mcpField
G
graincrawl

graincrawl

github.com/openclawProductivity393.3k284 installsUpdated today
Repository

About graincrawl

graincrawl is a skill for querying local Granola archive data before relying on other sources. It supports freshness checks, selective sync, bounded reads, and read-only SQL, with guidance for encrypted sources.

Key features

  1. 01Check archive status and freshness
  2. 02Sync from private API or desktop cache
  3. 03Search notes and retrieve transcripts
  4. 04Query panels and notes
  5. 05Run read-only SQL

Use cases

  1. 01Answer questions from a local Granola archive
  2. 02Refresh stale archive data on request
  3. 03Report date ranges and source gaps
  4. 04Check transcript and panel availability

Install

Copy the command and run it in a terminal.

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

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

Bundled filesagents/openai.yaml

Details

From the project README

Graincrawl

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

graincrawl doctor --json
graincrawl status --json

Refresh only when stale or asked:

graincrawl sync --source private-api
graincrawl sync --source desktop-cache

Query with bounded reads:

graincrawl search "query"
graincrawl notes --json
graincrawl note get <id>
graincrawl transcripts get <id>
graincrawl panels get <id>
graincrawl --json sql "select count(*) as notes from notes;"

Report absolute date spans, note titles, source gaps, and transcript/panel availability. Use read-only SQL for exact counts/rankings. Ordinary reads must not surprise-prompt Keychain. Before encrypted source debugging, inspect graincrawl secrets --json; use graincrawl unlock --json before enabling encrypted sources. Resolve the database from status/config rather than assuming a machine-specific path.

Comments

Markdown supported