prompt-engineering
Prompt engineering for Claude API, system prompts, context management, instruction design, depth levels, HTML generation. Use when working with Claude API integration, designing prompts, managing conversation context, or implementing AI-powered features.
npx skills add majiayu000/claude-skill-registry --skill prompt-engineering-bpmstc-websiteagent --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.
# Prompt Engineering for Claude API ## Core Principles 1. **Clear Instructions** - Be specific about what you want Claude to do 2. **Context First** - Provide all necessary context before asking 3. **Examples Work** - Show examples of desired output 4. **Constraints Matter** - Define boundaries and rules explicitly 5. **Iterate and Test** - Refine prompts based on actual outputs --- ## System Prompt Structure The system prompt in `server/prompts/system.txt` is the foundation of Claude's behavior. ### CORRECT: Well-Structured System Prompt ``` You are an expert instructional designer and educational content creator. Your job is to generate complete, self-contained HTML pages for educational purposes. # Your Role You create educational content at various depth levels (0-4) based on user specifications. Each page you generate must be: - A single, complete HTML file - Ready to paste into Blackboard LMS - Styled with inline CSS (no external stylesheets) - Accessible and well-structured - Appropriate for the specified depth level # Depth Levels (CRITICAL - NEVER DEVIATE) Level 0 (Minimalist): Reference-only content. Tables, lists, minimal explanation. - Example: CSS property reference ta
- Core Principles
- System Prompt Structure
- CORRECT: Well-Structured System Prompt
- Streaming Responses Pattern
- Depth Level Enforcement
- Image Integration Prompts
- Requesting Image Generation
- Adding User-Provided Images
- Error Handling in Prompts
- Handling Generation Failures
- Testing Prompts
- Checklist
- Before Implementing Prompt
- After Implementing Prompt
What does the prompt-engineering skill do?
Prompt engineering for Claude API, system prompts, context management, instruction design, depth levels, HTML generation. Use when working with Claude API integration, designing prompts, managing conversation context, or implementing AI-powered features.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill prompt-engineering-bpmstc-websiteagent --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.