How to turn a design doc into tasks with Claude
Give Claude the doc and ask it to put the doc on a Develosaur board. Claude reads it and writes the plan as an outline: sections become branches, the work in them becomes tasks, and you watch the board fill in and change the order of anything you disagree with. It works from Claude Code, claude.ai and the Claude desktop app.
Steps
- Connect Claude once. The setup for Claude Code, claude.ai and other clients is on the integrations page; Claude Code takes one command:
claude mcp add --transport http --scope user develosaur https://mcp.develosaur.com/v1/user/mcp - Paste or attach the doc, or point Claude Code at the file, and ask:
Put this design doc on a develosaur board, one branch per section. - Open the board to watch it appear, then reorder, retag or edit anything by hand.
- Ask for the first step:
What's the first task on the develosaur board?
Try it without an account
Paste this into your agent. It builds a temporary board you can keep later:
Read https://mcp.develosaur.com/llms.txt and use it to build me a develosaur board for my projectQuestions
Can I change the plan by hand?
Yes. Edit, retag and reorder tasks on the board; agents see the changes the next time they read it.
Which Claude can do this?
Claude Code, claude.ai and the Claude desktop app can all connect to the same board.
Can I try it without an account?
Yes. Paste this into an agent that can fetch URLs: "Read https://mcp.develosaur.com/llms.txt and use it to build me a develosaur board for my project". It builds a trial board you can keep later.
Related
Other answers
- How to make Claude Code remember the plan between sessions
- How to run multiple Claude Code agents without conflicts
- How to keep a Cursor project plan across chats
- How to share an AI agent's plan with your team
- MCP task manager for Claude Code: how to set one up
- How to put Codex and Claude Code on the same plan
- How to hand off work between AI agent sessions
- A kanban board your AI coding agents can update
- Persistent memory for AI coding agents vs a project board