About prompt-engineering
A prompt-engineering skill for people building LLM features, agents, or assistants. It covers structured prompt design, synthetic test generation, and iterative evaluation, with a requirement to deliver the complete prompt text.
Key features
- 01Structured prompt design
- 02Prompt optimization across LLMs
- 03Synthetic test data generation
- 04Evaluation across edge cases
- 05Prompt chains and pipelines
Use cases
- 01Refining an agent system prompt
- 02Extracting structured data from support tickets
- 03Testing a classification prompt
- 04Designing a multi-step document analysis chain
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/prompt-engineeringin Claude Code to confirm it loaded.
Bundled filesreferences/synthetic-data.mdreferences/techniques.md
Details
From the project READMEPrompt Engineering
Craft, test, and iterate prompts that deliver reliable outputs across LLMs. Covers prompt optimization techniques, structured prompt design, synthetic test data generation, and evaluation methodology.
When to Use This Skill
- Building or optimizing prompts for AI-powered features
- Crafting system prompts for agents or assistants
- Improving reliability and consistency of LLM outputs
- Generating synthetic test data to validate prompt behavior
- Evaluating prompt performance across edge cases
- Designing prompt chains and pipelines
Quick Reference
| Task | Load reference |
|---|---|
| Prompt techniques and patterns | skills/prompt-engineering/references/techniques.md |
| Synthetic test data generation | skills/prompt-engineering/references/synthetic-data.md |
Workflow
- Research: Gather the use case, constraints, and evaluation criteria. Audit existing prompts and model behaviors.
- Design: Draft structured prompts with examples, constraints, and evaluation hooks. Plan experiments and measurement strategy.
- Generate test data: Analyze prompt variables, generate diverse and realistic test cases to validate the prompt.
- Validate: Run prompt trials, capture outputs, document adjustments. Iterate until quality thresholds are met.
- Deliver: Hand off the final prompt with usage guidance and evaluation results.
Core Principle
When creating prompts, always display the complete prompt text in a clearly marked section. Never describe a prompt without showing it. The prompt must be copyable and self-contained.
Deliverables Checklist
For every prompt engineering task, produce:
- The complete prompt text (displayed in full, properly formatted)
- Explanation of design choices and techniques used
- Usage guidelines (model, temperature, parameters)
- Example expected outputs
- Test cases covering happy path, edge cases, and adversarial inputs
Example Interactions
- "Optimize this system prompt for our code review agent"
- "Create a prompt for extracting structured data from support tickets"
- "Generate test cases to validate this classification prompt"
- "Design a prompt chain for multi-step document analysis"
- "Improve consistency of this summarization prompt"