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.
npx skills add varunk130/ai-ux-skill-library --skill ai-ux-evalgit clone --depth 1 https://github.com/varunk130/ai-ux-skill-libraryWrote 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.
[](https://agentmods.dev/skills/varunk130/ai-ux-skill-library/ai-ux-eval)<a href="https://agentmods.dev/skills/varunk130/ai-ux-skill-library/ai-ux-eval"><img src="https://agentmods.dev/badge/skills/varunk130/ai-ux-skill-library/ai-ux-eval/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.
<a href="https://agentmods.dev/skills/varunk130/ai-ux-skill-library/ai-ux-eval"><img src="https://agentmods.dev/badge/skills/varunk130/ai-ux-skill-library/ai-ux-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.02045 |
| Opus 5.5 | $0.00035 | $0.00818 |
| Sonnet 5.5 | $0.00017 | $0.00409 |
| Haiku 4.5 | $0.00009 | $0.00204 |
Grade A, and why
ai-ux-eval 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI UX Eval
Turn "this AI feature feels off" into a number you can defend, compare, and re-run next sprint. The RUBRIC framework builds an evaluation that produces the same score for the same experience regardless of who runs it.
Core Principle
A UX eval is a decision instrument, not a report card. Every criterion must change what the team does next. If a score can move from 40 to 80 and nobody ships anything differently, the criterion is decoration - cut it.
This skill is the measurement counterpart to the design skills in this library: the other frameworks tell you what good looks like, RUBRIC tells you whether you built it.
The RUBRIC Framework
| Letter | Principle | Design Question |
|---|---|---|
| R | Represent Real Use | Does the eval set sample real user journeys, including the messy and adversarial ones? |
| U | Unitize Criteria | Is each criterion one observable behavior that two raters would score identically? |
| B | Band the Scores | Do scores map to named bands that each carry a ship / no-ship consequence? |
| R | Rate Reliably | Are raters - human or model - calibrated against gold examples, with agreement measured? |
| I | Instrument the Signal | Is the signal measured in the running product, not estimated in a workshop? |
| C | Compare to Baseline | Is every number compared against a prior version, a control, or a competitor? |
The Four Quality Dimensions
Score every AI surface on these four dimensions. They map 1:1 to the helpers in python_runtime/heuristics.py, so a manual review and an automated run produce comparable numbers.
| Dimension | What It Measures | Primary Design Skill | Runtime Helper |
|---|---|---|---|
| Transparency | Can the user tell what the AI did and why? | ai-trust-transparency (GLASS) |
score_transparency() |
| Recoverability | Can the user recover gracefully when the AI is wrong? | ai-error-resilience (RECOVER) |
score_recoverability() |
| Predictability | Can the user anticipate what the AI will do next? | ai-agent-ux (AUTONOMY) |
score_predictability() |
| Trust | Is the user's confidence calibrated to actual reliability? | ai-safety-guardrails (SHIELD) |
score_trust() |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 164 lines · 87 tokens per session scan A 62c0363d82a6
ai-ux-eval is a skill published in the GitHub repository varunk130/ai-ux-skill-library (3 stars, last pushed 12d ago), licensed MIT. It adds 87 tokens to every session and 2,045 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
design-dna
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides…
component-family-consistency
Buttons, inputs, badges and pills share radius, colour logic, shadow, border and spacing. Use when building or reviewing a component library.
extract-design
Extract colours, typography, spacing, components and W3C design tokens from a live website with Dembrandt. Use when you need a site's real tokens or want to seed a design system from it.
modular-scale-typography
Ratio-based type scale where every size relates to the others. Use when defining font sizes or type tokens, or when typography feels arbitrary.
data-display-and-selection
View modes, row selection, mass actions, sorting, filters, search and table patterns. Use when designing data tables, listings, file browsers or any collection.
modal-and-overlay-patterns
Modals, drawers, bottom sheets and popovers, each with its scope and blocking level. Use when designing dialogs, confirmations, side panels or action sheets.