Prompt Engineering Expert

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

Security Scan

This is an instruction-only prompt-engineering reference package that is internally consistent with its stated purpose and does not request extra privileges, installs, or credentials.

Purpose & Capability

Name, description, and all included files are consistent: the skill provides documentation, examples, and prompt-engineering guidance. It does not request unrelated credentials or binaries. Minor metadata inconsistencies exist (registry metadata/ownerId and version differ from the _meta.json content), which look like packaging/metadata drift but do not change the skill's behavior.

Instruction Scope

SKILL.md and the other markdown files contain guidance, examples, and upload instructions only. The instructions do not tell the agent to read system files, access secrets, call arbitrary external endpoints, or execute code. Example snippets reference uploading the folder and calling standard APIs (Claude/Anthropic) for normal usage—expected for this purpose.

Install Mechanism

No install spec and no code files are present. This is instruction-only, so nothing will be downloaded or written by an installer—lowest-risk installation model.

Credentials

The skill declares no required env vars, credentials, or config paths. The documentation recommends using standard APIs (Claude/Anthropic) where usual API keys would be needed, but the skill itself does not ask for or embed any secrets.

Persistence & Privilege

Skill flags are default (always: false, user-invocable: true, model invocation allowed). It does not request persistent or elevated privileges and contains no code that would modify agent/system configuration.

Assessment

This package appears to be a benign, documentation-only prompt-engineering skill. Before installing, consider: (1) the source is unknown and homepage is missing—if provenance matters to you, prefer skills from trusted authors; (2) do not paste secrets or private data into prompts when testing; (3) test its suggestions in a controlled environment (the skill is advisory only and does not execute prompts); (4) the repository metadata has small inconsistencies (ownerId/version in _meta.json vs registry) — likely harmless packaging drift but worth noting if you need traceability. If you plan to share the uploaded folder or use it in team settings, review licensing and remove any examples containing sensitive data.

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