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 agentmods add skills/microsoft/cat-agent-skills/generating-podcast-scriptnpx skills add microsoft/cat-agent-skills --skill generating-podcast-scriptgit 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/generating-podcast-script)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/generating-podcast-script"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/generating-podcast-script.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.02654 |
| Opus 5 | $0.00044 | $0.01327 |
| Sonnet 5 | $0.00018 | $0.00531 |
| Haiku 4.5 | $0.00009 | $0.00265 |
Grade A, and why
generating-podcast-script 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Podcast Script Generation
Produces a two-host, NotebookLM-style conversational episode: a readable script plus a multi-voice SSML document ready for Azure Text-to-Speech.
Step 1 — Gather inputs
Ask only for what is missing. Do not ask for optional fields that have safe defaults.
| Input | Required | Default |
|---|---|---|
source or topic |
Yes | — (source material such as a digest/newsletter/articles, or a plain topic) |
duration |
No | medium — short ≈ 3 min / ~450 words, medium ≈ 6 min / ~900 words, long ≈ 12 min / ~1,800 words |
language |
No | English |
cast |
No | Two hosts, NOVA and MILES (see Step 4) |
generate_audio |
No | Ask after the script is ready |
All word targets assume ~150 spoken words per minute. Stay within 10 percent of target.
Derive a lowercase-hyphenated <slug> from the source or topic (max 6 words,
ASCII only).
Step 2 — Parse the source material
Skip this step when the user gave a bare topic with no source material.
Extract every distinct article or item. For each, capture:
- headline
- publication / source
- date, if present
- the core factual claim
- any figures or quotes
- the "so what"
Merge duplicates covering the same event. Discard boilerplate, footers, disclaimers, legal notices, unsubscribe text, and image captions.
Step 3 — Editorial selection
Rank items by newsworthiness and reader impact. Keep the top 4 to 6 for full
treatment (fewer for short, more for long). Group the remainder into one
fast rapid fire segment. If the material has a dominant theme, lead with it
and thread it through the episode.
Step 4 — Cast
Two hosts, always the same personalities, always distinct voices:
- NOVA — voice
en-US-AvaMultilingualNeural. Lead host. Warm, curious, quick. Drives the agenda, asks the question the listener is thinking, reacts out loud, reframes jargon into plain language. Slightly faster cadence. - MILES — voice
en-US-AndrewMultilingualNeural. Analyst. Calm, dry, precise. Supplies context, numbers, caveats, second-order implications. Slightly slower, lower pitch. Occasionally pushes back on Nova.
What ships with it
2 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 · 237 lines · 89 tokens per session scan A cb59026214ee
generating-podcast-script is a skill published in the GitHub repository microsoft/cat-agent-skills (63 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 2,654 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 2026-08-30.
Other skills, from other repositories
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
剪辑环境的唯一管理者：就绪检查（skills 是否最新 → Runtime 是否配套）、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用；业务 Skill（剪口播/字幕/画面/导出）第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.
infographic-template-updater
Update template catalogs and UI prompts after adding new infographic templates (src/templates/.ts), including SKILL.md template list, site gallery template mappings, and the AIPlayground prompt list.