design-build
Skill10 starsChanged 27 days agoMITView on GitHub
Generate distinctive, production-grade frontend UI code from a design system — starting from an on-brand, accessible, rendered HTML scaffold and elaborating with taste that avoids the generic-AI-slop aesthetic. Trigger when the user says "build the site", "make the UI", "design and code", "create a landing page", "build a component", or wants polished frontend that looks intentional rather than templated.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- rschuft/ai-frontend-skill-packstheir own version, first seen Nov 15, 2026
- yagizdo/quivertheir own version, first seen Nov 15, 2026
- PRoBoT2004/deck-skilltheir own version, first seen Nov 8, 2026
- boman-ng/skillstheir own version, first seen Oct 25, 2026
- accountsFON/Claude-Skillstheir own version, first seen Mar 25, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- yagizdo/quiver★ 16same name
- rschuft/ai-frontend-skill-packs★ 4same name
- boman-ng/skills★ 2same name
- accountsFON/Claude-Skills★ 0same name
- PRoBoT2004/deck-skill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- blast-promptSkill
- client-outreachSkill
- content-draftSkill
- copywritingSkill
- csv-to-reportSkill
- design-accessibilitySkill
- design-croSkill
- design-dimensionsSkill
- design-motionSkill
- design-researchSkill
- design-system-genSkill
- design-system-persistSkill
- design-tokens-emitSkill
- design-visual-qaSkill
- html-extractSkill
- parallel-buildSkill
- portable-html-portSkill
- qa-gateSkill
- route-codex-reviewSkill
- route-gemini-contextSkill
- route-three-brainSkill
- seo-auditSkill
- seo-backlinksSkill
- seo-clusterSkill
- seo-competitor-pagesSkill
- seo-content-briefSkill
- seo-contentSkill
- seo-dataforseoSkill
- seo-driftSkill
- seo-ecommerceSkill
- seo-firecrawlSkill
- seo-geoSkill
- seo-googleSkill
- seo-hreflangSkill
- seo-image-auditSkill
- seo-image-genSkill
- seo-local-unifiedSkill
- seo-pageSkill
- seo-programmaticSkill
- seo-schemaSkill
- seo-sitemapSkill
- seo-strategySkill
- seo-sxoSkill
- seo-technicalSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 37
Get the design system: Run design-system-gen if none exists.
- Very specific: line 64
Variants: If the user wants 2+, hand the brief + design system to parallel-build.
- Very specific: line 66
Pre-delivery: Run design-accessibility and qa-gate before handoff.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
design-build
Family: design Status: Stable
Purpose
The frontend code generator — and the payoff of the whole design loop. It takes a
design system (from design-system-gen) and renders a real, on-brand starting
page via render_page.py (semantic HTML5, the system's actual palette/type/
effects as CSS variables, prefers-reduced-motion fallback, :focus-visible
states, contrast-safe buttons), then elaborates it with taste. The differentiator
is the anti-slop discipline: distinctive type, color, and interaction instead of
the default gradient-purple, rounded-corner look — grounded in the chosen style's
characteristics from data/ui-styles.csv.
