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 presentation-talk-track-buildergit 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/presentation-talk-track-builder)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/presentation-talk-track-builder"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/presentation-talk-track-builder.svg" alt="Measured on agentmods" 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 | $0.00165 | $0.02716 |
| Opus 5 | $0.00082 | $0.01358 |
| Sonnet 5 | $0.00033 | $0.00543 |
| Haiku 4.5 | $0.00016 | $0.00272 |
Grade A, and why
presentation-talk-track-builder 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 4d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This skill turns slides into a spoken talk track. For each requested slide it writes a first-person script the presenter can read aloud, grounded in the slide's content and — above all — its speaker notes. It calibrates the script length to a target time and speaking pace and returns a timing table so the presenter knows whether they will land on time.
Core rule: the speaker notes are the source of truth. When notes and slide text disagree, the script follows the notes and silently drops the contradicted slide text. This is what the author intended to say.
Works across Scout, Copilot Studio, and Cowork. The user can attach a
.pptx, provide slide images, paste slide text, or provide an outline.
When to Use
- "I'm presenting slides 8-11, write a script for each so I can present them."
- "Turn my speaker notes into what I should actually say."
- "Make a ~6-minute talk track for these four slides; I speak fast."
- "Write presenter narration for this deck / these slide images."
- "Give me a word-for-word script with pauses and a handoff to the next speaker."
When NOT to Use
- Creating, designing, or editing the visible content of the slides themselves.
- Summarizing a recorded meeting, call, or transcript.
- Writing a standalone document, memo, or article.
- A quick one-line answer that isn't a spoken script — answer inline.
Quick Start
User: "I'm presenting slides 8-11, write a script for each. If the notes
contradict the slides, follow the notes. Target ~6 minutes, business
audience."
1. Capture inputs — audience & goals, slide content, optional supporting
context.
2. Extract BOTH slide text AND speaker notes for the requested slides.
3. Reconcile: where notes contradict slides, follow the notes.
4. Calibrate: target minutes × pace (words/min) = word budget; split by
slide.
5. Write a first-person script per slide with delivery cues + a handoff line.
6. Return the scripts + a per-slide timing table (words → spoken minutes).
7. Offer to save as speaker notes back into a copy of the deck, or as a doc.
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.
- 4d ago First seen · 240 lines · 165 tokens per session scan A 9b389cb865e5
presentation-talk-track-builder is a skill published in the GitHub repository microsoft/cat-agent-skills (64 stars, last pushed today), licensed MIT. It adds 165 tokens to every session and 2,716 once invoked, about $0.0008 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
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.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.