Tutorials with the run still attached.
Each verified page records the date, pinned versions, command or test output, and the repo that produced them. The seven tutorials below are still drafts.
Tutorials
Sorted by last verified date once a run exists. Until then, this is the library order.
Integrate
Connect a Local MCP Server to Cursor and Use It to Finish a Real Repo Task
Start a local MCP server, connect it in Cursor, and complete a repo task that requires that tool.
Not yet verified
Migrate
Migrate a Working Claude Code Setup (CLAUDE.md, Hooks, and MCP) to Cursor
Migrate a working CLAUDE.md, hooks, and MCP config to equivalent Cursor behavior and re-test the same task.
Not yet verified
Migrate
Switch an OpenAI Agents SDK App from One Model Provider to Another Without Breaking Tools
After switching model/provider, tools and handoffs still work, proven with tests.
Not yet verified
Integrate
Add a Second Frontier Model to Claude Code with a Documented Fallback Path
Configure a second model and complete the same task via the fallback after a simulated failure.
Not yet verified
Integrate
Build a TypeScript MCP Server for a Real API, Test It with Inspector, and Call It from Claude Code
Implement the server, pass Inspector, then call it from Claude Code to finish a real API task.
Not yet verified
Tasks
Complete a Greenfield Refactor with a Coding Agent: Add Tests and Make CI Green
In a small public or sample repo, add tests, commit the change, and make CI green.
Not yet verified
Integrate
Call Qwen4-Max Through Your Existing OpenAI SDK and Finish a Tool-Calling Task
Call qwen4-max from the OpenAI SDK by changing only api_key, base_url and model, then finish a real tool-calling job: a checked dependency report for an npm project.
Not yet verified