Data and AI

16,068 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.

graph-engineering

145

codejunkie99/graph-engineering

Skill Claude CodeCodex

Teaches an agent graph engineering — both halves. Knowledge graphs (ontology design, entity/relation/event extraction, fusion, GraphRAG/memory serving; distilled and translated from Southeast University's graduate Knowledge Graph course, npubird/KnowledgeGraphCourse, 4.4K stars) and task graphs (agent orchestration …

not rated 477 +17 1mo ago A 152 tokens original MIT

npcpy-prompting

146

NPC-Worldwide/npcsh

Skill Claude CodeCodex

Skill "npcpy-prompting" from NPC-Worldwide/npcsh, covering npcpy-prompting, imports, basic-call, json-mode and npc-object.

not rated 476 +5 yesterday A 16 tokens original MIT

growthxai/output

Skill Claude CodeCodex

Guide to the providerOptions structure in .prompt files — decision tree for where an option goes, common mistakes, per-provider quick reference, and Anthropic prompt caching. Use when writing or reviewing .prompt file frontmatter (provider, model, providerOptions, messageOptions).

not rated 435 +1 changed yesterday A 59 tokens original Apache-2.0

agnes-ai-generation

148

Yacey/agnes-ai-generation-skill

Skill Claude CodeCodex

Call Agnes AI / Sapiens AI generation APIs for text, image, and video. Use when the user asks to use Agnes models, Agnes Image, Agnes Video, Agnes 2.0 Flash, apihub.agnes-ai.com, or to generate text, images, edit images, create videos, animate images, create keyframe videos, or test Agnes API calls.

not rated 410 +5 2mo ago A 80 tokens original MIT

ai-product-patterns

149

menkesu/awesome-pm-skills

Skill Claude CodeCodex

Builds AI-native products using OpenAI's development philosophy and modern AI UX patterns. Use when integrating AI features, designing for model improvements, implementing evals as product specs, or creating AI-first experiences. Based on Kevin Weil (OpenAI CPO) on building for future models, hybrid approaches, and…

not rated 402 +1 6mo ago A 69 tokens

quant.cpp CLAUDE.md

150

quantumaikr/quant.cpp

Instructions file

Claude Code instructions for quantumaikr/quant.cpp, covering quant.cpp — agent development guide, project vision, project overview, architecture and key documents.

not rated 400 +1 4mo ago A 2,450 tokens original Apache-2.0

bagel AGENTS.md

151

Extelligence-ai/bagel

Instructions file CodexOpenCode

AGENTS.md instructions for Extelligence-ai/bagel, covering bagel for agents, set up bagel for a user, use bagel well and develop on bagel.

not rated 397 +1 today A 601 tokens original Apache-2.0

rlm

152

brainqub3/RLM

Skill Claude CodeCodex

Recursive Language Model (RLM) loop for processing a context that is too large to read into the conversation directly. Loads the context as a variable in a persistent Python REPL and answers the query by writing code that probes, chunks, and programmatically sub-queries a cheap LLM (llmquery) over slices of it, then…

not rated 393 2mo ago A 227 tokens original MIT

promptscript

153

mrwogu/promptscript

Skill Claude CodeCodex

PromptScript language expert for reading, writing, modifying, and troubleshooting .prs files. Use when working with PromptScript syntax, creating or editing .prs files, adding blocks like @identity, @standards, @restrictions, @shortcuts, @skills, or @agents, configuring promptscript.yaml, resolving compilation errors…

not rated 391 5d ago A 135 tokens original MIT

pageindex-mcp

154

VectifyAI/pageindex-mcp

MCP server Claude CodeCodexCursor +2

Reasoning-based RAG system for chatting with long PDFs. Supports local and online files. Runs locally from the @pageindex/mcp npm package.

not rated 383 +1 1mo ago A tokens not measured original MIT

mcp-local-rag

155

shinpr/mcp-local-rag

Skill Claude CodeCodex

Searches, saves, and maintains a local document index through a local RAG MCP server. Use when user says "search my docs", "save this page", "read around that chunk", "sync my index", or invokes npx mcp-local-rag.

