> ## Documentation Index
> Fetch the complete documentation index at: https://deepline.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# How to Migrate from Clay to Claude Code
> Take an existing Clay table and produce equivalent scripts that run locally, on your schedule, with full control. Use it to get through setup and your first.
Clay tables are column-based — each column is a separately configured enrichment or AI step. Deepline is outcome-centric: describe what you're trying to achieve and Claude selects the right tools to get there.
The video walks through a real Clay table with email waterfalls, Claygent research, and ICP scoring — the full flow from table → phase 1 doc → scripts → output CSV.
***
## What you need
The table you want to migrate.
Install from [claude.ai/code](https://claude.ai/code) and log in.
Runs the enrichment scripts Claude Code generates. Install below.
You can use this skill just to **document** a Clay table without running
anything. If that's your goal, skip to [Documentation-Only
Path](#documentation-only-path) at the bottom.
***
## Install Deepline
Deepline is what runs the enrichment. It wraps providers like LeadMagic, Exa,
Instantly, and Claude into a single command. Ask your coding agent to set it up:
```text theme={null}
Set up Deepline in this environment by following https://code.deepline.com/SKILL.md. Read and follow the skill exactly.
```
If you prefer the terminal:
```bash theme={null}
npm install -g deepline@latest && npm exec --yes --package=deepline@latest -- deepline setup --json
```
Setup verifies the CLI, skills, authentication, and workspace before it
finishes. Use `deepline doctor --json` if setup reports a problem.
You don't need Deepline if you just want a Phase 1 doc (table summary +
dependency graph + pass plan). You only need it when you want to actually run
the output scripts.
***
## The workflow
Four steps. The first two are in Claude Code. The last two are in your terminal.
### Easy path: the Clay Extract bookmarklet
Instead of capturing network logs by hand, use the **Clay Extract bookmarklet**. It runs in your already-logged-in Clay tab, pulls the full table config, schema, sample records, and all cell data, then downloads a single `clay_extract_.json` you can hand straight to `/clay-to-deepline`. Your session cookie is never read or stored, only your browser uses it.