Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.

The most frequently used agent skills of Wade Foster, CEO of Zapier

172 expert marketing skills for AI agents — ClawFu MCP Server

Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes included.

✨ A curated list of awesome GitHub instructions, prompt, skills, MCPs and agent markdown files for enhancing your GitHub Copilot AI experience.

Prompt packs that make any AI agent a LaTeX expert — fix errors, polish writing, format for venues, read papers, recover source

✨ A customizable copilot-instructions.md ruleset & prompts to guide GitHub Copilot toward secure coding defaults in Java, Node.js, C# and Python. Blocks risky patterns, teaches safe habits.

AI agent skills for social media content strategy, creation, and analysis across text-first platforms

Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.

Markdown that steers an LLM is code. Genesis is the architectural layer for designing multi-agent, multi-skill systems -- with named patterns, contracts, and substrate portability, before you write them.

Agent skill for analyzing and improving prompts using 31 frameworks across 7 intent categories. Works with Claude Code, Gemini CLI, Cursor, Copilot, and 30+ Agent Skills compatible tools.

Commercial real estate AI agent skills for CRE underwriting, due diligence, financing, brokerage, legal and closing workflows - standalone prompts for Claude Code, ChatGPT, Cursor, and other LLMs.

GSD Pro — The most powerful AI coding workflow for Claude Code. Free alternative to Cursor Composer, Copilot Workspace, Devin & Bolt. Multi-model routing, rollback/recovery, adaptive context. Fork of 30K★ original. npx get-shit-done-cc

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.