May 30, 2026 · 6 min read
How to Write a Great AGENTS.md (With a Real Example)
AGENTS.md tells AI coding agents how to work in your repo. Here's what a great one contains, a real example, the five rules that make it work, and the mistakes to avoid.
All posts
Raju H · Tag
Posts tagged “claude-code”
7 posts.
May 30, 2026 · 5 min read
How to Set Up a New Project for Claude Code (AGENTS.md, Subagents, and Slash Commands)
A productive AI-agent project is more than one config file. Here's the complete .claude/ setup — rules file, a subagent, and a slash command — with verified formats and real examples.
May 29, 2026 · 4 min read
Claude Skills Explained: How to Install Them and Which Ones Are Worth It
What Claude Skills (Agent Skills) actually are, the correct way to install them (the viral posts get the command wrong), and a practical filter for which skills are worth adding.
May 26, 2026 · 8 min read
The 12 AI Prompts I Actually Use Every Week as an Indie Engineer
Not 50, not 100. Twelve specific prompts I reach for weekly building real production software solo — with the actual prompt text, when to use each, and the failure mode it prevents.
May 26, 2026 · 6 min read
Building a Production bKash Integration with Claude Code in One Afternoon
The real bKash Tokenized Checkout flow, the four production traps that kill most tutorials, and the spec-first prompt that gave me working code in 4 hours. Real code from buildwithraju.dev.
May 26, 2026 · 6 min read
Claude Code vs Cursor for Spec-First Workflows: A Working Engineer's Take
Token efficiency, context windows, and review ergonomics — which AI coding tool actually wins when you work spec-first, and why most senior engineers run both in 2026.
May 26, 2026 · 8 min read
Spec-Driven AI Explained: A Working Professional's Guide (with Real Examples)
Why spec-driven AI beats vibe-coding in production, the four-paragraph spec that ships a feature without 12 retries, and how to apply it whether you write code or not.