Borrowing it
Nothing to install: this file belongs to juspay/xyne-spaces. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/juspay/xyne-spaces/main/.claude/skills/xyne-usability-principles/SKILL.mdgit clone --depth 1 https://github.com/juspay/xyne-spacesWrote 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/juspay/xyne-spaces/xyne-usability-principles)<a href="https://agentmods.dev/skills/juspay/xyne-spaces/xyne-usability-principles"><img src="https://agentmods.dev/badge/skills/juspay/xyne-spaces/xyne-usability-principles/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/juspay/xyne-spaces/xyne-usability-principles"><img src="https://agentmods.dev/badge/skills/juspay/xyne-spaces/xyne-usability-principles.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 | $0.00155 | $0.02977 |
| Opus 5.5 | $0.00062 | $0.01191 |
| Sonnet 5.5 | $0.00031 | $0.00595 |
| Haiku 4.5 | $0.00015 | $0.00298 |
Grade A, and why
xyne-usability-principles 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 yesterday.
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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xyne usability principles
Ten principles drawn from recurring product feedback and checked against research. They exist because the same problems keep coming back: screens that load forever, Back buttons that loop, features nobody finds, themes nobody tested, automated changes nobody could edit first. Use them for two jobs: designing something new, and reviewing something that exists. The walkthrough is the method; the principles are the lens.
The ten principles
Each has a sentence to remember and the checks that make it concrete. Use the numbers: "it feels slow" is an opinion, "no feedback for 3 s after Save" is a finding someone can fix.
Performance — references/1-performance.md
- Speed is felt, not measured. Show something within a second, and show progress for anything longer.
- About 0.1 s feels instant; under 1 s needs no indicator; 1–10 s needs one; past 10 s needs percent done and a way to keep working.
- Render the shell and cached data first. One slow query must not blank the whole page.
- Uploads show bytes or percent. Search returns exact matches first, in under a second.
- What is on screen must match reality. Stale views and silent delays cost trust, not just time.
- Anything that can change behind the user (feeds, threads, counts) updates itself, or says "updated 2 min ago".
- The user's own action shows at once and reconciles with the server afterwards.
- Judge it on a slow network and a phone, not on office wifi.
Flow — references/2-flow.md
- Judge the whole journey, not the screen. Make the common path one action and keep the user's place when the view changes.
- Count the main task's steps: clicks, fields, page changes, decisions. Each one adds time (the keystroke-level model), and a decision with more options takes longer to make (Hick's law).
- The default is the most common intent; the other options are one click away.
- Scroll position, selected tab, filters and drafts survive mode changes, navigation and reload.
- Nothing the user is looking at moves or reorders by itself; leave room for content that loads late.
- Never trap people. Back always goes back, and every choice can be undone.
- Back or Escape reverses every navigation-like change (a panel, a filter, a wizard step), and never loops.
- Keep the main button enabled; on press, point at what's missing and focus it.
- "Hide" and "dismiss" come with Undo, and a place to find hidden things again.
What ships with it
7 files 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.
- yesterday First seen · 193 lines · 155 tokens per session scan A 488155728ff9
xyne-usability-principles is a skill published in the GitHub repository juspay/xyne-spaces (813 stars, last pushed today), licensed Apache-2.0. It adds 155 tokens to every session and 2,977 once invoked, about $0.0006 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 2026-10-17.
Other skills, from other repositories
omh-accessibility-audit
This is an OMH accessibility-audit workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-design-quality-gate
This is an OMH design-quality-gate workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-apple-design
This is an OMH apple-design workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
product-research
Find and compare current FF&E candidates from a design brief, with sourced purchasing facts and optional CSV-library save. Use to research or source products; not to match from an image or pair coordinating items.
design-craft
Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique. Use for new screens, landing pages, redesigns, typography/layout work, or UI that feels generic or AI-generated. For small fixes, preserve the existing design without starting a…
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…