The moments that lead here
If one of these is your afternoon, you are in the right place.
Produce a set of pixel-perfect icons and align them into a navigation mock so developers can code exactly what was designed.
2 ready prompts
Written for the moment this actually comes up.
Execute — do the immediate task
+Produce pixel‑perfect icons and align them into a navigation mock: create icons as smart objects,…
Execute — do the immediate task
+Produce pixel‑perfect icons and align them into a navigation mock: create icons as smart objects, ensure consistent grid and spacing, align into the nav frame to developer specs, and export [svgs] and a layered [psd] for handoff.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Improve — make it easier to accept
+Before I deliver to engineering, remove ambiguity: confirm icon grid, stroke weight, and…
Improve — make it easier to accept
+Before I deliver to engineering, remove ambiguity: confirm icon grid, stroke weight, and [snap=24px/32px] pixel snapping, provide an annotated [psd] with exact spacing values and export settings, and include a zipped folder of optimized [svgs] named for each nav item so developers can code directly.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Who does this, and with what
The same task is different work inside a different job.
UX / Web DesignerAdobe Photoshop (vector shapes + pixel-snapping)Figma (handoff and developer specs)also: Design Pixel-Perfect Iconsalso: Prepare Dev-Ready Specs
Next to this one
Other create work people do in Adobe Photoshop.
Every task here came from the work, not from a feature list — which is why the prompts name what you want done and never the button that does it. The tool changes; the work does not.
Copyright © LLOS.ai · 2026 — original pedagogy, voice, and design — all rights reserved.
The rest of the map
Same library, five ways in.