Deliver CSV analysis in a Slack thread with follow-ups

Connect an @mention and CSV attachment to an analysis session, stream progress in-thread, and return the report there.

Goal

Goal: Connect an @mention and CSV attachment to an analysis session, stream progress in-thread, and return the report there.

Use Slack Bolt @app.event("app_mention") to acknowledge the event and capture channel, thread timestamp, and question. [slack]
Send the attachment to the data-analyst session; persist its ID with the Slack thread key and post progress with say(..., thread_ts=...). [slack]
Post the completed report or link in that thread; reuse the session for follow-ups and archive it when finished. [slack]

Simulate a mention, CSV attachment, and follow-up; verify one acknowledgement and all output in the same thread.

Deduplicate repeated events by event ID; check Socket Mode scopes and whether the app joined the channel.

Python 3.11+, Anthropic API key, Slack bot token, `connections:write` app-level token, and a configured analyst agent.

Invite the bot only to authorized channels; verify file permissions and avoid echoing sensitive data in threads.

The demo stores tokens in `.env`; production should use a secret manager and minimize Slack scopes.

These values describe the upstream repository, not popularity or likes for an individual skill or playbook.

No metrics snapshot is available yet.

License: MIT