Optimization guidelines for Claude 3.5 Sonnet, Claude 3.5 Haiku, and Opus.
Scanned 9/10/2026
Install to Claude Code
npx -y skills add Rahulchaube1/Rahul-Chaube-Skills --skill anthropic --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Anthropic?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/rahulchaube1-anthropic)More formats (shields.io, HTML) on the badges page.
---
name: anthropic
description: Optimization guidelines for Claude 3.5 Sonnet, Claude 3.5 Haiku, and Opus.
---
# Anthropic
Optimization guidelines for Claude 3.5 Sonnet, Claude 3.5 Haiku, and Opus.
## Core Guidelines
- **XML Tag Usage**: Structure contexts, inputs, and thinking loops inside XML blocks (e.g. `<instructions>`, `<thought>`).
- **Chain of Thought**: Leverage Claude's reasoning skills by prompting for step-by-step logic.
- **System Prompts**: Utilize the dedicated system prompt block for behaviors.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!