ng-elemental: Skill for Cursor

.cursor/skills/ng-elemental-polish/SKILL.md

ng-elemental-polish is a skill for Cursor from AtulFalle/ng-elemental. It costs 86 tokens per session (1,289 once invoked), scanned A, original, MIT.

A checklist for polishing existing NgElemental Angular UI components, including their visual states, keyboard behavior, screen-reader support, and mobile behavior. WCAG is an accessibility standard, while ARIA APG is a guide for accessible interface patterns.

In plain words
What is it for?
Use it to audit or improve an existing El* widget, check accessibility against WCAG 2.2 AA, and add Storybook or documentation coverage for its states.
Why use it?
It helps find usability and accessibility problems before a component is shipped, such as poor contrast, missing focus indicators, or controls that do not work from the keyboard.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is AtulFalle/ng-elemental's own configuration. It tells Cursor how to work on ng-elemental itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ng-elemental configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/AtulFalle/ng-elemental/master/.cursor/skills/ng-elemental-polish/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AtulFalle/ng-elemental

Made for: Cursor.

Wrote 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.

agentmods badge for ng-elemental-polish

README.md
[![agentmods](https://agentmods.dev/badge/skills/atulfalle/ng-elemental/ng-elemental-polish/github.svg)](https://agentmods.dev/skills/atulfalle/ng-elemental/ng-elemental-polish)
Your own site
<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.

agentmods 80×15 button for ng-elemental-polish

Your own site · 80×15
<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>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,289 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 9d39fb5a5171, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

.cursor/skills/ng-elemental-polish/SKILL.md · 82 lines

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):

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-component first, then return here)
  • Parent/child state-ownership review only (use ng-elemental-review)

Workflow

  1. 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.
  2. Copy the audit from component-audit.md. Fill every box. N/A needs a reason (no disabled input, not a composite, no size API).
  3. Run the widget-scoped A11Y items in a11y-checklist.md. Page-level items belong to the docs app, not the primitive.
  4. Check keyboard, name, role, and state against the mapped APG pattern. Prefer a native host (button, a, input, table, …) over role="…".
  5. Confirm Storybook / docs cover every Visual and Content box that is not N/A.
  6. Add one Storybook Interactions story (not one story per case) that mounts the key states together and runs play with step('…') for pointer, keyboard (Enter/Space), disabled, loading/busy, and accessible name. Use the play context userEvent. Tag it tags: ['!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 set a11y.manual or a11y.test: 'off').
  7. Stop if Critical a11y defects remain (no name, no focus indicator, inoperable keyboard, contrast fail, disabled not exposed).

Read the full file on GitHub · 82 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 82 lines · 86 tokens per session scan A 9d39fb5a5171

Subscribe to this mod's changes

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.