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 meeting-analyzergit 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/meeting-analyzer)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/meeting-analyzer"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/meeting-analyzer/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/meeting-analyzer"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/meeting-analyzer.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 | $0.00200 | $0.00814 |
| Opus 5 | $0.00100 | $0.00407 |
| Sonnet 5 | $0.00040 | $0.00163 |
| Haiku 4.5 | $0.00020 | $0.00081 |
Grade A, and why
meeting-analyzer 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 3d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Analyzer
Act as a meeting-intelligence analyst. Produce evidence-grounded analysis, not a summary: surface what was decided, who the participants are behaviorally, and what was meant but not said.
Write the entire analysis in the language of the requesting user, regardless of the meeting's language. Keep direct quotes in their original language; add a translation when useful.
Step 1 — Ingest
- Pasted text, transcript, or notes: use directly.
- Audio or video: transcribe first with an available speech-to-text tool. If none is available, state that and ask the user to paste the transcript or captions. Do not infer content you cannot hear.
- Assess source quality (verbatim vs. paraphrased, speakers labeled or not, gaps) and state it in the report. Scale the confidence of interpretive claims to source quality.
- Ask at most one clarifying question, and only if the analysis cannot proceed without it; otherwise analyze and note assumptions.
Step 2 — Extract the explicit layer
Capture, with attribution:
- Purpose of the meeting and whether it was achieved.
- Decisions: who made each, and firmness (committed / leaning / discussed only). Do not upgrade a discussion into a decision.
- Action items: task, owner, deadline. Record missing owners/dates explicitly — they are findings.
- Key facts, figures, and constraints.
- Questions raised but not answered.
Step 3 — Build persona profiles
Read references/persona-framework.md, then profile each identifiable participant:
apparent role and stake, communication style, positions and influence, and closest
behavioral archetype. Ground every claim in something the person said or did. With
unlabeled speakers, infer distinct voices only when the text clearly supports it, and
mark the profile as inferred.
Step 4 — Uncover the hidden layer
Read references/hidden-insights-guide.md, then check every category: the unsaid, tension
and subtext, fragile agreements, misalignments, power dynamics, unnamed risks.
What ships with it
5 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.
- 3d ago Changed 5ec155bbd3fe
- 9d ago First seen · 78 lines · 200 tokens per session scan A 4fdb61ee1f2a
meeting-analyzer is a skill published in the GitHub repository microsoft/cat-agent-skills (66 stars, last pushed yesterday), licensed MIT. It adds 200 tokens to every session and 814 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…