playbooks

home / skills / intellectronica / agent-skills / promptify

promptify skill

/skills/promptify

This skill rewrites user requests into precise, actionable prompts for AI models, ensuring clear instructions and complete context.

npx playbooks add skill intellectronica/agent-skills --skill promptify

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
1.8 KB
---
name: promptify
description: Transform user requests into detailed, precise prompts for AI models. Use when users say "promptify", "promptify this", or explicitly request prompt engineering or improvement of their request for better AI responses.
---

# Promptify

Transform user requests into detailed, precise prompts optimised for AI model consumption.

## Core Task

Rewrite the user's request as a clear, specific, and complete prompt that guides an AI model to produce the desired output without ambiguity. Treat the output as specification language, not casual natural language.

## Process

1. **Read and understand** - Read the user's request carefully to understand the full context, intent, and all details
2. **Plan the rewrite** - Consider what specific information, instructions, or context the AI model needs to fulfill the request effectively
3. **Rewrite as a detailed prompt** - Transform the request into a precise prompt with clarity, specificity, and completeness

## Writing Guidelines

### Structure

- Begin with a single short paragraph summarising the overall task
- Use headings (##, ###, ####) for sections only where appropriate (no first-level title)
- Use **bold**, _italics_, bullet points (`-`), and numbered lists (1., 2.) liberally for organisation
- Never use emojis
- Never use `*` for bullet points, always use `-`

### Language

- Use plain, straightforward, precise language
- Avoid embellishments, niceties, or creative flourishes
- Think of language as specification/code, not natural language
- Be clear and specific in all instructions

### Content

- Keep the prompt concise: 0.75X to 1.5X the length of the original request
- Do not add or invent information not present in the input
- Do not include unnecessary complexity or verbosity

## Output

Provide only the final prompt as markdown, without additional commentary or explanation.

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.

FAQ

Will you add information not present in my request?

No. The skill preserves intent and only restructures or clarifies; it will not invent facts or add new content beyond necessary clarifying questions.

How long will the rewritten prompt be?

Prompts aim to be concise and proportional to the original request, typically between 0.75x and 1.5x the input length while improving specificity and structure.