AI Prompts Library

Compress this system prompt without changing model behaviour. It is billed on every single request, so every token matters.

Process:
1. Mark every instruction that is redundant with the model's default behaviour. Modern models do not need to be told to be helpful or to format code in code blocks.
2. Mark every instruction that duplicates another one in different words.
3. Mark every example that is not earning its token cost, meaning the behaviour it demonstrates is already covered by an explicit instruction.
4. Mark every hedge and politeness token that carries no instruction.
5. Identify anything ordered badly. Constraints belong near the top, formatting near the bottom.

Then output:
- The compressed prompt
- Token count before and after
- A list of anything you removed that carries ANY behavioural risk, so I can decide rather than discover

Do not remove anything whose effect you are unsure about. Flag it instead.

System prompt:
[PASTE]

Restructure this prompt so prompt caching actually works on it. Caching only helps when the prefix is byte-identical across requests, and most prompts break that without realising.

Do this:
1. Identify every part that is stable across requests and every part that varies.
2. Find the cache breakers: timestamps, request ids, user names, randomised example order, or anything dynamic sitting above stable content.
3. Reorder so all stable content comes first, in a fixed order, and everything variable comes last.
4. Mark where the cache breakpoint should be set.
5. Estimate the cached fraction before and after, and the resulting cost change.

Call out anything that cannot move without changing behaviour, and say why.

Prompt:
[PASTE]
What varies per request:
[DESCRIBE]

You are a prompt engineering expert who helps people write more effective prompts for AI models. Given a task description, generate an optimized prompt that will produce the best results.

**Task:** [DESCRIBE WHAT YOU WANT THE AI TO DO]
**Target AI Model:** [GPT-4 / Claude / Gemini / Llama / General]
**Output Format:** [Text / JSON / Code / Markdown / Structured data]
**Quality Level:** [Draft / Professional / Publication-ready]

**Prompt Engineering Principles to Apply:**

1. **Role Assignment:**
   - Assign a specific expert persona that matches the task
   - Include years of experience and domain expertise
   - Specify the audience they communicate with

2. **Context Setting:**
   - Provide all necessary background information
   - Define the scope (what to include and exclude)
   - Set constraints and boundaries

3. **Task Specification:**
   - Use clear, unambiguous instructions
   - Break complex tasks into numbered steps
   - Specify the output format exactly
   - Include examples of desired output (few-shot prompting)

4. **Quality Controls:**
   - Define what "good" looks like (evaluation criteria)
   - Specify what to avoid (common mistakes, anti-patterns)
   - Request self-verification steps
   - Ask for confidence levels on uncertain items

5. **Advanced Techniques:**
   - Chain-of-thought: Ask the model to reason step by step
   - Self-consistency: Request multiple approaches and compare
   - Structured output: Use templates and schemas
   - Iterative refinement: Build in revision cycles

6. **Output Formatting:**
   - Specify headings, bullet points, code blocks
   - Define length constraints (word count, page count)
   - Request metadata (confidence, sources, alternatives)

**Generate:**
- The optimized prompt
- Explanation of each technique used and why
- 3 variations for different emphasis (concise, detailed, creative)
- Tips for iterating on the prompt based on initial results

**Output**: The optimized prompt plus a brief guide on how to use and refine it.