Connect Snowflake

What it does

When your agent uses it

• The user says connect to snowflake
• Use the live data
• Query the warehouse
• Asks is this hitting snowflake

Example prompts

• “connect to snowflake”
• “use the live data”
• “go remote”
• “/connect-snowflake”

Requirements

• Python 3
• A credential in SNOWFLAKE_TOKEN

Workflow steps

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

1. 1Run through ConnectionManager with remote opted in
2. 2Verify you're actually on Snowflake (not the DuckDB fallback)
3. 3Log every query

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

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

• Network

  No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

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

• Credentials

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

  • SNOWFLAKE_TOKEN
  • SNOWFLAKE_PASSWORD

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

Context cost

Connect Snowflake loads about 1.4k tokens when it runs. Until then it costs about 104 tokens; SKILL.md has 594 words of instructions outside code blocks.

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

~104

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

~1.4k

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:20

  elds, stores the approved credential in `.env`, and verifies the native

• NoteMentions a .env fileSKILL.md:50

  `ConnectionManager` auto-loads `.env`, expands the `$SNOWFLAKE_*` placeholders

• NoteMentions a .env fileSKILL.md:84

  config** (`.env` / `connection_templates/`) — compare against what you expect,

• NoteMentions a .env fileSKILL.md:105

  - A PAT lives in `.env` as `SNOWFLAKE_TOKEN`; a legacy password uses

• NoteMentions a .env fileSKILL.md:107

  manifest. Never echo or cat `.env`.

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). 594 words, ~1,411 tokens.

name

connect-snowflake

description

Query the live/remote Snowflake warehouse instead of the local practice copy. Use when the user says "connect to snowflake", "use the live data", "go remote", "query the warehouse", or asks "is this hitting snowflake or duckdb?". Assumes credentials already exist (first-time setup is /setup-snowflake); opts into remote via ConnectionManager and verifies the connection type before any query runs.

export AAP_USE_REMOTE=1 && python3 -W ignore -c "
import warnings; warnings.filterwarnings('ignore')
from helpers.data.connection_manager import ConnectionManager
mgr = ConnectionManager()
print('backend:', mgr.connection_type)   # MUST print 'snowflake'
events = mgr.table_reference('events')
df = mgr.query(f'SELECT event_type, COUNT(*) n FROM {events} GROUP BY event_type ORDER BY n DESC')
print(df.to_string(index=False))
mgr.close()
"

python3 scripts/log_query.py --dataset {active} --agent ad-hoc \
  --purpose "..." --sql "..." --result "..."

© 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/connect-snowflake of ai-analyst-lab/ai-analyst.

Open the folder on GitHubat commit 52c0744