Data Science & ML Agent Skills
Compare the best open-source agent skills for data science & ML. Models, RAG pipelines, embeddings and datasets. Ranked by GitHub stars, with install commands, what each one can touch and scan reports where available.
Elephant Goldfish Model
Open-source skills for designing and reviewing software with AI agents
Datamodel Code Generator
Generate Pydantic v2 models, dataclasses, TypedDict, and msgspec.Struct from OpenAPI, JSON Schema, GraphQL, Avro, Protobuf, and raw JSON/YAML/CSV.
Knowhere
Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.
J Space Cognition Suite
J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research.
Fable Method
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
Dstack
A unified orchestration layer for heterogeneous AI compute. It standardizes how to manage compute and run training and inference on GPU clouds, Kubernetes, VMs, or bare-metal clusters.
Synthadoc
Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.
Cc Thinking Skills
28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools
Wesight
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.
Opencode Power Pack
55 rigorous skills for Claude Code, Codex, OpenCode 1 and 2, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more.
Compose Skill
Compose Skill (Compose Kit): agent skills for Jetpack Compose & Compose Multiplatform. Makes Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode write better Compose: MVI, Koin, Navigation 3, Ktor, Room. Tested blind on 5 models in 120 agentic runs.
Grace Marketplace
GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with semantic markup, knowledge graphs, and support for Claude Code, Codex CLI, and Kilo Code.
REA Reconstruction Companion
Open-source, model-independent Agent Skill for evidence-based software reconstruction with REA. Optional integration, portable installer, and validation workflows.
Great Cto
You already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.
Weaviate Claude Skills
Claude Skills for connecting Claude.ai to local Weaviate vector databases - manage collections, ingest data, and query with RAG
Claude Rag Skills
Professional RAG development skills for Claude Code - audit, evaluate, optimize, and scaffold RAG pipelines
Claude Skills Mental Models
Mental models as files an agent reads — bring your own, or start with 21 sourced ones. An Open Knowledge Format bundle + Claude Code skill.
List refreshed November 15, 2026. Data comes from public GitHub repositories.