Data and AI instructions files

711 tagged Data and AI, measured the same way as everything else here.

Browse within: copilot 28model-context-protocol 20embeddings 16machine-learning 16ollama 16instructions 15knowledge-graph 15azure 14data-engineering 14openai 14prompt-engineering 14ai-tools 13claude-code-plugin 13knowledge-base 13

VLM-wiki AGENTS.md

217

VeniVeci/VLM-wiki

Instructions file CodexOpenCode

Instructions for VeniVeci/VLM-wiki, covering vlm wiki agent, core philosophy, architecture, special files and model configuration.

not rated 11 2mo ago A 1,638 tokens original MIT

xLSTM-metal AGENTS.md

218

MLXPorts/xLSTM-metal

Instructions file CodexOpenCode

Instructions for MLXPorts/xLSTM-metal, covering agent and developer guide, quick reference, claude guidance (read me first), zero-mock policy (production code) and always reuse before rebuilding.

not rated 11 4mo ago A 1,075 tokens original Apache-2.0

wiro-ai-sdk CLAUDE.md

219

altudev/wiro-ai-sdk

Instructions file

Instructions for altudev/wiro-ai-sdk, covering claude.md, quick command reference, build & type checking, development and testing.

not rated 11 10mo ago A 2,278 tokens original MIT

samwei12/UsefulPrompts

Instructions file

A set of Claude Code instructions for a repository of AI expert-role prompts, including explanations of computer topics and its folder structure.

not rated 11 1y ago A 1,735 tokens

vector-mcp AGENTS.md

221

markdevshop/vector-mcp

Instructions file CodexOpenCode

Instructions for markdevshop/vector-mcp, covering agents.md, tech stack & architecture, architecture diagram, workflow diagram and commands (run these exactly).

not rated 11 2mo ago A 2,938 tokens original MIT

VelociRAG AGENTS.md

222

HaseebKhalid1507/VelociRAG

Instructions file CodexOpenCode

Instructions for HaseebKhalid1507/VelociRAG, covering agents.md — velocirag for ai coding agents, what is this?, architecture, module map and key classes.

not rated 11 5mo ago A 2,908 tokens original MIT

llm-brain CLAUDE.md

223

kimsanguine/llm-brain

Instructions file

A set of Claude Code instructions for llm-brain, a system that turns source files into a searchable wiki and answers questions from it.

not rated 10 21d ago A 3,289 tokens original MIT

kitlau86/agent-vision-mcp

Instructions file

Repository instructions for an MCP server that lets a non-visual AI model analyze images through a configured OpenAI-compatible vision service. MCP is a connection format for exposing tools to AI clients.

not rated 10 3mo ago A 436 tokens original MIT

goai CLAUDE.md

225

shaharia-lab/goai

Instructions file

Claude Code instructions for shaharia-lab/goai, covering claude.md, commands, architecture and conventions.

not rated 10 2d ago A 1,119 tokens original MIT

rcpch/rcpchgrowth-python

Instructions file CodexOpenCode

AGENTS.md instructions for rcpch/rcpchgrowth-python, covering agents.md - guidance for ai/llm development, project overview, who reference migration (completed), development workflow and container-based development.

not rated 10 today A 1,943 tokens AGPL-3.0

Vadiml1024/whisper-speech-to-text

Instructions file

Instructions for Vadiml1024/whisper-speech-to-text, covering whisper speech-to-text with speaker diarization, project overview, architecture, core components and technology stack.

not rated 10 1y ago A 993 tokens original MIT

jrgleason/embeddings-demystified

Instructions file

Claude Code instructions for jrgleason/embeddings-demystified, covering openspec instructions, vector databases and embeddings demystified, project overview, presentation goals and description.

not rated 10 3mo ago A 3,194 tokens

rahulsethi/SAPDatasphereMCP

Instructions file

Claude Code instructions for rahulsethi/SAPDatasphereMCP, covering claude.md — sap datasphere mcp server, what this is, layout, conventions and commands.

not rated 10 2mo ago A 1,440 tokens

PhAlves23/prompt-engineering-skill

Instructions file Gemini CLI

Instructions for PhAlves23/prompt-engineering-skill, covering prompt engineering — gemini context, prompt engineering, operating principle, workflow and canonical structure (omit sections that don't add value).

not rated 9 3mo ago A 1,067 tokens original MIT

click6067-ship-it/fitllm-engine

Instructions file CodexOpenCode

AGENTS.md instructions for click6067-ship-it/fitllm-engine, covering agents.md — how ai agents should use this repo, use it without cloning, use it as a library, rules for agents modifying this repo and measured data welcome.

not rated 8 changed today A 749 tokens original MIT

DocGraph AGENTS.md

234

Detective-XH/DocGraph

Instructions file CodexOpenCode

Instructions for Detective-XH/DocGraph, covering agents.md — docgraph fit guide for llm agents, the fit decision, decisive signals — any one means: use docgraph, supporting signals — useful when several hold together and anti-signals — prefer your own grep/read.

not rated 8 +1 1mo ago B 1,698 tokens original MIT

yumeiriowl/repo-graphrag-mcp

Instructions file CodexOpenCode

Instructions for yumeiriowl/repo-graphrag-mcp, covering repo graphrag mcp usage guide, prerequisites, three tools, tool 1: graphcreate and tool 2: graphquery.

not rated 7 7mo ago A 1,315 tokens original MIT

funsjanssen/faker-mcp

Instructions file GitHub Copilot

Instructions for funsjanssen/faker-mcp, covering faker-mcp development guidelines, active technologies, project structure, commands and code style.

not rated 7 10mo ago A 177 tokens original MIT

luccapinto/agentic-data-kit

Instructions file GitHub Copilot

Instructions for luccapinto/agentic-data-kit, covering agentic data kit — operating rules, language, how to work, data engineering principles (always apply) and data debugging quick reference.

not rated 7 1mo ago A 594 tokens original MIT

alessio-web-dev/social-cli-mcp

Instructions file

Claude Code instructions for alessio-web-dev/social-cli-mcp, covering v7.0 | flutur-cc | 2026-02-07, grafo, entità centrali, flussi dati and fonti canoniche (ρ→0).

not rated 7 5mo ago A 2,758 tokens original MIT