Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jamestorrevillas/prompt-engineering
Use this skill when writing, improving, or debugging prompts for any AI model — Claude, GPT, Gemini, or Copilot. Also use when designing plan-before-execute workflows, verification patterns, self-improvement loops, or structuring AI instructions for maximum clarity and output quality. Trigger on keywords: prompt, prompt engineering, instruct AI, system prompt, few-shot, chain-of-thought, AI instruction, prompt template, prompt pattern.
Passed 24 of 24 test cases with the skill, and 22 of 24 without it.
2 fixed22 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
When an LLM generates invalid SQL during a chat session, what steps should be included in the user's feedback prompt to prevent repeating the mistake?
| Checked | Without skill | With skill |
|---|---|---|
| Instructs providing the execution error logs along with the failing SQL query in the feedback prompt. | Missed | Passed |
| Instructs prompting the model to identify the root cause before rewriting the query. | Passed | Passed |
The instructions your model reads when the skill loads.
A great prompt is not a magic spell — it's a specification. The more precisely you define the goal, context, constraints, and output format, the more reliably the AI performs. Think of prompting like writing a function signature: the model is the implementation, you are the interface designer.
The Golden Rule: If the output isn't what you wanted, the problem is almost always in the prompt — not the model.
Every effective prompt has four components:
ROLE: Who the AI should be (expertise, perspective, voice)
GOAL: What you want done (specific, unambiguous task)
CONTEXT: Relevant background, data, constraints, examples
OUTPUT: Exact format, length, structure of the response
ROLE: You are a senior TypeScript developer with expertise in React and Next.js.
GOAL: Review this component for performance issues and suggest specific improvements.
CONTEXT: This is a client component in Next.js 15 App Router.
Performance is critical — this renders on every keystroke.
[paste code here]
OUTPUT: List issues as BLOCKER / WARNING / SUGGESTION with specific fix for each.
Ask directly with no examples. Works for well-understood tasks.
Write a conventional commit message for this diff: [diff]
test cases passed, vs 22 / 24 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.