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 call-for-speakers-digestgit 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/call-for-speakers-digest)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/call-for-speakers-digest"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/call-for-speakers-digest/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/call-for-speakers-digest"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/call-for-speakers-digest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 99 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00113 | $0.03078 |
| Opus 5 | $0.00056 | $0.01539 |
| Sonnet 5 | $0.00023 | $0.00616 |
| Haiku 4.5 | $0.00011 | $0.00308 |
Grade A, and why
call-for-speakers-digest 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 11d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Call for Speakers Digest
Compatibility
Requires web search. Building the HTML digest in Copilot Studio specifically requires Code Interpreter enabled on the agent, printing raw HTML into the chat as text won't render it. Sending the digest as an actual email requires a connected email tool (Gmail, Outlook). Without Code Interpreter or an email tool, present the finished digest as plain formatted chat text instead and say so plainly, don't pretend it was sent or rendered as a file when it wasn't.
Step 1: Build the speaker profile (first run only)
Ask for, and remember, this profile so it doesn't need to be re-collected every week:
- Check whether the topics collectively sit inside one bigger platform or ecosystem, and offer to broaden to it. People naming specific products they work in day to day usually won't think to say "and treat this as shorthand for the whole platform," that's your job to notice, not theirs to volunteer. If the topics given all live under one identifiable umbrella (Copilot Studio, Copilot Cowork, and Agent 365 are all Microsoft 365, for example), say so plainly and ask whether to search that entire ecosystem rather than staying narrow to just the named products, since a huge amount of genuinely relevant content lives at conferences and events branded at the platform level rather than the specific-product level, and staying narrow risks silently missing most of it. If they say yes, ask if there's anything within that ecosystem they specifically want excluded (using the Microsoft 365 example: someone focused on Copilot Studio and Agent 365 likely doesn't want Teams-only or device-management/Intune content, even though those are technically part of the same platform). Remember both the broadened scope and any exclusions as part of the profile.
If they'd rather stay narrow to just the named topics, that's a legitimate choice too, don't push, just make sure they've actually been offered the broader option once so it's an informed choice rather than a default they never got to consider.
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.
- 11d ago First seen · 106 lines · 113 tokens per session scan A e1a30bb58b68
call-for-speakers-digest is a skill published in the GitHub repository microsoft/cat-agent-skills (67 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 3,078 once invoked, about $0.0006 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…