not rated 383 +6 yesterday A 61 tokens original MIT

claude-api

156

JrCx7scC/claude-code-source

Skill Claude CodeCodex

This skill helps you build LLM-powered applications with Claude. Choose the right surface based on your needs, detect the project language, then read the relevant language-specific documentation.

not rated 376 +1 5mo ago A 0 tokens

framedex

157

Simbastack-hq/framedex

Skill Claude CodeCodex

Build a portable knowledge base of your video (and eventually photo) archive across multiple SSDs or directly from an Apple Photos library. For each clip: GPS + reverse-geocoded place, speaker-diarized multi-lingual transcript with English translation, face detection + embeddings for later named-person queries…

not rated 376 +2 2mo ago A 284 tokens original MIT

prompt-review

158

tokoroten/prompt-review

Skill Claude CodeCodex

A review tool for AI prompts and past conversations. It examines chats from coding assistants such as Claude Code, Copilot Chat, Cursor, and Codex to estimate technical understanding, prompting habits, and reliance on AI.

not rated 361 4mo ago A 140 tokens

getcrew44/crew44

Skill Claude CodeCodex

Assess whether your product work is AI-first or AI-shaped. Use when evaluating AI maturity and choosing the next team capability to build.

not rated 359 2mo ago A 33 tokens original MIT

dais-polymtl/flock

Instructions file GitHub Copilot

Instructions for dais-polymtl/flock, covering copilot instructions for flock, repository layout, building, setup vcpkg (first time or after clean) and release build.

not rated 355 1mo ago A 1,406 tokens original MIT

context-engine

161

melonelish/context-engine

MCP server Claude CodeCodexCursor +2

Task-aware context compression for logs, RAG, and coding workflows. Runs locally from the melonelish-context-engine Python package.

not rated 353 +2 1mo ago A tokens not measured original MIT

deepseek

162

DMontgomery40/deepseek-mcp-server

MCP server Claude CodeCodexCursor +2

Official DeepSeek MCP server for chat, completion, model listing, and balance endpoints. Runs locally from the deepseek-mcp-server npm package. Needs 1 environment variable to run.

not rated 351 +1 17d ago A tokens not measured original MIT

add-rollout-function

163

THUDM/DeepDive

Skill Claude CodeCodex

Guide for adding a new rollout function in slime and wiring it through --rollout-function-path. Use when user wants to implement custom rollout data generation logic, custom train/eval rollout outputs, or migrate from the default sglang rollout path.

not rated 346 +1 2mo ago A 54 tokens

visualtorch

164

willyfh/visualtorch

MCP server Claude CodeCodexCursor +2

Architecture visualization of Torch models. Runs locally from the visualtorch Python package.

not rated 332 today A tokens not measured original MIT

openai

165

mattt/emcee

MCP server Claude CodeCodexCursor +2

One of 3 in claude_desktop_config.json

MCP server "openai", hosted remotely at raw.githubusercontent.com, as configured in mattt/emcee.

not rated 332 +2 2mo ago A tokens not measured original MIT

Model Monitoring

166

aj-geddes/useful-ai-prompts

Skill Claude CodeCodex

Monitor model performance, detect data drift, concept drift, and anomalies in production using Prometheus, Grafana, and MLflow.

not rated 332 +6 6mo ago A 28 tokens original MIT

CHEATSHEET

167

cognesy/instructor-php

Agent

Agent loop, state model, tools, context management, hooks, and subagent orchestration.

not rated 326 4d ago A 18 tokens original MIT

volcengine/mcp-server

Skill Claude CodeCodex

Manage OpenViking collections (OV libraries) from the command line with ov-cp — list / create / get / update / usage / get the data-plane API key / delete, plus managing the users of an enterprise-tier library (list / register / update / delete) and configuring how a library is billed (AgentPlan AFP deduction vs…

not rated 321 +1 2d ago A 164 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: