agentsclimarketplace

Ui ux design

Skill mblauberg/provenant/skills/ui-ux-design

Portable equal-primary Claude and Codex agent harness for a governed agentic SDLC

Install
npx -y skills add mblauberg/provenant --skill ui-ux-design

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 2 stars2 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.

What its author says it does

Copied from the file, not written here

Use for frontend UI/UX: read-only review (default — visual, accessibility, responsive, interaction) or authorised design, redesign, and live iteration. Not for source-diff review or React profiling; use code-review or react-performance.

SKILL.md

2.7 KB, as published. Nobody here has run it

<!-- Modified from Impeccable for this harness; see the repository THIRD_PARTY_NOTICES.md. -->

UI/UX design

Review or design production-grade frontend interfaces. Two branches share one entry point; the model picks the branch from what the request authorises, never a slash command.

Branches

  • review (default, read-only). Evidence-bearing critique of the rendered UI: visual hierarchy, accessibility, responsiveness, interaction states, copy and brand fit. No Write/Edit/NotebookEdit calls. Load review.
  • design/make (write authority required). Design, implement, redesign or polish an interface, including the interactive live codegen protocol. Load setup, then command routing; for live browser work, live.

A request framed as review stays on the review branch even when a fix looks obvious; escalate to design/make only under an explicit authority grant naming implement (or this skill under implement) as action-owner. Never infer write authority from review findings alone.

Lifecycle boundary

This skill supplies the frontend review and design methods; it is not a delivery lifecycle. Run every source-changing command inside implement. Route unsettled design intent through scope, design-document placement through engineering-docs, general source-diff review through code-review, and measured React performance work through react-performance. This skill cannot accept, release or certify its own work.

Detector evidence engine

scripts/detector/ is an antipattern and contrast-ratio engine (static HTML/CSS analysis, regex text scanning, full browser rendering) shared by both branches:

node "${AGENTS_HOME:-$HOME/.agents}/skills/ui-ux-design/scripts/detect.mjs" [file-or-dir-or-url...]

Review treats it as one evidence lane among several, never a substitute for manual inspection. Design/make may run it after edits to check for contrast/antipattern regressions; a clean result is evidence, not proof of completion.

Routing (design/make)

Command routing holds the full command catalogue, lookup tables and dispatch rules. No argument shows the grouped menu; a known first word follows its reference; an unknown first word is general design context. Implement complexity proportional to the chosen aesthetic; interpret context creatively and reject category-derived defaults.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.