This is a real guide, generated for an example user. Yours is built from a short interview about how you actually work — your saved prompts, your projects, your do-not-break workflows. Free during beta.
How to move from Claude to Claude Code.
A step-by-step playbook to move Claude workflows into Claude Code — copy-ready, checkable, and checked against each tool’s own docs.
- Prepared for
- An example 3-person marketing team
- Sources
- 15 verified sources
7 steps, 5 paste-ready assets, 12 to confirm in Claude Code, about 20 minutes.
- Projects for repo/codebase context
- Coding help in long chats
- Artifacts for code
- Skills for repeatable tasks
- File uploads of code
Setup steps
Work through these in order. Check each off as you go; your progress is saved on this device.
Install the CLI with `npm install -g @anthropic-ai/claude-code`, then run `claude` in any project directory. On first launch run `/login` and authenticate with the same Anthropic account you use on claude.ai — your subscription (Pro/Max/Team) is detected automatically, no separate purchase. Heads up: usage limits are SHARED between web chat and Claude Code, so a heavy coding day eats the same weekly quotas as your web usage.
Subscription plan gatingInteractive chat sessionClone/`cd` into your GitHub repository in your local terminal, then run `claude` from the repo root. This is the equivalent of opening a long Claude.ai chat, except the agent now has implicit Read/Write/Edit access to the cwd and everything below it — no more pasting code in. Work in natural-language turns just like chat; `@path/to/file` injects a specific file, and the agent uses Glob/Grep/Read to pull in context on demand. Use `/help` to see the slash-command surface (`/clear`, `/compact`, `/model`, `/review`, etc.).
A few things to confirm
We flag these up front so nothing surprises you — a short list to double-check in Claude Code as you go.
- 12 items are flagged to confirm in Claude Code — check the menu paths and field names as you go.
Paste-ready assets
Workflows from Claude, rewritten to paste straight into Claude Code.
A Claude.ai Project holding the project's docs and key files so Claude has standing context.
# Project Context ## What this repo is <one-paragraph description of the project, its purpose, and tech stack — paste from your Claude.ai Project instructions> ## Architecture / key files - `src/` — <what lives here> - `<path>` — <role> - Entry point: `<path>` (Don't paste file contents here — Claude Code reads them on demand via Read/Glob/Grep. Use `@path/to/file` in a turn to pull a specific file into context.) ## Conventions & standards - Language/runtime: <e.g. TypeScript, Node 20> - Style: <linting, formatting rules> - Testing: <framework, how to run, e.g. `npm test`> - Build/run: <commands> ## How I want help - Tone: direct, engineer-to-engineer. Skip preamble; give me the change and the reasoning. - When debugging, propose the smallest fix first; explain root cause briefly. - For multi-file changes, use Plan mode and show diffs before applying. ## Static guidance docs - See `@docs/architecture.md` and `@docs/conventions.md` for deeper context.
Same-day walkthrough
This sample was built for an example user. Yours gets built around how you work.
A 15–25 minute interview captures your workflows, then the guide is generated for you — same structure, your prompts, your projects, your gotchas. Nothing in your stack is changed or cancelled by any of it.