--- title: GitHub Copilot CLI description: "Give Copilot CLI the HyperFrames skills, make a first request, and preview the project locally." --- GitHub Copilot CLI supports both project and personal agent-skill locations. HyperFrames skills give it the framework rules and creation workflows required to build a real project. ## Install the skills Run: ```bash npx hyperframes skills update ``` This installs or refreshes the global core set and links it into compatible installed agents. Copilot reads the shared `~/.agents/skills` location, so the skills remain available across projects. Open the project folder you want to edit, then start Copilot: ```bash copilot ``` If you installed the skills during an active session, run: ```text /skills reload ``` Use `/skills list` or `/skills info hyperframes` to confirm discovery. GitHub's [current skills guide](https://docs.github.com/en/copilot/how-tos/copilot-cli/customize-copilot/add-skills) lists every supported location and management command. ## Make the request ```text Using /hyperframes, make a 10-second product intro for https://example.com. ``` Copilot can load a relevant skill automatically, but naming `/hyperframes` makes the intended entry point explicit. Continue in the same session for revisions. ## Preview and render In another terminal: ```bash npx hyperframes preview ``` Then ask Copilot to render or run: ```bash npx hyperframes render --output output.mp4 ``` Run `npx hyperframes lint` and `npx hyperframes check` before delivery. ## Hosted alternative For hosted HyperFrames tools, add the MCP server to one Copilot session: ```bash copilot --additional-mcp-config \ '{"mcpServers":{"hyperframes":{"url":"https://mcp.heygen.com/mcp/hyperframes/"}}}' ``` For a persistent connection, use Copilot's [current MCP configuration](https://docs.github.com/en/copilot/reference/copilot-cli-reference/cli-command-reference#mcp-server-configuration). The [HyperFrames MCP guide](/guides/mcp) explains the creation workflow. Vocabulary and patterns that produce better compositions. See what the agent does between the request and the finished project.