Setup Snowflake

What it does

When your agent uses it

• The user says set up snowflake
• Connect to snowflake
• Configure the warehouse
• Is routed here from /connect-data

Example prompts

• “set up snowflake”
• “connect to snowflake”
• “configure the warehouse”
• “/setup-snowflake”

Requirements

• Python 3
• A credential in SNOWFLAKE_TOKEN

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Choose authentication and collect the connection details
2. 2Write credentials to .env
3. 3Register the dataset
4. 4Verify you are LIVE on Snowflake (hard gate)
5. 5Explore and hand off

What it can do on your machine

Read from SKILL.md and the folder at commit 52c0744. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python3
  • pip
  • bash
  • curl
  • sh
  • uvx

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • astral.sh

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • SNOWFLAKE_PASSWORD
  • SNOWFLAKE_TOKEN

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Setup Snowflake loads about 2k tokens when it runs. Until then it costs about 160 tokens; SKILL.md has 801 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~160

When it runs · the whole SKILL.md, loaded when a task matches

~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:6

  field, stores the approved credential in .env, registers the dataset, and VERIFIES the session is live on

• NoteMentions a .env fileSKILL.md:53

  o place the approved secret directly in `.env`:

• NoteMentions a .env fileSKILL.md:61

  ## Step 2: Write credentials to `.env`

• NoteMentions a .env fileSKILL.md:62

  Read any existing `.env` first and preserve other variables. Then set (Write/Edit tool only):

• NoteMentions a .env fileSKILL.md:69

  `.env`. Account, user, warehouse, database, schema, and role are not secrets and go in the dataset

• NoteMentions a .env fileSKILL.md:85

  SNOWFLAKE_TOKEN"         # expanded from .env at connect time

• NotePipes a well-known installer script into a shellSKILL.md:141

  1. Install `uv`: `curl -LsSf https://astral.sh/uv/install.sh | sh`, then `~/.local/bin/uvx --version`.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ai-analyst-lab/ai-analyst at commit 52c0744, republished under its MIT licence (© ai-analyst-lab). 801 words, ~1,974 tokens.

name

setup-snowflake

description

First-time Snowflake setup wizard for the NATIVE ConnectionManager path (the connection the analyst actually queries through, with auto-logged provenance). Prompts for every connection field, stores the approved credential in .env, registers the dataset, and VERIFIES the session is live on the warehouse before declaring success. Use when the user says "set up snowflake", "connect to snowflake", "configure the warehouse", or is routed here from /connect-data. For day-to-day remote querying after setup, use connect-snowflake. An optional Snowflake MCP server (for interactive ad-hoc queries) is covered in the appendix.

python3 -c "import snowflake.connector; print('driver OK')" || pip install snowflake-connector-python

SNOWFLAKE_AUTHENTICATOR=programmatic_access_token
SNOWFLAKE_TOKEN=<programmatic-access-token>

connection:
  type: snowflake
  authenticator: programmatic_access_token
  account: "<account>"
  warehouse: "<warehouse>"
  database: "<database>"
  schema: "<schema>"
  user: "<username>"
  token: "$SNOWFLAKE_TOKEN"         # expanded from .env at connect time
  # role: "<role>"                  # include only if given

active_dataset: "{id}"
use_remote: true

AAP_USE_REMOTE=1 python3 - <<'PY'
from helpers.data.connection_manager import ConnectionManager
cm = ConnectionManager(dataset_id="{id}")
cm.connect()
print(cm.test_connection()["message"])          # -> "Live on account ..., warehouse ..."
v = cm.verify_remote()                            # proves snowflake, not the local fallback
assert v["remote"], f"NOT LIVE: {v['reason']}"
print("Tables:", cm.list_tables()[:25])
PY

AAP_USE_REMOTE=1 python3 -c "from helpers.data.connection_manager import ConnectionManager as C; c=C(dataset_id='{id}'); c.connect(); print(c.list_tables())"

© ai-analyst-lab, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/setup-snowflake of ai-analyst-lab/ai-analyst.

Open the folder on GitHubat commit 52c0744