explaingit

kmanan/spratt-skills

Analysis updated 2026-05-18

0PythonAudience · developerComplexity · 4/5Setup · hard

TLDR

Python infrastructure add-ons for OpenClaw that turn it into a household automation system for messages, trips, flights, and groceries.

Mindmap

mindmap
  root((spratt-skills))
    What it does
      Household automation for OpenClaw
      LLM plans code delivers
    Tech stack
      Python
      SQLite
      OpenClaw
      FlightAware API
    Use cases
      Scheduled messages
      Trip management
      Flight tracking
      Grocery reorder
    Audience
      Developers
      OpenClaw users

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Schedule iMessage notifications through a reliable outbox instead of letting an AI send them live.

USE CASE 2

Track family trip details, flights, and hotel reminders in a database the AI writes to.

USE CASE 3

Poll a flight tracking API and get automatic delay or gate change notifications.

USE CASE 4

Automatically stage a recurring Instacart grocery cart based on past order patterns.

What is it built with?

PythonSQLiteOpenClawFlightAware AeroAPIBlueBubbles

How does it compare?

kmanan/spratt-skills0xhassaan/nn-from-scratch3ks/embedoc
Stars00
LanguagePythonPythonPython
Last pushed2023-06-08
MaintenanceDormant
Setup difficultyhardmoderatehard
Complexity4/54/51/5
Audiencedeveloperdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · hard Time to first run · 1h+

Requires OpenClaw plus several external services (BlueBubbles for iMessage, a paid FlightAware AeroAPI key) and runs best on macOS with launchd daemons.

In plain English

Spratt Skills is a Python collection of household automation add-ons built on top of OpenClaw, an AI agent platform. Unlike typical OpenClaw skill files that teach an AI assistant what to do in plain text, most of these components are infrastructure: persistent daemons, SQLite databases, and scripts that run alongside OpenClaw and handle tasks where AI inconsistency would cause real world failures. The guiding principle stated in the README is that the LLM plans and code delivers, meaning the AI decides what to do while deterministic code handles the actual execution. The collection includes four main components. The Outbox is a SQLite message queue with a Python daemon that delivers scheduled iMessage notifications via a tool called BlueBubbles. It exists because letting an AI reinterpret delivery instructions each run caused wrong recipients and missed notifications. Trip Manager is a command line database for family travel, covering flights, hotels, restaurants, and group chat notifications, where the AI writes structured data and Python scripts automatically generate reminder schedules. It supports watchers, people who want flight updates without being travelers. Flight Monitor is a persistent daemon that polls FlightAware AeroAPI at adaptive intervals, three minutes during active flight windows and thirty minutes when idle, and sends landing, delay, and gate change notifications through the Outbox. The Instacart component tracks grocery order history in SQLite, computes reorder timing from purchase patterns, and stages a cart automatically on a schedule, sending a confirmation text before anything ships. The project runs in production on a Mac Mini M4. The full README is longer than what was shown.

Copy-paste prompts

Prompt 1
Explain how the Outbox pattern in this repo avoids the problem of an AI reinterpreting scheduled messages.
Prompt 2
Walk me through setting up the Trip Manager database and its watcher feature for family travel.
Prompt 3
Show me how the Flight Monitor daemon polls FlightAware AeroAPI and sends notifications.
Prompt 4
Help me understand how the Instacart component decides which items are due for reorder.

Frequently asked questions

What is spratt-skills?

Python infrastructure add-ons for OpenClaw that turn it into a household automation system for messages, trips, flights, and groceries.

What language is spratt-skills written in?

Mainly Python. The stack also includes Python, SQLite, OpenClaw.

How hard is spratt-skills to set up?

Setup difficulty is rated hard, with roughly 1h+ to a first successful run.

Who is spratt-skills for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.