promptify_skill

Overview

This skill transforms user requests into precise, detailed prompts crafted for AI models. It rewrites input as a specification-style prompt that removes ambiguity and supplies exactly the instructions a model needs to produce the desired output. Use when you want higher-quality, more consistent AI responses from any model.

How this skill works

The skill reads the user’s original request, identifies missing context and necessary constraints, and plans a concise rewrite that preserves intent without adding new facts. It outputs a clean, specification-like prompt formatted for direct use with an AI model, keeping length proportional to the original input and avoiding unnecessary complexity.

When to use it

• You want a clearer prompt that yields consistent, accurate model outputs.
• You have a vague or under-specified task and need it turned into a precise instruction.
• You need to adapt a user request for use with a specific model or API.
• You want to improve response quality without changing the original intent.
• You need a prompt that can be copy-pasted into an AI interface or pipeline.

Best practices

• Provide the original request and any essential context or constraints up front.
• Do not expect the skill to invent missing facts; supply details you require in outputs.
• Specify desired output format (e.g., JSON, bullet list, code) when relevant.
• Indicate tone, length, and audience if those affect the result.
• Use the produced prompt directly with the target model; avoid further casual edits that reintroduce ambiguity.

Example use cases

• Convert 'Write a marketing email about our new product' into a detailed prompt specifying audience, tone, key points, and CTAs.
• Rewrite a vague research question into a step-by-step prompt that asks for methodology, sources, and summary.
• Transform a feature request into a prompt that yields acceptance criteria, example inputs/outputs, and edge cases.
• Produce a prompt that instructs an LLM to output structured JSON suitable for downstream parsing.
• Refine a user’s design brief into actionable deliverables, file formats, and constraints.