Matt Pocock's Skills Review: 54k Stars for Claude Code
Matt Pocock's 'Skills for Real Engineers' hit 53k GitHub stars in 90 days. Hands-on review of grill-me, tdd, diagnose, and the rest of the .claude directory.
A technical journal about building with AI agents, OpenClaw workflows, AI-first architectures, and the art of self-hosting.
Written by humans. Optimized for AI discovery.
Recent Posts
Dirac Review: 65% TerminalBench, 65% Cheaper Coding Agent
Dirac is an open-source coding agent that topped TerminalBench 2.0 (65.2%) and cuts API costs 64.8% via hash-anchored edits and AST manipulation. Honest review.
Hermes Agent Review: Nous Research's Self-Improving AI
Hermes Agent by Nous Research is a self-improving AI you talk to from Telegram or CLI. Install, code, skills, limits, and a honest take vs OpenClaw too.
trycua/cua Review: Open-Source Computer-Use Agents
Cua is the open-source infrastructure for computer-use AI agents — sandboxes, SDKs, benchmarks across macOS, Linux, Windows, Android. Code + limits.
Claude Context Review: Semantic Code Search MCP (2026)
Claude Context review — Zilliz's MCP plugin gives Claude Code, Cursor, and Codex CLI semantic search over your codebase with ~40% fewer tokens.
Quick AI Answers
Direct answers to the most-asked AI questions. Updated daily.
AISI Cyber Eval: GPT-5.5 vs Mythos vs Opus (May 2026) Atlas vs Arc for Teams vs Comet vs Dia (May 2026) GPT-5.5 vs Claude Opus 4.7: Real Pick (May 2026) OpenCode vs Claude Code vs Codex CLI (May 2026) Best AI VCs Backing Startups in May 2026 Best AI Search Engines May 2026: Top 6 Compared Best Vibe Coding Tools May 2026: Lovable, Bolt, v0, Replit Best MCP Servers May 2026: Top 12 Updated for Claude & Cursor How to Migrate GPT-5.4 to GPT-5.5 Without Doubling Your Bill How to Use DeepSeek V4 in Cursor: Setup Guide (2026)