developing-ai-prompts

name	developing-ai-prompts
description	Write effective prompts and instructions for AI models and agents. Covers universal techniques plus model-specific guidance for Claude, GPT, and Gemini. Use when writing, reviewing, or adapting prompts for any AI model. Invoke PROACTIVELY when creating system prompts, agent instructions, or optimizing model performance.

<essential_principles>

State exactly what you want. Models follow instructions precisely—if you want elaborate output, ask for it explicitly. "Create an analytics dashboard with as many relevant features as possible" outperforms "Create an analytics dashboard." Explain WHY behind instructions. "Never use ellipses because the text-to-speech engine won't know how to pronounce them" beats "NEVER use ellipses." Models generalize from explanations. Wrap distinct sections in XML tags (``, ``, ``). This creates unambiguous boundaries, enables selective attention, and improves parsing accuracy across all models. Few-shot examples outperform lengthy explanations. Show 2-3 input/output pairs demonstrating the exact format and style you want. Models learn patterns better from demonstrations than descriptions. Tell the model what TO do, not what NOT to do. "Write in flowing prose paragraphs" beats "Don't use bullet points." Positive patterns guide behavior more effectively than prohibitions. High-stakes operations (security, payments, data migrations) need exact instructions with no freedom. Creative tasks (writing, analysis, code review) benefit from high freedom with principles over procedures. Prompts edited by multiple people or composed from multiple sources degrade over time. Each engineer adds emphasis for their concern, implicitly diluting others. Periodically review the entire prompt as a system: remove duplicates, tighten language, rebalance intent. A holistic view beats "prompting harder."

</essential_principles>

What would you like to do?

1. Write a new prompt or system instruction
2. Review/improve an existing prompt
3. Adapt a prompt for a different model
4. Get guidance on a specific technique

Wait for response before proceeding.

| Response | Workflow | |----------|----------| | 1, "write", "create", "new", "draft" | `workflows/write-prompt.md` | | 2, "review", "improve", "optimize", "fix" | `workflows/review-prompt.md` | | 3, "adapt", "convert", "migrate", "port" | `workflows/adapt-for-model.md` | | 4, "guidance", "technique", "help", "how" | Clarify specific topic, then route to relevant reference |

Intent-based routing:

• "system prompt for Claude" → workflows/write-prompt.md + references/claude-specific.md
• "why isn't my prompt working" → workflows/review-prompt.md
• "convert GPT prompt to Gemini" → workflows/adapt-for-model.md
• "how do I use few-shot" → references/universal-techniques.md

<quick_reference>

Universal Structure:

<role>Who the model is</role>
<context>Background information</context>
<instructions>What to do</instructions>
<examples>
<example>
<input>Sample input</input>
<output>Expected output</output>
</example>
</examples>
<constraints>Boundaries and limitations</constraints>
<output_format>How to structure response</output_format>

Model Selection:

• Claude: Best for nuanced reasoning, long context, agentic tasks. Responds well to XML, context explanations, thinking blocks.
• GPT: Strong instruction adherence, scope discipline. Benefits from explicit length constraints, schema definitions.
• Gemini: Excellent multimodal, strong few-shot learning. Use input/output prefixes, positive examples only.

</quick_reference>

<reference_index> All in references/:

Techniques: universal-techniques.md (XML structure, few-shot, chain-of-thought, output formatting) Claude: claude-specific.md (Claude 4.x best practices, thinking, tool use, agentic patterns) GPT: gpt-specific.md (GPT-5 patterns, verbosity control, scope discipline) Gemini: gemini-specific.md (Gemini 3 patterns, prefixes, temperature, multimodal) Avoid: anti-patterns.md (common mistakes across all models) </reference_index>

<workflows_index> All in workflows/:

File	Purpose
write-prompt.md	Create new prompts from scratch
review-prompt.md	Audit and improve existing prompts
adapt-for-model.md	Port prompts between models
</workflows_index>

<success_criteria> A well-crafted prompt:

• States the task explicitly with clear success criteria
• Provides context explaining why instructions matter
• Uses XML structure for distinct sections
• Includes 2-3 few-shot examples when format matters
• Matches specificity to task stakes
• Works reliably across multiple test cases
• Avoids known anti-patterns for the target model </success_criteria>