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 rich-html-presentationgit 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/rich-html-presentation)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/rich-html-presentation"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/rich-html-presentation/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/rich-html-presentation"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/rich-html-presentation.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 | $0.00092 | $0.02985 |
| Opus 5.5 | $0.00037 | $0.01194 |
| Sonnet 5.5 | $0.00018 | $0.00597 |
| Haiku 4.5 | $0.00009 | $0.00298 |
Grade A, and why
rich-html-presentation 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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
Step 1 — Gather the content first
If the deck is grounded in the user's world (a meeting/transcript, documents, a project, a product), retrieve it with the right tools (SearchM365, ListCalendarView + meeting-transcript tools, ReadFileContent, web_search) before authoring. Use clearly-marked placeholders (e.g. [Add Q3 number]) for anything you can't find — never invent names, numbers, quotes, or dates.
Step 2 — Start from the template
Read references/template.html and references/components.md from this skill folder. The template is the source of truth for the design system. Copy its <style> block and all five <script> blocks verbatim — do not restyle or rewrite the navigation/theme engine. Only the slide content, <title>, and .brand label change.
The engine ships as five separate small scripts on purpose. Never merge them into one, and never make one depend on a variable from another — see "Preview-surface constraints" below. (The fifth is the optional speaker-notes tray; delete it wholesale if the deck has no notes.)
Step 2a — Preview-surface constraints (why the engine looks the way it does)
Decks get shared, and most recipients open them in an embedded preview — the Teams file-preview pane, Outlook's reading pane, a SharePoint preview — not a real browser tab. Those hosts rewrite the document before rendering, and they impose three limits that are easy to violate by accident:
- Inline scripts over ~2000 characters are silently never executed. (The Teams preview injects its own guard carrying
LIMIT=2000.) Keep every<script>under ~1700 characters to leave headroom. - Each inline script is wrapped, so top-level
const/letdoes not reach a shared global scope. Aconstdeclared in one block is invisible to the next. - Each inline script may get its own global object. Even an explicit
window.myThing = {}in one block can beundefinedin the next. There is no reliable cross-block channel.
What ships with it
4 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.
- 1mo ago First seen · 101 lines · 92 tokens per session scan A 938c44077af9
rich-html-presentation is a skill published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 2,985 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.