Deterministic design skill
Deterministic, measurable design verification — render the UI and PROVE it's balanced and usable instead of trusting the model's eye. Layout audit (centroid / optical-center / pixel-oracle balance via deterministic math, annotated screenshot) + a vision-judged Nielsen usability audit by a SEPARATE fresh-eyes judge. Use to catch AI-generated UI that "looks off", is misaligned / centered-mush, or fails usability — the measurement+judgment layer that token-and-taste design skills (including the default) don't have.From its SKILL.md
npx -y skills add connerkward/deterministic-design-skillAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.7 KB, 291 tokens by cl100k_base, as published. Nobody here has run it
deterministic-design
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):
- design-spatial — deterministic layout audit: explicit grid
- 8-pt spacing, and
layout-audit.jscomputes centroid / optical-center / pixel-oracle balance and draws an annotated screenshot. Numbers, not vibes. Plus a render-then- critique vision loop.
- 8-pt spacing, and
- design-ux — usability audit: scores the rendered UI against Nielsen's 10 + interaction heuristics via a SEPARATE fresh-eyes judge → prioritized fix list.
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).
What ships with it: 7 files
446.6 KB alongside SKILL.md
.claude-plugin/
- marketplace.json654 B
- plugin.json657 B
docs/
- balance-explorable.png29.2 KB
- demo.gif410.0 KB
Gives 0 of the 12 instructions most design frontend skills give in 291 tokens
Counted across 1,169 of the 1,878 authors here whose files we hold, read 2026-08-07
- Use CSS variables for color consistencyin 72 of 1169, across 23 files
- Commit to one bold aesthetic direction before codingin 72 of 1169, across 27 files
- Match implementation complexity to the aesthetic visionin 70 of 1169, across 20 files
- Add atmospheric background effects and texturesin 57 of 1169, across 9 files
- Use unexpected spatial compositions and layoutsin 56 of 1169, across 8 files
- Implement real working codein 55 of 1169, across 7 files
- Vary themes and aesthetics across different designsin 48 of 1169, across 7 files
- Launch chromium in headless modein 47 of 1169, across 4 files
- Close the browser when donein 47 of 1169, across 4 files
- Run provided scripts with help flag firstin 47 of 1169, across 4 files
- Wait for network idle statein 47 of 1169, across 4 files
- Use descriptive selectors for elementsin 47 of 1169, across 4 files
Said here and by no other author read
- measure the layout deterministically
- compute layout balance
- draw an annotated screenshot
- score the UI against usability heuristics
- use a separate fresh-eyes judge
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.