Write a great skill on Air

Learn how to write, configure, and test great custom AI skills in Air for better creative workflows.

Written by Charlotte Maguy
Updated over a week ago

The anatomy of a skill prompt

Every good skill prompt has four parts, in this order:

1. Goal statement — One or two sentences describing what the skill does and what must stay the same. This is the most important part. Read at the beginning, it sets the intent for everything that follows.

2. Input check — Before doing anything, confirm the right assets were provided. If something is missing, ask for it clearly.

3. Steps — The actual instructions, in order. Keep these short and concrete.

4. Output — What to deliver and in what format.

Configure your skill

When you create a new skill, you will set up its basic details and provide the instructions that power the AI workflow. Fill out the name, slash command, description, and source asset type, then paste your prompt into the Instructions field.

To get the best results from your custom skills, follow these best practices when writing your instructions:

Put preservation in the goal

If something must not change (dimensions, content, colors, composition), say so in the goal line. The AI reads the goal first and uses it to frame everything else.

Less is more

More instructions doesn't always mean better results. Start minimal. Add a line only when you've actually seen a problem it would fix.

Be specific about what you do not want

Whenever the AI could reasonably pick something close-but-wrong, close the gap explicitly.

Use the edit operation for photos

For skills where the real photo must be preserved, always specify edit explicitly. Otherwise the AI may regenerate the image from scratch — which loses all the original detail.

Always include an input check

Every skill should start by confirming it has what it needs. If a required image is missing, the skill should ask the user to provide it.

Support multiple images explicitly

If you want your skill to work on batches, say so. Otherwise, the AI may only process the first image.

Try concrete analogies for tricky operations

Abstract instructions often misfire. If you're describing something visual or spatial, a concrete analogy beats a technical description.

Set sensible defaults

If your skill has configurable settings, pick a good default and let users override it inline.

Test your skill

Before publishing, test your skill with different aspect ratios, inputs that are slightly wrong, and very simple and complex subjects.

Know what Skills can't do reliably (yet)

Some operations are inherently inconsistent. Keep in mind the limitations of AI when setting expectations.

Summary: The Checklist for a Publishing Great Skill

☑️ You've included a goal statement that states the objective and what must NOT change
☑️ Your skill checks for required inputs and asks clearly if something's missing
☑️ Skill Instructions are as short as possible while still being specific
☑️ You've described what you don't want, not just what you do
☑️ If the skill edits a real photo, you've specified the edit operation
☑️ You've tested on at least 5 different assets
☑️ You've tested what happens when the user provides the wrong input
☑️ Output format is clearly specified (PNG, transparent background, dimensions, etc.)

Now that you know how to write a great skill, learn how to manage and access them in your workspace. Check out our guide on Explore Skills to dive deeper into command-driven workflows.