A practical, no-hype workflow for AI coding agents: context, plan, implement, review, QA, ship, retro. Templates, two Claude Code skills, and a 40% context rule - every claim traced to official docs.

A reusable agent workflow kit with personas, skills, rules, and memory files.

VexJoy AI Agent with Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.

from vibe coding to agentic engineering - practice makes claude perfect

Playwright for coding agents. Benchmark Claude Code, Codex, Gemini, and OpenCode on your own tasks - and test that your skills, MCP servers, and CLIs work when an agent uses them. Sandboxed YAML suites, activation checks, A/B experiments, CI gates.