AUTOMATIONSWITCH
Editorial · Reviews · Field guides

Reviewedby builders.Built for shipping.

Editorial reviews and field guides on MCP servers, agentic frameworks, skills, coding assistants, and the tools moving automation forward. 113 servers reviewed, 17 frameworks scored, 27 coding assistants compared.

Read the latest →Browse the directories →
Where to startCurated
Editor’s wedgeLead

The SKILL.md Directory

The configuration primitive every agent builder is reaching for, indexed and editorially reviewed. Start here if SKILL.md is new to you.

436 sessions / 90dRead the directory →
Directory

Where to find MCP servers

14 directories ranked. Every major index compared, with notes on what each is best for.

Tool

Tools

Configurators, calculators, decision engines.

Directory

AI Coding Assistants

14 scored on speed, MCP support, and pricing transparency.

113MCP Servers Reviewed17Agentic Frameworks7,530Skills Indexed27Coding Assistants Scored
Cited 200+ times daily by AI SearchLive counts · auto-updating
Latest ArticlesView all →
Editor’s pick· Case Study

How a 28-Day-Old Site Got Cited 1,400 Times by AI Assistants

Automation Switch dogfood case study. Concrete narrative with full citation data. Demonstrates the agent-readability methodology working at the smallest possible scale.

Case StudyMay 202611 min readRead →
01Case Study

From grep to glance: building a visibility layer for AI-native work

Inaugural Build Log for GovPort. Why I extracted it from GoldenPath, the three architectural problems that forced the standalone direction, the Next.js + Vercel + Postgres + GitHub OAuth stack, and the cross-product framing where one tool watches both Scaletific and Automation Switch.

May 20267 min readRead →
02Fundamentals

What Is an Agent Harness? (And How It Differs From an Agent Framework)

An agent harness is the runtime that turns an LLM into something that can act. How harnesses differ from frameworks, why the distinction matters, and what to look for in production.

May 202610 min readRead →
03Tool Guide

CLAUDE.md vs AGENTS.md: When to Use Each (And Why You Need Both)

CLAUDE.md and AGENTS.md often get treated as alternatives. They are complementary layers. CLAUDE.md is the Claude-specific overlay; AGENTS.md is the cross-platform base. Most repos benefit from both.

May 20269 min readRead →
04Deep Dive

memory.md and 'Claude Memory': What It Actually Is

memory.md and 'Claude memory' get used loosely. Four mechanically distinct things hide behind the word across Claude Code, Claude.ai, ChatGPT, and Cursor. The taxonomy.

May 202615 min readRead →
New: Skills Hub
The SKILL.md Directory

The index the agent ecosystem has been missing. Browse, filter, and copy SKILL.md files by domain, platform, and use case. Built with Firecrawl. Growing weekly.

Browse the Directory →
7,530
Skills Indexed
ResourcesView all →

Visual breakdowns. Long-form research distilled into scrollable infographics. 4 in the library.

Visual breakdown

Hyperautomation vs Agentic AI

7 sections · scrollable
Visual breakdown

Agent Skills Landscape

7 sections · scrollable
Visual breakdown

MCP Security Visual Audit

9 sections · scrollable
Visual breakdown

AI Coding Assistants Scorecard

5 sections · scrollable
ToolsView all →

Platform Selector

Score Zapier, Make, n8n, and the rest against your team shape, workload, and migration tolerance. Five-axis decision in three minutes.

Live

Token Generator

Generate the design tokens behind any AS-style component: surface, border, eyebrow, type scale. Copy as CSS or Tailwind.

Live

Automation Prioritizer

Rank candidate automations by ROI, time saved, and execution difficulty. Surface the workflows worth building first.

Live