How much time will I actually save with Fazm?

Most users report saving 45-90 minutes per day on repetitive tasks. The biggest time savings come from email management (drafting replies, sorting, archiving), form filling (expense reports, CRM updates, applications), research (comparing products, gathering data from multiple sites), and social media (cross-posting, scheduling, replying). For example, booking a flight that normally takes 10 minutes of clicking through airline sites takes a single voice command with Fazm. Filing an expense report that requires opening a PDF, extracting numbers, and entering them into a spreadsheet becomes one spoken sentence. The more repetitive and multi-step your daily work is, the more time you get back.

What exactly can Fazm control?

Fazm controls everything you can do manually on your Mac. That includes mouse movements and clicks, keyboard typing, browser navigation and form filling, app switching, file management in Finder, and system-level actions. It uses direct browser DOM control for web interactions - meaning it reads and manipulates the actual page structure rather than taking screenshots and guessing where to click. For native macOS apps, Fazm uses accessibility APIs to interact with buttons, menus, text fields, and other UI elements. This works across any application: Chrome, Safari, VS Code, Slack, Figma, Terminal, Mail, Calendar, and more.

How is Fazm different from ChatGPT or Claude?

Chatbots like ChatGPT and Claude give you answers in a conversation window. Fazm takes action directly on your computer. When you say 'reply to Sarah's email,' Fazm opens your email app, finds Sarah's message, writes a contextual reply, and sends it. A chatbot would tell you what to write, but you still have to do all the clicking and typing yourself. Fazm moves your mouse, types on your keyboard, clicks buttons, and navigates between apps. It is a computer agent, not a chat assistant.

How does the memory layer work?

Fazm builds a personal knowledge graph by extracting information from your files, browsing history, conversations, and daily activity. Over time, it learns your contacts (names, emails, relationships), accounts and credentials, preferences (formatting, tone, scheduling habits), and frequently used workflows. In your first week, you might say 'Reply to Sarah's email, she's my cofounder, her email is sarah@acme.com.' By week four, you just say 'Reply to Sarah' because Fazm already knows who she is. By week eight, Fazm can draft the reply before you even ask. All of this data stays locally on your Mac - your knowledge graph never leaves your machine or gets sent to any cloud service.

Is Fazm safe? Can it mess up my computer?

Safety is built into every layer of Fazm. You watch every action in real-time on your screen - Fazm moves your mouse and types visibly, so there is nothing hidden. You can stop any action at any point by pressing a keyboard shortcut. Fazm also shows you what it plans to do before executing destructive actions like deleting files or sending emails, giving you a chance to confirm or cancel. Because Fazm is open source, the code is fully auditable on GitHub. There is no hidden behavior, no background processes making changes you cannot see, and no actions that bypass your screen.

What platforms does Fazm support?

Fazm currently supports macOS, running natively on both Apple Silicon (M1, M2, M3, M4) and Intel Macs. It is built with Swift and uses macOS-specific frameworks like ScreenCaptureKit for screen analysis and Accessibility APIs for app control, which is why macOS is the primary platform. Windows and Linux support are on the roadmap but do not have release dates yet. You can also control your Mac remotely from your phone using Fazm Remote, which gives you voice access to your desktop while you are away from your computer.

How does Fazm voice input work?

One keyboard shortcut activates push-to-talk. Hold the key, speak naturally about what you need done, and release. Fazm transcribes your speech locally using on-device models, so there is no network latency for the voice recognition step. You do not need wake words like 'Hey Siri' or 'OK Google' - just press and talk. You can also type commands into the floating toolbar if you prefer text input. Fazm understands natural language, so you do not need to memorize specific commands. Say 'book me a flight to Tokyo next Thursday' or 'find the cheapest AirPods on Amazon' and Fazm figures out the steps.

Is my data sent to the cloud?

Fazm processes screen analysis and memory entirely on your machine. The personal knowledge graph, file indexing, and screen capture all run locally. The only data that leaves your Mac is the intent - a text description of what you want to accomplish, which is sent to the AI model (Claude or GPT) for action planning. Your actual screen content, file contents, browsing history, and personal knowledge graph never leave your computer. Fazm is also open source, so you can verify exactly what data is transmitted by reading the code on GitHub. For users who need complete air-gapped operation, local model support is planned.

Making Claude Code Skills Repeatable - 30 Skills Running Reliably

Fazm Team·March 17, 2026·3 min read

claude-code skills reliability automation developer-workflow

Making Claude Code Skills Repeatable - 30 Skills Running Reliably

After building and running 30+ Claude Code skills for a macOS desktop agent, the pattern for reliability is clear: explicit frontmatter and narrow scope. Everything else is secondary.

What Makes a Skill Reliable

A Claude Code skill is a markdown file that tells Claude how to perform a specific task. The difference between a skill that works once and a skill that works every time comes down to three things:

1. Explicit frontmatter with all parameters defined

Every input the skill needs should be declared upfront. Do not rely on Claude inferring parameters from context. If the skill needs a file path, declare it. If it needs an API key name, declare it. Ambiguity is where failures start.

2. Narrow scope - one task per skill

A skill that "sends an email and updates the CRM and logs to the database" will fail intermittently because any of those three steps can break. Split it into three skills. Each one succeeds or fails independently, and you can debug each in isolation.

3. Clear input/output contracts

Define exactly what the skill produces. If it creates a file, specify the path. If it returns data, specify the format. Claude performs better when it knows precisely what success looks like.

Common Failure Patterns

Skills break in predictable ways:

Implicit dependencies - assuming a tool is installed or a file exists without checking
Broad scope with partial failure - step 3 of 5 fails and the skill does not know how to recover
Context-dependent behavior - the skill works differently depending on what conversation happened before it
Missing error handling - the skill does not check if its actions succeeded

The 30-Skill Architecture

For a macOS agent, the skill set breaks down into categories:

System skills - file management, app launching, clipboard operations
Communication skills - email sending, message posting, notification handling
Development skills - git operations, build processes, deployment
Integration skills - API calls to specific services with specific formats

Each category has 5-8 skills, each doing exactly one thing. The orchestration layer decides which skill to invoke. The skill just executes.

Fazm is an open source macOS AI agent. Open source on GitHub.

Making Claude Code Skills Repeatable - 30 Skills Running Reliably

Making Claude Code Skills Repeatable - 30 Skills Running Reliably

What Makes a Skill Reliable

Common Failure Patterns

The 30-Skill Architecture

More on This Topic

Related Posts

The Irony of AI Automation - Debugging Skills Takes Longer Than the Original Task

Claude Code Skills Are Mini Startup Wrappers - How Playwright MCP Ties 30+ Skills Together

Custom Skills vs Marketplace Skills in Claude Code - Why Building Your Own Wins