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 Uxcel-Lab/product-skills --skill buttonsgit clone --depth 1 https://github.com/Uxcel-Lab/product-skillsWrote 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/uxcel-lab/product-skills/buttons)<a href="https://agentmods.dev/skills/uxcel-lab/product-skills/buttons"><img src="https://agentmods.dev/badge/skills/uxcel-lab/product-skills/buttons/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/uxcel-lab/product-skills/buttons"><img src="https://agentmods.dev/badge/skills/uxcel-lab/product-skills/buttons.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 | $0.00076 | $0.02601 |
| Opus 5 | $0.00038 | $0.01300 |
| Sonnet 5 | $0.00015 | $0.00520 |
| Haiku 4.5 | $0.00008 | $0.00260 |
Grade A, and why
ux-buttons 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 10d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buttons Skill
How this skill behaves (read first)
This is a generative skill. The default failure modes are opposite: flat sameness (every action gets the same generic button, no hierarchy, vague "Submit/OK" labels, missing states) and decoration overload (every button raised, shadowed, branded, icon-stuffed). A checklist is not a mandate, so this skill gates:
- Establish context — platform, the screen's action hierarchy, brand personality, and whether any action is destructive.
- Apply the always-true core — hierarchy-driven type selection, action-verb labels, full state coverage, accessible sizing and contrast.
- Surface the stylistic levers (shape, elevation, icon-only, FAB, width strategy) as decisions with trade-offs — not defaults.
Then it hands off to ux-heuristics-audit, ux-accessibility-audit, ux-aesthetics-audit, and ux-microcopy-audit for validation.
Step 0 — Establish context before designing
Ask if not known; state the assumption if proceeding without an answer:
- Platform — mobile tightens everything: touch targets (≥48×48px), spacing between adjacent buttons, fixed widths for stacked buttons, tactile feedback. Desktop relies on hover/cursor cues instead.
- Action hierarchy on this screen — what is the one thing the user came to do? That action gets the only primary button; everything else is secondary or tertiary.
- Brand personality — serious/trustworthy vs. friendly/playful decides shape (sharp ↔ rounded ↔ pill) and how expressive styling can get.
- Destructive or irreversible actions? — these flip defaults: explicit verb labels ("Delete project," never "Yes"), semantic color (red family), never a FAB, never the visually dominant button by default.
The always-apply core (correct for almost every case)
Pick the type from the action's importance — not from looks
- Primary — the action the interface wants users to take. One per view, most visually prominent (saturated, contrasting fill). If everything is prominent, nothing is.
- Secondary — the alternative (Cancel next to Submit). Subdued: outlined/ghost works well, but the outline needs enough contrast to stay visible.
- Tertiary — rare or low-priority actions. Text buttons, muted colors, smaller weight; place them away from the primary to prevent accidental taps.
- Grouping types: a menu/dropdown button tucks related actions of equal importance into a list; a split button adds a default one-click action plus a dropdown — keep a visual separator so users don't expect the whole button to open the menu; a toggle group keeps 2–3 mutually exclusive options visible with one selected.
- ❌ A dropdown as a catch-all bucket of unrelated actions ✅ Only related actions, grouped to simplify the decision
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.
- 10d ago First seen · 132 lines · 76 tokens per session scan A 852bbeb8df5b
ux-buttons is a skill published in the GitHub repository Uxcel-Lab/product-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 2,601 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
interface-polish
Design-engineering micro-detail pass for interfaces that already work but feel unrefined. Applies concrete CSS/JS rules for hover/active/focus states, transition timing and easing, enter/exit animations, stagger patterns, layered shadows, border-vs-shadow elevation, nested border-radius, optical alignment, typography…
premium-hero-builder
Build premium, dark-themed hero sections and landing pages with cinematic video backgrounds, liquid glass morphism, editorial typography, and pixel-perfect specifications. Based on the Viktor Oddy methodology of detailed design prompts that produce agency-quality results from AI code generation. Use when building hero…
page-flow-cleanup-audit
A review process for cleaning up a user-facing page or feature flow by tracing where its data and states come from. It checks loading, empty, error, permission, and lifecycle behavior before removing unnecessary code.
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…
empty-states
Turn dead ends into moments that build trust and guide action. Covers zero-data screens, error recovery, loading states, and retention micro-copy. Use when handling empty dashboards, failed searches, or moments where users hit a wall.