Index of every page on this site: llms.txt
All skills
jamesrochabrun avatar

/anthropic-prompt-engineer

@2482c17
Run it yourself

Master Anthropic's prompt engineering techniques to generate new prompts or improve existing ones using best practices for Claude AI models.

Use this Skill: https://skilld.dev/gh/jamesrochabrun/skills/anthropic-prompt-engineer

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈42 tokens for metadata: the name and description. ≈1k when used: this file. ≈6.2k more on demand in 5 files.

Description uses 2.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈168 characters, or 2.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Anthropic Prompt Engineer

Master the art and science of prompt engineering with Anthropic's proven techniques. Generate new prompts from scratch or improve existing ones using best practices for Claude AI models (Claude 4.x, Sonnet, Opus, Haiku).

What This Skill Does

Helps you create and optimize prompts for Claude AI using Anthropic's official techniques:

  • Generate new prompts - Build effective prompts from requirements
  • Improve existing prompts - Optimize prompts for better results
  • Apply best practices - Use proven techniques from Anthropic
  • Avoid common mistakes - Prevent hallucinations and unclear outputs
  • Optimize for Claude 4.x - Leverage latest model capabilities
  • Structure complex prompts - Build multi-step, production-ready prompts

Why Prompt Engineering Matters

Without proper prompting:

  • Inconsistent or incorrect outputs
  • Hallucinations and made-up information
  • Unclear or verbose responses
  • Wasted tokens and API calls
  • Poor performance on complex tasks
  • Difficulty reproducing results

With engineered prompts:

  • Precise, reliable outputs
  • Factual, grounded responses
  • Clear, formatted results
  • Efficient token usage
  • Excellent complex task performance
  • Reproducible, production-ready results

Quick Start

Generate a New Prompt

Using the anthropic-prompt-engineer skill, create a prompt that:
- Extracts structured data from customer emails
- Returns JSON format
- Handles missing information gracefully
- Includes 2 examples

Improve an Existing Prompt

Using the anthropic-prompt-engineer skill, improve this prompt:

"Analyze this code and tell me if there are bugs"

Make it more effective using Anthropic's best practices.

Core Techniques Summary

1. Be Clear and Direct

Provide explicit, unambiguous instructions. Claude 4.x excels with precise direction.

2. Use XML Tags for Structure

Organize prompts with semantic tags like <instructions>, <example>, <context>.

3. Chain of Thought (CoT)

Ask Claude to think step-by-step for complex reasoning.

4. Prefilling

Start Claude's response to guide format and style.

5. Few-Shot Examples

Provide 2-5 diverse examples showing the pattern you want.

6. Role Assignment

Give Claude a specific role or persona for appropriate context.

Reference Materials

All techniques, examples, and templates are available in the references/ directory:

  • core_techniques.md - Essential techniques with examples
  • advanced_techniques.md - Advanced methods and optimization
  • common_mistakes.md - Pitfalls to avoid
  • claude_4_best_practices.md - Claude 4.x specific guidance
  • prompt_templates.md - Ready-to-use templates

Usage Examples

Example 1: Generate a Data Extraction Prompt

Create a prompt that extracts names, emails, and phone numbers from business cards.

Example 2: Improve a Vague Prompt

Transform "Write about machine learning" into a structured, effective prompt.

Example 3: Debug a Failing Prompt

Fix inconsistent outputs by adding structure, examples, and format specification.

Best Practices Checklist

  • Instructions are clear and specific
  • Output format is explicitly defined
  • Examples align with desired behavior
  • XML tags separate different sections
  • Context is minimal but sufficient
  • Edge cases are addressed
  • Tested on diverse inputs
  • Token usage is optimized

Key Principles

  1. Empirical Approach - Test, measure, iterate
  2. Context as Resource - Every token counts
  3. Clarity Over Cleverness - Explicit instructions work best
  4. Examples Teach Best - Show, don't just tell
  5. Structure Helps - Organization reduces confusion
  6. Iteration Improves - Refine based on results

Summary

Master prompt engineering to create:

  • Reliable and consistent outputs
  • Production-ready prompts
  • Token-efficient solutions
  • Easy to maintain systems

Apply Anthropic's proven techniques for best results.


Remember: Good prompts are engineered, not guessed.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts2mo5 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    The skill is a collection of educational resources and templates for prompt engineering. It contains no executable code, malicious instructions, or security vulnerabilities.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

  • Runlayer9mo

    6 files scanned · No issues

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 2482c17. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Dormantupdated last year

README badge

README badge for jamesrochabrun/skills/anthropic-prompt-engineer