Borrowing it
Nothing to install: this file belongs to AtulFalle/ng-elemental. 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/AtulFalle/ng-elemental/master/.cursor/skills/ng-elemental-polish/SKILL.mdgit clone --depth 1 https://github.com/AtulFalle/ng-elementalWrote 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/atulfalle/ng-elemental/ng-elemental-polish)<a href="https://agentmods.dev/skills/atulfalle/ng-elemental/ng-elemental-polish"><img src="https://agentmods.dev/badge/skills/atulfalle/ng-elemental/ng-elemental-polish/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/atulfalle/ng-elemental/ng-elemental-polish"><img src="https://agentmods.dev/badge/skills/atulfalle/ng-elemental/ng-elemental-polish.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 | $0.00086 | $0.01289 |
| Opus 5 | $0.00043 | $0.00645 |
| Sonnet 5 | $0.00017 | $0.00258 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade A, and why
ng-elemental-polish 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 11d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NgElemental component polish
Read this skill before changing visual, interaction, or accessibility of any El* widget. The checklist is the same for every component. Mark a box N/A with a one-line reason when that widget truly has no such state; do not skip a section.
Target WCAG 2.2 Level AA. Native HTML first. ARIA only when the native element cannot express the pattern.
REQUIRED REFERENCES (open both, then the APG pattern for this widget):
- The A11Y Project checklist
- ARIA Authoring Practices Guide (APG)
- APG Patterns: https://www.w3.org/WAI/ARIA/apg/patterns/
Also follow ng-elemental-component (files, tokens, API) and ng-elemental-review (one owner per piece of state). This skill does not replace either.
When to use
- Picking the next existing component to polish
- Auditing visual / interaction / a11y / responsive / API on any
El*widget - Adding Storybook or docs coverage for states
- Keyboard, focus, name, contrast, or screen-reader questions on an
El*widget
When not to use
- Scaffolding a brand-new component (use
ng-elemental-componentfirst, then return here) - Parent/child state-ownership review only (use
ng-elemental-review)
Workflow
- Name the widget and its APG pattern from aria-apg.md. Open that APG page. Layout-only widgets still run Visual, Content, Appearance, Contrast, and Responsive.
- Copy the audit from component-audit.md. Fill every box.
N/Aneeds a reason (no disabled input,not a composite,no size API). - Run the widget-scoped A11Y items in a11y-checklist.md. Page-level items belong to the docs app, not the primitive.
- Check keyboard, name, role, and state against the mapped APG pattern. Prefer a native host (
button,a,input,table, …) overrole="…". - Confirm Storybook / docs cover every Visual and Content box that is not
N/A. - Add one Storybook
Interactionsstory (not one story per case) that mounts the key states together and runsplaywithstep('…')for pointer, keyboard (Enter/Space), disabled, loading/busy, and accessible name. Use theplaycontextuserEvent. Tag ittags: ['!test'](string literal — CSF cannot parse spread/variable tags) so Vitest does not auto-run it. Enable the Code panel (parameters.docs.codePanel: true) and axe in the Accessibility panel (do not seta11y.manualora11y.test: 'off'). - Stop if Critical a11y defects remain (no name, no focus indicator, inoperable keyboard, contrast fail, disabled not exposed).
What ships with it
3 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.
- 11d ago First seen · 82 lines · 86 tokens per session scan A 9d39fb5a5171
ng-elemental-polish is a skill published in the GitHub repository AtulFalle/ng-elemental (2 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 1,289 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
implement-component
Implements production-ready UI using DB UX Design System v3 components, tokens, and icons with a discovery-first approach.
uswds
Build, audit, or convert websites with the U.S. Web Design System (USWDS) using the unofficial uswds-mcp server. Use when work involves USWDS components, patterns, templates, accessibility guidance, design tokens, utilities, @uswds/uswds, or federal website implementation.
daisyui-colors
Color rules that you must use with daisyUI 5.
daisyui-config
Configuration options for daisyUI 5.
seed-token-analysis
A read-only analyzer for one SEED color token, including its definitions, aliases, dependent tokens, component uses, generated outputs, and color contrast. A design token is a named value such as a color that can be reused across an interface.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.