prompt-optimization
Guidelines for creating effective prompts that maximize AI understanding and response quality. Helps developers craft clear, specific, actionable prompts with appropriate context for optimal AI assistance.
Best use case
prompt-optimization is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Guidelines for creating effective prompts that maximize AI understanding and response quality. Helps developers craft clear, specific, actionable prompts with appropriate context for optimal AI assistance.
Teams using prompt-optimization should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/prompt-optimization/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How prompt-optimization Compares
| Feature / Agent | prompt-optimization | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Guidelines for creating effective prompts that maximize AI understanding and response quality. Helps developers craft clear, specific, actionable prompts with appropriate context for optimal AI assistance.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Prompt Optimization Guide Comprehensive guide for crafting high-quality prompts that maximize AI understanding and effectiveness. Contains best practices for clarity, context, structure, and tactical approaches to prompt engineering. ## When to Apply Reference these guidelines when: - Crafting initial prompts for complex tasks - Improving AI response quality and accuracy - Training team members on effective AI interaction - Iterating on prompts that aren't producing desired results - Creating reusable prompt templates ## Rule Categories by Priority | Priority | Category | Impact | Prefix | |----------|----------|--------|--------| | 1 | Clarity and Precision | CRITICAL | `clarity-` | | 2 | Context Provisioning | CRITICAL | `context-` | | 3 | Structure and Formatting | HIGH | `structure-` | | 4 | Tactical Tips | MEDIUM | `tactical-` | | 5 | Examples and Patterns | MEDIUM | `example-` | | 6 | Advanced Techniques | HIGH | `advanced-` | ## Quick Reference ### 1. Clarity and Precision (CRITICAL) - `clarity-specific-language` - Use precise terminology instead of vague concepts - `clarity-define-terms` - Define technical terms or acronyms - `clarity-clear-objectives` - State specific goals and expectations - `clarity-avoid-ambiguity` - Eliminate vague pronouns and references ### 2. Context Provisioning (CRITICAL) - `context-project-info` - Include relevant project background - `context-current-state` - Describe current situation and constraints - `context-goals-outcomes` - Specify desired outcomes and success criteria - `context-priorities-tradeoffs` - Explain important priorities and trade-offs ### 3. Structure and Formatting (HIGH) - `structure-segmentation` - Break complex requests into logical sections - `structure-order-of-info` - Present information in logical sequence - `structure-formatting-visual` - Use markdown for readability - `structure-sequential-steps` - Number steps when sequence matters ### 4. Tactical Tips (MEDIUM) - `tactical-role-definition` - Assign specific roles to AI - `tactical-expectation-setting` - Explicitly state output format - `tactical-feedback-loops` - Include iteration and refinement cycles - `tactical-constraints-clarification` - Clearly define limitations ### 5. Examples and Patterns (MEDIUM) - `example-good-vs-bad` - Compare effective and ineffective approaches - `example-template-patterns` - Provide reusable prompt templates - `example-industry-specific` - Show domain-specific best practices - `example-error-patterns` - Highlight common mistakes to avoid ### 6. Advanced Techniques (HIGH) ## How to Use Follow the systematic approach outlined in USAGE.md for consistent prompt optimization results.
Related Skills
reviewing-agent-prompting
Review and improve prompts for coding agents. Use PROACTIVELY when auditing, checking, or evaluating agent instructions, system prompts, or task delegation text. Applies state-machine thinking to identify structural gaps and improve effectiveness.
prompt-repetition
LLM 정확도 향상을 위한 프롬프트 반복 기법. 70개 벤치마크 중 67%(47/70)에서 유의미한 성능 향상 달성. 경량 모델(haiku, flash, mini)에서 자동 적용.
prompt-factory
World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through intelligent 7-question flow, 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory, specialized-technical, research, creative-media), multiple output formats (XML/Claude/ChatGPT/Gemini), quality validation gates, and contextual best practices from OpenAI/Anthropic/Google. Supports both core and advanced modes with testing scenarios and prompt variations.
Prompt Engineering Skill
Craft effective prompts that get the best results from language models.
prompt-engineering-openai-api-f7c24501
Log in [Sign up](https://platform.openai.com/signup)
prompt-engineer-llm
World-class expert in prompt engineering, LLM fine-tuning, RAG systems, and AI/ML workflows. Use when crafting prompts, designing AI agents, building knowledge bases, implementing retrieval systems, or optimizing LLM performance at production scale.
portfolio-optimization
Optimize project portfolio selection under constraints using mathematical optimization
llm-optimization
Optimize websites for AI assistant recommendations. ChatGPT, Gemini, Perplexity, Claude. Get cited in AI answers.
generative-optimization
Expert guidance for solving optimization problems using generative models (GMM and Flow Matching). Use when users need to solve optimization, inverse problems, or find feasible solutions under constraints using probabilistic sampling approaches.
create-prompt
Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.
create-custom-prompt
Prompt for creating custom prompt files
agentv-prompt-optimizer
Iteratively optimize prompt files against AgentV evaluation datasets by analyzing failures and refining instructions.