ui-taste

ui-taste is a skill for Claude Code, Codex from Orkas-AI/Orkas. It costs 3 tokens per session (1,314 once invoked), scanned A, original, MIT.

A design-review guide for making interfaces feel specific to their product, audience, and brand instead of generic. It focuses on the visual direction, subject matter, and the product's main task.

In plain words
What is it for?
Use it for expressive restyling, brand-led visual concepts, critiques of visual taste, and requests for a less generic interface.
Why use it?
It helps identify why a design feels interchangeable or overly machine-made and gives the agent a basis for a more distinctive direction.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for expressive restyling, brand-led visual concepts, critiques of visual taste, and requests for a less generic interface.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orkas-ai/orkas/ui-taste
About the project

Orkas is a desktop application for commanding a team of AI agents through one chat, with a commander model assigning work to specialist agents in parallel or in sequence. People use it to coordinate research, writing, presentations, and software tasks while keeping files on their computer. The catalogue includes skills for extending the agents available to Orkas.

Orkas-AI/Orkas · 1,911 stars · on GitHub · orkas.ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Orkas-AI/Orkas --skill ui-taste
Clone the repo
git clone --depth 1 https://github.com/Orkas-AI/Orkas

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ui-taste

README.md
[![agentmods](https://agentmods.dev/badge/skills/orkas-ai/orkas/ui-taste/github.svg)](https://agentmods.dev/skills/orkas-ai/orkas/ui-taste)
Your own site
<a href="https://agentmods.dev/skills/orkas-ai/orkas/ui-taste"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/ui-taste/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ui-taste

Your own site · 80×15
<a href="https://agentmods.dev/skills/orkas-ai/orkas/ui-taste"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/ui-taste.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,314 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Memory Poisoning · line 77
    Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
    Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00003 $0.01314
Opus 5 $0.00002 $0.00657
Sonnet 5 $0.00001 $0.00263
Haiku 4.5 $0.00000 $0.00131

Measured 12d ago against content hash a7ffd132f77f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ui-taste scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

resources/builtin/marketplace/agents/bcfcb4921dce/skills/ui-taste/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ui-taste

Use this specialist when the user explicitly asks for a less generic/less AI-looking direction, an expressive restyle, brand-led visual thesis, or a taste critique. ui-design-executor already carries the baseline subject grounding and visual thesis for ordinary work.

Ground The Design In The Subject

Before choosing a style, identify:

  • The concrete product or subject, not only a broad category such as “AI SaaS”.
  • The audience and pressure they feel: speed, trust, comparison, learning, creativity, delight, or compliance.
  • The page's single job and the primary workflow that proves it.
  • The subject's own visual material: tools, objects, environments, vocabulary, data shapes, imagery, or physical qualities.
  • Real or representative content that makes this artifact belong to the product.

Typography, structure, imagery, copy, and motion should come from this evidence. A design that could keep the same layout and copy after swapping the product name has not gone far enough.

Visual Thesis

Before rendering a design, define:

  • product_type: operational tool, creative workspace, consumer product, developer tool, marketplace, education, finance, content, or brand site.
  • subject: concrete product world and the material or behavior the UI can borrow from.
  • audience_pressure: the user's dominant need.
  • single_job: what this page must help the user complete or understand.
  • primary_workflow: the action users repeat.
  • density: compact, balanced, spacious, or editorial.
  • tone: 2 precise words, not "modern" or "clean" alone.
  • palette_roles: 4–6 named functional colors or existing product tokens.
  • type_roles: deliberate display/title, body, label, and data choices as applicable.
  • layout_concept: one sentence explaining how composition supports the job.
  • signature_device: one subject-specific visual rule, not decoration.
  • aesthetic_risk: one intentional choice that gives the artifact a point of view without harming usability.
  • anti_template_rejection: what generic idea you rejected.

Read the full file on GitHub · 123 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 123 lines · 3 tokens per session scan A a7ffd132f77f

Subscribe to this mod's changes

ui-taste is a skill published in the GitHub repository Orkas-AI/Orkas (1,911 stars, last pushed yesterday), licensed MIT. It adds 3 tokens to every session and 1,314 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.