# Prompt, Workflow, or Skill? Choose a Reusable Format for Your AI Task

Authored ToolFlowKit practice material. These records are teaching examples, not customer data, current vendor offers, or measured software results.

## Choose the smallest format that preserves the useful process

A larger package does not automatically make the model better. Choose based on what another operator needs to reproduce the reviewed task, and keep the format understandable without requiring them to reverse-engineer a previous conversation.

| Need | Starting format | What to include |
| --- | --- | --- |
| One bounded drafting or review task | Prompt plus source pack | Task, inputs, output, conditions, checks |
| Repeated work with stages and exceptions | Workflow instructions | Inputs, sequence, failure route, reviewer, handoff |
| Reusable instructions in a compatible agent host | Skill directory | Host-compatible metadata, instructions, examples, references, dependencies |

## What could the same task look like as a Skill package?

This is a proposed directory layout, not a universal Skill format. Match the instructions and any metadata to the host that will load it. Start with a plain prompt for one request; add files and scripts only when the task needs them. Permissions for sending messages, spending money, or changing accounts still belong to the execution host.

| File | Purpose | Practice contents |
| --- | --- | --- |
| SKILL.md | Instructions the chosen host can load | Name the quote-review task, input files, steps, and acceptance checks |
| examples/quotes.md | Expected interpretation | Currency and minimum-order example with freight pending |
| scripts/check-fields.py | Optional deterministic check | Validate required columns; no purchasing action |

Guide: https://toolflowkit.com/guides/prompt-workflow-skill

License: CC0 1.0.