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 Carlos-Dominguez-faber/criterio --skill ui-vocabularygit clone --depth 1 https://github.com/Carlos-Dominguez-faber/criterioWrote 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/carlos-dominguez-faber/criterio/ui-vocabulary)<a href="https://agentmods.dev/skills/carlos-dominguez-faber/criterio/ui-vocabulary"><img src="https://agentmods.dev/badge/skills/carlos-dominguez-faber/criterio/ui-vocabulary/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/carlos-dominguez-faber/criterio/ui-vocabulary"><img src="https://agentmods.dev/badge/skills/carlos-dominguez-faber/criterio/ui-vocabulary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00158 | $0.01796 |
| Opus 5 | $0.00079 | $0.00898 |
| Sonnet 5 | $0.00032 | $0.00359 |
| Haiku 4.5 | $0.00016 | $0.00180 |
Grade A, and why
ui-vocabulary 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ui-vocabulary
Glosario español-inglés de componentes, patrones y estilos de interfaz, más el brief para pedírselos al agente.
Por qué existe
La causa raíz número uno de la UI genérica no es el modelo: es el vocabulario. Si pides "un menú bonito", el agente devuelve el promedio estadístico de todos los menús que vio. Si pides "un command palette con búsqueda difusa, agrupada por sección, con atajos visibles a la derecha", devuelve otra cosa.
El ciclo que enseña esta skill es corto: veo algo → sé cómo se llama → lo pido por su nombre → el output deja de ser genérico.
Existen diccionarios visuales excelentes en la web para esto. Este vive dentro del agente, funciona sin conexión, y está en español, que es lo que le falta al resto.
Procedimiento
Paso 1 — Entender qué describe el usuario
El usuario casi nunca llega con el nombre. Llega con una descripción coloquial, una captura, una URL, o un gesto ("eso que se abre desde abajo").
Antes de buscar en el glosario, aclara tres cosas si no están claras:
- Plataforma. Web, iOS, Android, macOS o escritorio. Importa porque el mismo elemento tiene nombres distintos en cada una, y usar el nombre de la plataforma equivocada produce el componente equivocado. Un bottom sheet de móvil y un drawer de web se parecen y no son lo mismo.
- Qué lo dispara. Hover, clic, scroll, atajo de teclado, o aparece solo. Esto separa un tooltip de un popover, y un toast de un banner.
- Si bloquea o no. Un elemento que impide interactuar con el resto de la pantalla es modal; uno que no, no lo es. Es la distinción que más se confunde y la que más cambia el código.
Paso 2 — Buscar en el glosario
Lee references/glossary-es.md. Está organizado por categoría y cada entrada trae cuatro columnas: nombre en inglés, nombre en español, cómo lo describe la gente, y cuándo usarlo.
Busca primero por la columna coloquial. Es la que corresponde a cómo llegó el usuario.
Si hay dos candidatos parecidos, preséntalos juntos con la diferencia. Ese contraste es donde está el aprendizaje: "lo que describes puede ser un popover o un tooltip; la diferencia es que el tooltip solo informa y aparece con hover, y el popover puede tener botones y se abre con clic. ¿Cuál necesitas?"
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.
- 12d ago First seen · 107 lines · 158 tokens per session scan A 1573d866c0e2
ui-vocabulary is a skill published in the GitHub repository Carlos-Dominguez-faber/criterio (55 stars, last pushed 1mo ago), licensed MIT. It adds 158 tokens to every session and 1,796 once invoked, about $0.0008 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.
Other skills, from other repositories
write
Rewrites and polishes prose in Chinese or English, removes AI-like wording, and reviews product localization copy while preserving intent for drafts, docs, release notes, launch copy, and social posts. Use when users ask in any language to draft, rewrite, proofread, localize, polish release notes, remove AI-like…
inclusive-design
Use when working on inclusion, i18n/localization, global name/address forms, low-end devices, slow/metered networks, affordability, or first-time/low-confidence users; not WCAG/screen readers (see accessibility).
canva-translate-design
Translate all text in a Canva design to another language, creating a translated copy. Faster than manually copying and editing each text box in Canva's editor. Use when users say "translate my design to [language]", "make a Spanish/French/etc version", or "localize my Canva design".
harden
Production-readiness pass — audits and implements the full non-happy-path matrix: loading skeletons, empty states, error messages, partial data, i18n, offline, permissions, and first-run guidance. Use when preparing a surface for production or when the user says "it crashes on empty data" / "there's no loading state"…
global-toolbar-controls
Quick global settings — currency, language, region, units — belong in a persistent, low-profile location such as a header toolbar or footer. These controls are frequent but not primary, so they use small typography and stay out of the main content hierarchy. Use when designing global selectors, locale switchers, or…
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.