> ## Documentation Index > Fetch the complete documentation index at: https://docs.graphify.com/llms.txt > Use this file to discover all available pages before exploring further. # Choose your coding assistant > Install the Graphify skill in your editor, terminal agent, or shared agent environment. Graphify offers two ways to give an assistant context: a **skill** that guides the build and query workflow, and an **MCP server** that exposes the saved graph as tools. You can use either or both.

Claude Code

Skill and project instructions.

Cursor

Skill and editor rules.

Codex

Skill and AGENTS.md integration.

Gemini CLI

Skill and Gemini instructions.

GitHub Copilot

Copilot CLI and VS Code setup.

Other assistants

OpenCode, Kilo, Kiro, and more.

## The common workflow ```bash theme={null} uv tool install graphifyy graphify install --platform cursor ``` Replace `cursor` with the installer platform for your assistant. Restart or refresh the assistant if it does not discover the new skill immediately, then ask it to map the current repository with Graphify. Skill invocation differs by client. Slash commands are common; Codex also exposes skills through the `$` picker. If a client does not show slash commands, explicitly ask it to use the installed Graphify skill. ## Project or personal installation The default registration is personal. Add `--project` for repository-local registration where supported. This makes the instructions reviewable in version control and lets a team share the setup. The installer adds platform-specific files and may install hooks or instructions that suggest querying the graph before reading source. It does not grant your assistant new permissions. ## Prefer tools instead? [Connect the graph MCP server](/mcp/overview). It provides ten tools for graph exploration and PR context, independently of whether you installed the skill.