mcpField
S
slacrawl

slacrawl

github.com/openclawProductivity393.3k279 installsUpdated today
Repository

About slacrawl

slacrawl is a skill for querying local Slack archive data and refreshing it when needed. It covers freshness checks, bounded searches, message queries, and read-only SQL; syncing methods have different token requirements.

Key features

  1. 01Checks archive freshness and status
  2. 02Searches and lists messages
  3. 03Runs read-only SQL queries
  4. 04Syncs through wiretap, bot, or MCP
  5. 05Supports bounded queries and syncs

Use cases

  1. 01Answering questions from archived Slack data
  2. 02Checking whether recent data is available
  3. 03Counting or ranking messages with SQL

MCP support

A configured connector can be selected with `--source mcp` to sync Slack archive data. The skill otherwise queries the local archive.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/openclaw/openclaw --skill slacrawl

After installing, type/slacrawlin Claude Code to confirm it loaded.

Bundled filesagents/openai.yaml

Details

From the project README

Slacrawl

Use local Slack archive data first. Check freshness for recent/current questions:

slacrawl doctor
slacrawl status --json

Refresh only when stale or asked:

slacrawl sync --source wiretap
slacrawl sync --source bot --latest-only

wiretap reads Slack Desktop cache; bot uses API tokens. The desktop/api aliases remain valid. A configured connector can use --source mcp; select the workspace explicitly when needed. Use --full only for deliberate backfills.

Query with bounded slices:

slacrawl search --limit 20 "query"
slacrawl messages --since 7d --limit 50
slacrawl sql "select count(*) from messages;"

Report workspace/channel names, absolute date spans, counts, and token/source limits. Use read-only SQL for exact counts/rankings. API sync and full thread/DM hydration require Slack tokens; do not assume they exist.

Comments

Markdown supported