Prompt Mastery
Advanced LLM prompt engineering expertise for crafting highly effective prompts, system messages, and tool descriptions with Claude-specific techniques
npx skills add majiayu000/claude-skill-registry --skill prompt-mastery --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Prompts for advanced LLM prompt engineering with a Claude-focused approach, providing clear, explicit instruction practices, context and motivation, and structure-oriented techniques. It targets system prompts, tool descriptions, and agent instructions, and emphasizes designing the question space and iterative refinement.
How it works
- Advises on delivering clear and explicit instructions to Claude models.
- Encourages providing context and motivation to improve target responses.
- Recommends using XML tags to structure prompts for better control and parseability.
- Describes enabling thinking steps, prefilling responses, and placement of critical requirements in user messages.
- Presents advanced prompting techniques (CoT, few-shot prompting, meta-prompting, prompt scaffolding) with concrete XML/JSON examples.
- Covers structured prompting formats (XML, JSON schema, function/tool calling) to enforce output structure.
- Includes role-based prompts to influence tone and focus, along with guardrails for safety.
- Addresses multimodal prompting concepts and basic prompt-injection defenses.
When to use it
Invoke before writing any significant prompts to leverage advanced techniques, especially when creating system prompts, tool descriptions, or agent instructions, or any scenario requiring sophisticated prompt design.
What it can touch
The skill references several tools and formats: XML tags like <task>, <context>, <output_format>, and Python-like tool calling structures; mentions of handling structured outputs via JSON schemas and tool definitions. It also notes Claude-specific model families and optimization concepts.
Caveats
The content presents best practices and techniques but does not guarantee performance or outcomes. It emphasizes explicit instructions and structured formats, and acknowledges framing effects like prompt placement and prefilling limitations. It references security considerations around prompt injection defense but does not provide guarantees.
# Prompt Mastery: Advanced LLM Prompt Engineering Skill **Purpose**: This skill provides comprehensive prompt engineering expertise, distilling cutting-edge research, best practices, and battle-tested techniques for crafting highly effective prompts for Large Language Models, with special emphasis on Claude. **When to invoke**: Use this skill when creating system prompts, tool descriptions, agent instructions, or any situation requiring sophisticated prompt design. Invoke before writing any significant prompts to leverage advanced techniques. --- ## 🎯 Core Principles ### The Fundamentals (Never Violate These) 1. **Clarity Over Cleverness**: Clear, explicit instructions consistently outperform clever wordplay 2. **Specificity Beats Vagueness**: Precise requirements produce better results than general requests 3. **Context is Currency**: Provide enough background for the model to understand the task deeply 4. **Structure Reduces Ambiguity**: Well-structured prompts eliminate confusion 5. **Iteration is Essential**: First prompts rarely achieve perfection—treat prompting as iterative ### The 2025 Paradigm Shift Modern prompt engineering isn't about asking questions—it's about **desig
- 🎯 Core Principles
- The Fundamentals (Never Violate These)
- The 2025 Paradigm Shift
- 🔷 Claude-Specific Techniques
- Official Anthropic Best Practices (2025)
- 🚀 Advanced Prompting Techniques
- Chain-of-Thought (CoT) Prompting
- Few-Shot Prompting
- Meta-Prompting & Self-Reflection
- Prompt Scaffolding
- 📐 Structured Prompting
- XML Prompting (Claude's Native Format)
- JSON Schema for Structured Output
- Function/Tool Calling for Structure
What does the Prompt Mastery skill do?
Advanced LLM prompt engineering expertise for crafting highly effective prompts, system messages, and tool descriptions with Claude-specific techniques
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill prompt-mastery --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.