Explore Anthropic guides and tutorials on vybecoding.ai. Each guide is a structured, multi-lesson course covering practical techniques, real-world examples, and hands-on exercises for developers at every skill level. Whether you are just getting started with Anthropic or looking to deepen your expertise, these guides provide the depth and clarity to move forward with confidence.
The five agentic patterns from Anthropic's 'Building Effective Agents' — prompt chaining, routing, parallelization, orchestrator-workers, and evaluator-optimizer — each with one runnable Python example. Start simple, add complexity only when it pays for itself.
After cataloging every internal skill at Anthropic, the Claude Code team found they cluster into exactly nine categories. Here is each one — what it does, the skills Anthropic names as examples, and how to map the taxonomy onto your own .claude directory.
A small Anthropic-popularized prompting trick: instead of asking your AI agent to reply in plain text, ask it for HTML. You get scannable tables, color-coded options, and diagrams instead of a wall of prose. This guide covers the exact prompt, a before/after readability comparison, the real use cases, and the honest tradeoffs (token cost, noisy diffs) so you know when NOT to use it.
A fact-checked look at Anthropic's official frontend-design skill for Claude Code — including a correction to the widely-cited 277K install figure, what the skill actually changes versus default Claude output, and when it is not the right tool.
Anthropic engineers do not write better prompts — they stop writing prompts. This guide breaks down the 4 rules they actually follow: prompt skills not Claude, build tools not just prompts, compose small skills instead of one giant one, and let every session sharpen the skill. Includes an annotated /draft-email skill and a composable domain-checker example.
Haiku handles simple tasks, Sonnet manages most workloads, and Opus takes the judgment calls. This guide covers Anthropic's three-tier routing strategy, the Adviser API pattern, and the decision matrix for choosing which model to call when.
The five agentic patterns from Anthropic's 'Building Effective Agents' — prompt chaining, routing, parallelization, orchestrator-workers, and evaluator-optimizer — each with one runnable Python example. Start simple, add complexity only when it pays for itself.
Level: intermediate · 8 min read
After cataloging every internal skill at Anthropic, the Claude Code team found they cluster into exactly nine categories. Here is each one — what it does, the skills Anthropic names as examples, and how to map the taxonomy onto your own .claude directory.
Level: intermediate · 14 min read
A small Anthropic-popularized prompting trick: instead of asking your AI agent to reply in plain text, ask it for HTML. You get scannable tables, color-coded options, and diagrams instead of a wall of prose. This guide covers the exact prompt, a before/after readability comparison, the real use cases, and the honest tradeoffs (token cost, noisy diffs) so you know when NOT to use it.
Level: beginner · 11 min read
A fact-checked look at Anthropic's official frontend-design skill for Claude Code — including a correction to the widely-cited 277K install figure, what the skill actually changes versus default Claude output, and when it is not the right tool.
Level: intermediate · 13 min read
Anthropic engineers do not write better prompts — they stop writing prompts. This guide breaks down the 4 rules they actually follow: prompt skills not Claude, build tools not just prompts, compose small skills instead of one giant one, and let every session sharpen the skill. Includes an annotated /draft-email skill and a composable domain-checker example.
Level: beginner · 17 min read
Haiku handles simple tasks, Sonnet manages most workloads, and Opus takes the judgment calls. This guide covers Anthropic's three-tier routing strategy, the Adviser API pattern, and the decision matrix for choosing which model to call when.
Level: beginner · 96 min read