Stats
Actions
Tags
From antigravity-awesome-skills
Renders UI and applies deterministic layout audit (centroid, optical-center, pixel-oracle) plus Nielsen usability audit via separate judge. Proves balance and usability instead of relying on model's eye.
How this skill is triggered — by the user, by Claude, or both
Slash command
/antigravity-awesome-skills:deterministic-designThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use to catch AI-generated UI that "looks off", is misaligned or centered-mush, or fails usability — when you need to PROVE a layout is balanced and usable instead of trusting the model's eye. Compose it with any taste/token design skill before reporting design "done".
Use to catch AI-generated UI that "looks off", is misaligned or centered-mush, or fails usability — when you need to PROVE a layout is balanced and usable instead of trusting the model's eye. Compose it with any taste/token design skill before reporting design "done".
Source: connerkward/deterministic-design-skill (MIT).
Thesis: determinism beats AI randomness. A model can't trust its own eye on layout — so don't. Render the UI and measure it.
Two sub-skills (load as needed):
layout-audit.js computes centroid / optical-center / pixel-oracle
balance and draws an annotated screenshot. Numbers, not vibes. Plus a render-then-
critique vision loop.This improves existing design skills (including the default Anthropic one) by adding the layer they lack — it doesn't just advise on taste, it renders, measures, and judges the output. Composable with any design skill.
In central this lives as a subdir of ckw-design; it publishes separately as
deterministic-design-skill (its own distribution) via publish-skill. One of the two
flagship narratives — the determinism one; its sibling is human-in-the-loop (lookdev).
npx claudepluginhub sickn33/antigravity-awesome-skills --plugin antigravity-bundle-aas-mobile-app-builderAudits existing UI pages for visual hierarchy, spacing, alignment, and priority issues. Systematically prioritizes fixes to elevate designs to production quality.
Renders UI changes and judges layout from actual pixels, not CSS tokens. Diagnoses spacing, grouping, visual hierarchy, and alignment issues. Supports reference-match mode where a user-provided screenshot is the spec.
Scores visual designs across 8 VisAWI-aligned dimensions (layout, typography, color, etc.) 1-5 each (40 max), provides anti-pattern checklists and audit workflows for quantitative comparisons.