Flitsy running inside a Claude chat, showing a 'Plan my week' board of accounts to reach out to, dragged onto days

flitsy: a CRM that lives inside your AI chat

flitsy is a CRM you never open. Instead of another web app with seven tabs, you connect it to Claude (or any Model Context Protocol client) and just ask. The AI reads your pipeline, drafts replies in your tone, and chases the follow-ups. You stay in the chat you were already in. This is the inverse of “a CRM with an AI button bolted on.” There’s no CRM screen to look at, because the AI is the screen. ...

May 27, 2026
Moonjar on iPad answering a hotel comparison question with a structured table and source citations

Moonjar: a second brain that reads

Moonjar is a personal knowledge system that captures anything you want to remember and hands it to an assistant that has already done the reading. Send it a photo, a link, a PDF, an email, a voice note, or a stray thought, and Moonjar files it, pulls out the details that matter, and answers when you come looking, with citations back to the source. It replaces the pile of bookmarking apps, read-it-later queues, and note scratchpads with one place: save it once, ask for it later in plain language. ...

May 27, 2026

Agent Skills - Production-Grade Skills for AI Coding Agents

Agent Skills is a collection of production-grade engineering skills by Addy Osmani, designed so AI coding agents follow senior engineering workflows consistently across every phase of development. Seven slash commands map to the full development lifecycle: /spec — Define what to build with requirements and acceptance criteria /plan — Break work into small, atomic, verifiable tasks /build — Implement incrementally, one slice at a time /test — Prove it works with failing tests first /review — Five-axis code review before merge /code-simplify — Clarity over cleverness /ship — Pre-launch checklist, monitoring, rollback plan The collection includes 19 skills covering the full engineering lifecycle — from spec-driven development and TDD through security hardening, performance optimisation, and deployment — plus three dedicated agent personas (code reviewer, security auditor, test engineer) that run as subagents for structured, formatted review passes. ...

April 8, 2026