microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.
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 microsoft/cat-agent-skills --skill wcag-power-platformgit clone --depth 1 https://github.com/microsoft/cat-agent-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/microsoft/cat-agent-skills/wcag-power-platform)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/wcag-power-platform"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/wcag-power-platform/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/microsoft/cat-agent-skills/wcag-power-platform"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/wcag-power-platform.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 | $0.00247 | $0.02123 |
| Opus 5 | $0.00123 | $0.01061 |
| Sonnet 5 | $0.00049 | $0.00425 |
| Haiku 4.5 | $0.00025 | $0.00212 |
Grade A, and why
wcag-power-platform 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 6d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WCAG 2.1 for Web Apps & Power Platform
This skill makes anything you build or review conform to WCAG 2.1 Level AA (the legal default for most public-sector and EU/UK accessibility law), while flagging the AAA criteria worth reaching for. It covers generic web content, full HTML pages/sites and SPAs, and modern theming (dark mode, high contrast, design tokens), and the four Power Platform component types: PCF controls, model-driven apps/forms, canvas apps, and Power Pages.
Default target
Unless the user states otherwise, conform to Level AA. Level A is the floor and AA is what regulations (ADA, Section 508, EN 301 549 / UK Public Sector Bodies Accessibility Regulations) actually require. Mention AAA only as an optional enhancement.
How to use this skill
- Identify the component type (web/PCF/model-driven/canvas/Power Pages). The platform changes how you satisfy a criterion — see the routing table below and read the matching reference file.
- Author or review against the four principles. Read
references/wcag-checklist.md— it lists every WCAG 2.1 success criterion grouped under Perceivable, Operable, Understandable, Robust, with the concrete, testable thing to check for each. This is the heart of the skill. - Apply the platform-specific guidance from the relevant reference file.
- Self-verify using the verification section below before declaring done.
When building something new, bake the checks in as you write — don't bolt them on afterwards. When auditing, report findings as a table: criterion, level (A/AA/AAA), pass/fail, location, and the fix.
Component routing
| If the work involves… | Read this reference |
|---|---|
| Generic HTML/CSS/JS or React web artifacts | references/wcag-checklist.md |
| A full HTML page, website, or single-page app | references/html-pages.md |
| Theming: Power Apps modern themes, dark mode, high contrast, design tokens | references/theming.md |
| PCF (PowerApps Component Framework) controls | references/pcf.md |
| HTML/JS web resources (model-driven) | references/web-resources.md |
| Model-driven apps, forms, views, dashboards | references/model-driven.md |
| Canvas apps | references/canvas.md |
| Power Pages (portals) | references/power-pages.md |
What ships with it
10 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.
- 6d ago First seen · 148 lines · 247 tokens per session scan A 9a5121e9a26a
wcag-power-platform is a skill published in the GitHub repository microsoft/cat-agent-skills (66 stars, last pushed today), licensed MIT. It adds 247 tokens to every session and 2,123 once invoked, about $0.0012 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 2026-09-03.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.