Triggers
- "build the site" / "make the UI" / "design and code"
- "create a landing page" / "build a component"
- "make this beautiful" / "production-grade frontend"
Inputs
- Design system (from
design-system-gen, or "generate one") - Page/component spec (from
blast-prompt, or free-text) - Stack (HTML+CSS+JS | React | Next.js | Vue | Svelte | Astro)
- Variants (1 = single build; 2+ = invokes
parallel-build)
Steps
- Get the design system. Run
design-system-genif none exists; save JSON. - Render the on-brand scaffold — a real, accessible starting point, not a blank
page:
(orpython3 "${CLAUDE_PLUGIN_ROOT}/scripts/design/render_page.py" --design-json ds.json --out page.html # use `py` on Windows if python3 is absent ($env:CLAUDE_PLUGIN_ROOT in PowerShell)--product-type/--industry/--keywordsto run the engine inline). - Elaborate with taste (anti-slop pass). Replace placeholder copy (use
copywriting), shape the sections to the brief, and add distinctive details that match the style'scharacteristicsfromdata/ui-styles.csv— reject the generic AI look. Honordata/ux-rules.csv(one primary CTA, contrast, etc.). Apply the tell→build-move mapping and the chart-handling guidance inreferences/design-build/anti-slop.md(it applies the sharedreferences/shared/anti-slop-principles.mdrubric at build time). When a section needs a chart, let the data shape pick it deterministically rather than defaulting to a bar or pie:
It returns a chart type, an A/B/C accessibility grade + fallback, apython3 "${CLAUDE_PLUGIN_ROOT}/scripts/design/gen_charts.py" --shape time-series-multi --series 4 --colors "#1f77b4,#ff7f0e" # use `py` on Windowsvolume_warningwhen the series/point count overflows the chart's readable band, and (with--colors) a series-color contrast check reusing the engine's WCAG luminance. The reasoning behind the shape→chart table is inreferences/design-build/chart-selection.md. - Target the stack. For HTML+CSS+JS, build straight from the scaffold. For
React/Vue/etc., translate the scaffold's structure + tokens into components
(use
design-tokens-emitfor the token file). - Variants. If the user wants 2+, hand the brief + design system to
parallel-build. - Pre-delivery. Run
design-accessibilityandqa-gatebefore handoff.
Outputs
| Output | What it contains | Format | Quality bar (how it is scored) |
| Built UI | Production frontend elaborated from the rendered on-brand scaffold | HTML/CSS/JS or framework components | Clears the intentionality checklist and passes the swap test in references/design-build/anti-slop.md; keeps the scaffold's a11y guarantees (semantic HTML, focus-visible, reduced-motion, AA contrast) |
| Build manifest | Tokens used, sections built, what was elaborated vs. scaffolded, and the one-sentence reason for each brand deviation | md / JSON | Every non-default choice is defensible in one sentence; no unexplained default shipped |
| Charts / data marks (if any) | Chart type matched to data shape, series colors from tokens, text alternative | inline SVG / component | Mark fits the data shape; every series/label clears AA; meaning never by hue alone; no fabricated data point |
Filed to: the user's project workspace, never into the plugin.
Error Handling
| Condition | Detection | Behavior (degrade, never fail) | User-facing message |
| No design system yet | no design-system JSON provided | run design-system-gen first, then build | "Generated a design system first so tokens stay consistent." |
| Renderer script unavailable | render_page.py missing or errors | build from the design-system JSON by hand using the same tokens/a11y contract | "Scaffold renderer unavailable — built from tokens directly; a11y contract preserved." |
| Copy is placeholder | headline/body still generic on review | route to copywriting for concrete, specific copy before handoff | "Replaced placeholder copy — generic text is slop, not a shippable draft." |
| 2+ variants requested | user asks for variants | hand brief + design system to parallel-build (shared tokens) | "Dispatching N variants via parallel-build; all share one token set." |
| Internal-tool build | user requests "default styling" mode | skip the distinctiveness pass; keep the accessible baseline | "Built the plain accessible baseline — skipped the distinctiveness pass as requested." |
| Bad / empty spec | nothing to build against | ask for the page/component spec; invent nothing | "Give me the page or component spec (or say 'landing page') and I'll build it." |
Dependencies
scripts/design/render_page.py(required) — Python 3.10+, standard library onlydesign-system-gen(tokens),data/ui-styles.csv+data/ux-rules.csv(taste constraints),copywriting(real copy),design-tokens-emit(component token files)scripts/design/gen_charts.py+data/chart-types.csv(optional — deterministic data-shape → chart recommendation with an a11y grade + series-color contrast check; method inreferences/design-build/chart-selection.md)
Notes
The renderer guarantees a baseline that's already semantic, responsive, and accessible — so the human/taste effort goes into distinctiveness, not boilerplate. For internal tools, the user can request "default styling" mode to skip the distinctiveness pass.
Related: for 2+ variants this skill hands the brief + tokens to parallel-build
(Step 5), which runs design-build per variant. That is a prose reference, not a
Dependencies edge, so the dependency graph stays acyclic.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

