more — instant browser feedback, no GPU required.
- aradotso-trending-skills Skill Clawd Code Python Port
Python port of Claude Code agent harness — tools, commands, task orchestration, and CLI entrypoint via oh-my-codex
- aradotso-trending-skills Skill Gemma Tuner Multimodal
Fine-tune Gemma 4 and 3n models with audio, images, and text on Apple Silicon using PyTorch and Metal Performance Shaders.
- aradotso-trending-skills Skill Karpathytalk Community
Run and interact with KarpathyTalk, an open markdown-based developer social network with GitHub auth, SQLite, and an LLM-friendly JSON/markdown API.
- aradotso-trending-skills Skill Talk Normal LLM Prompt
System prompt toolkit that removes AI slop and makes any LLM respond like a normal person — concise, direct, no filler.
- aradotso-trending-skills Skill Tiangolo Library Skills
Install and manage AI agent skills from Python/JS libraries so agents always use up-to-date patterns
- aradotso-trending-skills Skill Tilekernels Gpu Kernels
Expert skill for using TileKernels, a library of optimized GPU kernels for LLM operations (MoE routing, quantization, transpose, engram gating, Manifold HyperConnection) built with TileLang.
- aradotso-trending-skills Skill Claude Code Source Study
Deep dive into Claude Code source code to learn production-grade AI agent architecture patterns
- aradotso-trending-skills Skill Flashkda Delta Attention
High-performance Kimi Delta Attention CUDA kernels built on CUTLASS for efficient recurrent state inference
- aradotso-trending-skills Skill Clawgod Claude Code Patch
Runtime patch for Claude Code that unlocks hidden features, removes restrictions, and enables advanced capabilities like multi-agent swarms and computer use.
- oimiragieo Bundle Pathml
Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler.
0 - aradotso-trending-skills Skill Kwcode Local Coding Agent
KWCode (天工开物) — a CLI coding agent optimized for local open-source models (8B-30B), featuring deterministic expert pipelines, BM25+AST code location, runtime debugging, and a self-improving flywheel — all running fully offline.
- aradotso-trending-skills Skill Meta Harness Optimization
Framework for automated search over task-specific model harnesses — the code around a fixed base model that decides what to store, retrieve, and show while the model works.
- aradotso-trending-skills Skill Serve Sim Apple Simulator
Host Apple iOS Simulators in the browser with MJPEG streaming, touch/gesture control, and AI agent integration via npx serve-sim.
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include research-introduction-architect, orchardcore-ai-chat-interactions, orchardcore-ai-response-handlers. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.