Data and AI

13,567 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

chroma

241

AlexAI-MCP/hermes-CCC

Skill Claude CodeCodex

Open-source embedding database for RAG — store embeddings, vector search, metadata filtering. Simple API, scales from notebook to production.

not rated 134 5mo ago A 29 tokens

local-rag-search

242

nkapila6/mcp-local-rag

Skill Claude CodeCodex

Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of…

not rated 134 7d ago A 80 tokens original MIT

code_interpreter

243

wanmol/goal-flow

Skill Claude CodeCodex

A tool for running Python code in an isolated environment. Python is a programming language often used for calculations, data processing, file-format conversion, and preparing chart data.

not rated 133 +2 24d ago A 42 tokens original MIT

keirouter

244

mydisha/keirouter

Skill Claude CodeCodex

Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions KeiRouter, KEIROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant…

not rated 130 +1 10d ago A 82 tokens original MIT

neurolink-guide

245

juspay/neurolink

Skill Claude Code

Guide for using the NeuroLink SDK and CLI. Invoke when users ask how to use neurolink, integrate AI providers, add MCP tools, configure RAG, set up memory, deploy servers, or work with multimodal content. Covers SDK, CLI, providers, tools, and enterprise features.

not rated 129 +1 yesterday A 65 tokens original MIT

model-shelf

246

alexziskind1/model-shelf

Plugin Claude Code

Bundles 1 skill, 1 hook · 66 tokens together

Local-first resolver for Hugging Face models (GGUF, MLX, safetensors). The agent checks your own storage and any mounted drives before downloading anything.

not rated 129 5d ago A tokens not measured original MIT

rt22766/claude-skill-model-fingerprint

Skill Claude CodeCodex

A check for whether an API is really serving a Claude model rather than a model with an unclear source or a third-party wrapper. It can run quick checks and, when needed, a deeper review of identity, tools, metadata, and nested responses.

not rated 128 5mo ago A 83 tokens

openzim-mcp

248

cameronrye/openzim-mcp

MCP server Claude CodeCodexCursor +2

OpenZIM MCP - ZIM MCP Server that enables AI models to access and search ZIM format knowledge bases offline. Runs locally from the openzim-mcp Python package. Needs 1 environment variable to run.

not rated 128 +1 3d ago A tokens not measured original MIT

lazyFrogLOL/Harness_Engineering

Skill Claude CodeCodex

This skill provides guidance for implementing tensor parallelism in PyTorch, specifically column-parallel and row-parallel linear layers. Use when implementing distributed neural network layers that split weights/activations across multiple ranks, working with torch.distributed for model parallelism, or implementing…

not rated 126 3mo ago A 69 tokens

prompt-engineering

251

TanShilongMario/PromptSkill4image

Skill Claude CodeCodex

Advanced image prompt engineering assistant for Chinese-first users. Turns any input into high-quality image-generation prompts: reverse-engineers prompts from images, expands rough prompts into structured prompts, translates/transwrites prompts, extracts reusable variables, suggests phrase banks, supports minimal…

not rated 125 3mo ago A 63 tokens original MIT

early-experience-data

252

OSU-NLP-Group/EarlyExperience

Skill Claude CodeCodex

Use this skill whenever the user asks to generate, collect, inspect, or prepare early-experience training data (Implicit World Modeling or Self-Reflection, in the sense of arXiv:2510.08558) for an agent environment. Trigger phrases include "rollout", "collect expert trajectories", "generate reflection", "smoke test…

not rated 124 2mo ago A 125 tokens original MIT

andrej-karpathy

253

henryalouf/ruflow

Skill Claude CodeCodex

Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo.

not rated 123 +3 3mo ago A 47 tokens original MIT

altimate-code

254

AltimateAI/data-engineering-skills

Skill Claude CodeCodex

Delegates dbt and warehouse work to altimate-code, a specialized CLI agent with 100+ purpose-built data tools. USE THIS SKILL FIRST whenever the task mentions or implies: warehouse access (Snowflake, BigQuery, Redshift, Databricks, Postgres, MySQL, DuckDB), column-level lineage, downstream-impact analysis, dbt builds…

not rated 122 1mo ago A 0 tokens original MIT

dspy-skills

255

OmidZamani/dspy-skills

Plugin Claude Code

Bundles 24 skills · 860 tokens together

Collection of 22 focused skills for building, optimizing, evaluating, and deploying DSPy applications.

not rated 122 2mo ago A tokens not measured original MIT

code-graph-rag-mcp

256

er77/code-graph-rag-mcp

MCP server Claude CodeCodexCursor +2

Multi-agent LiteRAG MCP server for advanced code graph analysis. Runs locally from the @er77/code-graph-rag-mcp npm package.

not rated 121 2mo ago A tokens not measured original MIT archived

skills

257

probabl-ai/skills

Plugin Claude Code

Bundles 14 skills · 6,446 tokens together

Skills to support Machine Learning experimentation using the Python ecosystem.

not rated 119 20d ago A tokens not measured original BSD-3-Clause

nativeprompt

258

edvardgrishin27/nativeprompt

Skill Claude CodeCodex

A prompt editor that adapts a user's request to the rules of a selected coding model, such as Claude Code, Codex, Gemini CLI, or GPT-5.

not rated 119 +3 2d ago A 147 tokens original MIT

coleam00/cole-medin-knowledge-base

Skill Claude Code

Build an OKF (Open Knowledge Format) knowledge base from any YouTube channel. Uses Google's OKF standard so any AI can read the output with zero setup. Uses Supadata (managed API, paid). Invoke with /channel-to-kb-supadata @ChannelHandle.

not rated 117 +3 1mo ago A 63 tokens

sparesparrow/mcp-prompts

Command Claude CodeCursor

Command "use-mcp-prompts-in-order-to" from sparesparrow/mcp-prompts, covering core concept: prompt engineering as a service, detailed breakdown of mcp tools, how to use in software development, instructions for other llms (system prompt) and mcp tool usage protocol.

not rated 117 1mo ago A 0 tokens

sandbase

263

sandbaseai/cli

Skill Claude Code

Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbasediscover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the…

not rated 116 +22 9d ago A 67 tokens original Apache-2.0

luma-vision

264

JochenYang/luma-mcp

Skill Claude CodeCodex

A skill for analyzing images with several external vision models. It is activated only when a user starts a request with /skill luma-vision and includes an image.

not rated 114 +1 29d ago A 37 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: