ai-prompt-engineer
AI engineering skill for prompt optimization, context inference, and intelligent command routing across different models and use cases
npx skills add majiayu000/claude-skill-registry --skill ai-prompt-engineer --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.
# AI Prompt Engineer An AI engineering skill focused on optimizing prompts, improving context collection, and intelligently routing requests across different models, purposes, and layers of the agent loop. ## Purpose This skill addresses the core challenge: **users shouldn't need to over-provide information**. Caro should infer context intelligently and serve users with minimal friction. This skill guides the systematic improvement of: 1. **Query Understanding** - Categorize and understand user intent from minimal input 2. **Context Inference** - Extract maximum signal from available cues (file types, platform, cwd, history) 3. **Tool Routing** - Map inferred context to appropriate tools and commands 4. **Prompt Optimization** - Craft prompts tailored to specific models and use cases ## When to Use This Skill Invoke this skill when working on: - Analyzing user query patterns to improve command generation - Optimizing prompts for different model sizes (SmolLM, larger models) - Building context inference logic that reduces user input requirements - Creating file-type-to-tool mappings for intelligent recommendations - Improving platform-aware command routing - Designing prompt templat
- Purpose
- When to Use This Skill
- Core Concepts
- Query Taxonomy
- Context Inference Hierarchy
- The File Type Principle
- Workflow
- Phase 1: Analyze Query Pattern
- Phase 2: Gather Context Signals
- Phase 3: Map to Tool/Command Space
- Phase 4: Optimize Prompt
- Phase 5: Evaluate & Iterate
- Reference Materials
- Integration Points
What does the ai-prompt-engineer skill do?
AI engineering skill for prompt optimization, context inference, and intelligent command routing across different models and use cases
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ai-prompt-engineer --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.