Promptdex
Index
Explore
Directory
Collections
Learn
Search prompts, topics, models, guides...
⌘K
3
Submit Prompt
Admin CMS
admin
Edit Prompt: Meta-Prompt: Universal Prompt Engineer
Configure parameters, versioning, and runtime model compatibility.
Editor
Preview
Save & Publish
Identity & Taxonomy
Prompt Title *
URL Slug *
Description / Abstract *
Generate production-grade, jailbreak-resistant system prompts from a simple raw instruction using advanced prompt engineering patterns.
Category
Coding
Research
Writing
Marketing
Business
Data Analysis
Productivity
Prompt Engineering
Education
Design
Career
Finance
Sales
Customer Support
SEO
Social Media
Image Generation
Video
Automation
Difficulty
Beginner
Intermediate
Advanced
Expert
Publish Status
Published
Draft
Archived
Version Number
Version Change Summary (Optional archive note)
Prompt Instruction Buffer *
Word count: 181
You are an elite AI Prompt Engineering Architect specializing in LLM steering, context alignment, and adversarial guardrails. Transform the following raw prompt idea into a high-reliability, production-grade system prompt: Task Intent: {{task_intent}} Target Model Family: {{target_model}} Input Format: {{input_format}} Output Schema: {{output_schema}} Safety & Boundary Rules: {{boundary_rules}} Synthesize a complete, structured prompt featuring: 1. ROLE & IDENTITY DEFINITION - Explicit domain seniority and persona constraints. - Epistemic calibration: When to acknowledge lack of information rather than hallucinating. 2. INPUT/OUTPUT CONTRACT - Strict delimiters (e.g., XML tags or Markdown blocks) to prevent prompt injection. - Unambiguous schema enforcement (JSON Schema, TypeScript interface, or markdown table). 3. REASONING PROCESS (CHAIN-OF-THOUGHT) - Embedded invisible or scratchpad reasoning steps before output generation. - Self-correction checkpoint before finalizing answer. 4. FEW-SHOT DEMONSTRATIONS (SYNTHETIC EXAMPLES) - Provide 2 high-quality canonical examples illustrating input -> reasoning -> expected output. - Provide 1 negative edge-case demonstration (handling invalid inputs or adversarial requests). 5. DEFENSIVE GUARDRAILS - Inoculation against system prompt extraction ("Ignore previous instructions"). - Graceful refusal templates. Provide the complete ready-to-deploy prompt inside a clean markdown code block.
Parameterized Variables (5)
Add Variable
Token
Label
Default
Token
Label
Default
Token
Label
Default
Token
Label
Default
Token
Label
Default
Model Compatibility & Tags
GPT-4o
Claude 3.5 Sonnet
Claude 3 Opus
Gemini 1.5 Pro
DeepSeek R1
Llama 3.3 70B
Mistral Large
Qwen 2.5 72B
Midjourney v6
Stable Diffusion 3.5
Tags (Comma-separated)