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 explainer-videogit 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/explainer-video)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/explainer-video"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/explainer-video/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/explainer-video"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/explainer-video.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 | $0.00184 | $0.02057 |
| Opus 5.5 | $0.00074 | $0.00823 |
| Sonnet 5.5 | $0.00037 | $0.00411 |
| Haiku 4.5 | $0.00018 | $0.00206 |
Grade A, and why
explainer-video 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explainer Video
Turns a subject under discussion into a narrated, captioned MP4 that explains it. The output is a
finished video in output/, not a deck and not a script.
When NOT to Use
- Slides for live presenting →
pptx. A deck is not a video. - A single image, diagram or infographic →
image-operations/pptx. - Audio only (podcast, briefing) → call
PodcastGeneratedirectly. - A written explainer (SOP, guide, one-pager) →
docx. - Marketing film, live action, real people's likenesses, licensed footage or music — not possible here. Say so plainly and offer the b-roll style this skill can do.
Workflow
1. Frame the subject (one short round)
Establish, from the conversation first and only then by asking: subject, audience
(newcomer / practitioner / exec), target length (default ~2 minutes ≈ 6-8 beats), and the
angle ("when to use each option", "how it works", "what changed"). Use AskUserQuestion
once — never a chain of questions.
Always ask the visual style in that same card: dark (navy slides, colour-coded sections,
photographic b-roll) or light (white slides, brand accents, sparing photography).
Ask whether they have screenshots to include if the subject is a product, tool or UI walkthrough.
2. Gather (only what the video actually needs)
- Research when it matters — external facts, product capabilities, statistics, "what's new":
use
web_search/web_fetch, or thedeep-research-agentwhen claims need citing. Skip research entirely when the subject is already covered by this conversation or the user's own content. Never research a topic the user has already explained. - Internal subjects — pull from
SearchM365,ReadFileContent, meeting transcripts. Ground every internal claim in what those return. - Screenshots —
Glob input/**/*and check any<attached_files>block. Screenshots are used as supplied: framed, optionally box-highlighted, never regenerated or redrawn, so the product UI stays truthful. Note any UI text you rely on in narration so it matches the pixels.
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 · 157 lines · 184 tokens per session scan A c464697d2a1a
explainer-video is a skill published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 184 tokens to every session and 2,057 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.