Claude Code
Run claude in the course folder and approve the coursecode server once. The workflow skills appear as /coursecode-outline, /coursecode-build-slides, and so on.
CourseCode Framework is open source and runs on your computer. Your AI tool writes the course as regular project files, and CourseCode's MCP server lets it preview, screenshot, lint, and test what it built. Export SCORM 1.2, SCORM 2004, cmi5, or LTI 1.3.
Create an empty folder, start your AI tool in it (Claude Code, Codex, Cursor, VS Code, or any tool that can run commands), and paste this:
Set up a CourseCode Framework course in this folder. Check that Node.js 22.15 or later is installed and help me install it if it isn't. Then run `npx coursecode@latest create .` and tell me what to do next.
When it's done, restart your AI tool in the same folder so it loads the CourseCode tools, then describe the
course you want. The project includes MCP settings, an AGENTS.md, and workflow skills for outlining,
building, reviewing, and publishing. No account is required. Full setup guide
Run claude in the course folder and approve the coursecode server once. The workflow skills appear as /coursecode-outline, /coursecode-build-slides, and so on.
Run codex in the course folder and trust it, so Codex reads the project's MCP settings and skills.
Cursor and VS Code pick up the project's settings and skills. Any other MCP client can run
npx -y coursecode mcp. See MCP setup.
Prefer a plugin? An optional Claude Code and Codex plugin runs the tools in every folder, so your AI tool can start a course before a project exists.
An AI tool that only writes files can't see the course. Through 16 MCP tools, it can open the real course in a headless preview and check it the way a reviewer would.
Screenshot any slide at desktop and phone sizes, then fix layout problems before you look.
Answer questions right and wrong, take assessments, and read the score, feedback, and LMS data that result.
Run static lint checks and read build, runtime, and console errors from the live preview.
Browse catalogs of components, interactions, CSS classes, and icons instead of guessing at names.
Start from an older SCORM course, a PowerPoint deck, PDFs, or Word documents. coursecode convert
turns documents into text your AI tool can read, and it rebuilds the material as a course you can review, update,
and repackage.
A CourseCode project can target several LMS formats without separate source versions. Local builds produce one format at a time; CourseCode Cloud keeps one deployment and generates the requested download later.
The broadest-compatibility option. Confirm the required SCORM version with your LMS administrator and test the package in your target platform.
Separate completion and success status plus richer tracking. Use it when your LMS supports the required SCORM 2004 edition.
An xAPI-based launch standard with richer statement data. It requires a cmi5-capable LMS.
A server-backed integration rather than a static ZIP. Production use requires platform registration, keys, and a trusted backend.
Multiple choice, drag-and-drop, matching, sequencing, hotspots, fill-in-the-blank, and graded assessments with keyboard and LMS tracking support. Review content and media for accessibility before release.
Local preview with live reload, in-browser editing, config panels, and a simulated LMS, with no upload needed during development.
Slides, settings, and theme are plain files you can review, version in Git, and extend with plugins for custom interactions and components.
No cloud account required.