wren-quickstart

Wren Quickstart

Version check

Silently fetch https://raw.githubusercontent.com/Canner/wren-engine/main/skills/versions.json. Compare the wren-quickstart key with this skill's version (from the frontmatter above). If the remote version is newer, notify the user before proceeding:

A newer version of the wren-quickstart skill is available. Update with:

npx skills add Canner/wren-engine --skill wren-quickstart --agent claude-code

Then continue with the workflow below regardless of update status.

---

This skill walks a user through setting up Wren Engine end-to-end — from creating a workspace to running their first query via MCP. Each phase delegates to a focused skill. Follow the steps in order.

Prerequisites: The dependent skills (wren-generate-mdl, wren-project, wren-mcp-setup, wren-connection-info) must be installed. If they are missing, use /wren-usage first — it handles skill installation and then routes back here for setup.

---

Phase 1 — Create a workspace

1a — Set up Python virtual environment

Before creating the workspace, ensure a Python virtual environment is available. This is required if the user will run ibis-server locally (instead of relying solely on Docker). Skip this step if the user will use only the Dockerized ibis-server.

python3 -m venv .venv
source .venv/bin/activate        # macOS / Linux
# .venv\Scripts\activate         # Windows
pip install --upgrade pip

Tip: Place the venv inside or adjacent to the workspace directory so it is easy to find. Avoid committing it to version control — add .venv/ to .gitignore.

1b — Create a workspace directory

Create a dedicated workspace directory on the host machine. This directory will be mounted into the Docker container, so the container can read and write MDL files.

Ask the user where they want the workspace, or suggest a default:

mkdir -p ${PWD}/wren-workspace

Save the chosen path as <WORKSPACE_PATH> (absolute path, e.g. /Users/me/wren-workspace). All subsequent steps reference this path.