Prompt Engineering

Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents

Security Scan

The skill is an instruction-only prompt-engineering documentation bundle whose requirements and instructions align with its stated purpose and do not request extra privileges or sensitive data.

Purpose & Capability

The name/description (prompt engineering expert) match the provided files (SKILL.md, README, BEST_PRACTICES, TECHNIQUES, EXAMPLES). There are no unrelated requirements (no cloud credentials, no platform binaries) that would be incoherent for this kind of skill.

Instruction Scope

Runtime instructions are documentation and examples for crafting and evaluating prompts. They do not instruct the agent to read system files, exfiltrate data, call arbitrary external endpoints, or access credentials. Integration notes mention using Agent SDK/Files API for legitimate workflows but the skill does not include steps that would automatically transmit data.

Install Mechanism

There is no install spec and no code files to execute — this is instruction-only documentation, which is the lowest-risk install profile.

Credentials

The skill requests no environment variables, credentials, or config paths. Sample snippets reference the Anthropic client but don't require the skill to store or access secrets itself.

Persistence & Privilege

The skill does not request always:true and makes no claims about modifying other skills or system-wide settings. It is user-invocable and does not request elevated or persistent privileges.

Assessment

This appears to be a coherent, documentation-only prompt-engineering skill and is safe from a privilege/credential perspective. Before installing: (1) skim the README/SKILL.md to confirm it matches your expectations, (2) do not paste secrets, API keys, or private documents into prompts when testing, and (3) if you integrate it with your Agent SDK or Files API, supply credentials only to the SDK/environment — the skill itself does not need them. If you see later versions requesting env vars, downloads, or commands that read system files or contact unknown URLs, treat that as a red flag and re-evaluate.

Prompt Engineering Expert Skill

This skill equips Claude with deep expertise in prompt engineering, custom instructions design, and prompt optimization. It provides comprehensive guidance on crafting effective AI prompts, designing agent instructions, and iteratively improving prompt performance.

Capabilities

• Prompt Writing Best Practices: Expert guidance on clear, direct prompts with proper structure and formatting
• Custom Instructions Design: Creating effective system prompts and custom instructions for AI agents
• Prompt Optimization: Analyzing, refining, and improving existing prompts for better performance
• Advanced Techniques: Chain-of-thought prompting, few-shot examples, XML tags, role-based prompting
• Evaluation & Testing: Developing test cases and success criteria for prompt evaluation
• Anti-patterns Recognition: Identifying and correcting common prompt engineering mistakes
• Context Management: Optimizing token usage and context window management
• Multimodal Prompting: Guidance on vision, embeddings, and file-based prompts

Use Cases

• Refining vague or ineffective prompts
• Creating specialized system prompts for specific domains
• Designing custom instructions for AI agents and skills
• Optimizing prompts for consistency and reliability
• Teaching prompt engineering best practices
• Debugging prompt performance issues
• Creating prompt templates for reusable workflows