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 holiday-recapgit 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/holiday-recap)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/holiday-recap"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/holiday-recap/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/holiday-recap"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/holiday-recap.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 Excessive Agency · line 294 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00156 | $0.11943 |
| Opus 5 | $0.00078 | $0.05972 |
| Sonnet 5 | $0.00031 | $0.02389 |
| Haiku 4.5 | $0.00016 | $0.01194 |
Grade A, and why
holiday-recap 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 10d 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 — 834 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Holiday Recap
Catch the user up after annual leave or any extended out-of-office period. Reviews Outlook email, meeting invitations, meetings held while away, Teams channels, group chats, 1:1 chats and meeting chats, then reports Mails, Meeting Request, Important Meetings Recap and Chats — each item appearing exactly once, deep-linked, styled to match the app it came from (Outlook items read like Outlook, Teams items read like Teams) — before executing the meeting responses, sends and posts the user approves.
When NOT to Use
- Daily or end-of-day catch-up ("what did I miss today", "morning briefing") →
daily-briefing. - A single meeting's summary, transcript or action items →
meeting-intel. - Calendar hygiene, declining low-value meetings, defending focus time →
calendar-management. - Booking, moving or cancelling a meeting →
schedule-meeting. - Ordinary inbox triage or a one-off email search → use the Outlook tools directly.
- Absences of roughly a day or less, where a daily briefing is the better fit.
This skill orchestrates those built-in capabilities across a multi-day absence window; it does not replace them. Where a built-in skill does the job better for one item (e.g. a deep meeting summary), use it and fold the result into the recap.
Workflow
Step 1 — Ask the scoping questions, starting with which areas to cover
Before any mailbox, calendar, chat or channel call runs, ask the user through this sequence,
starting with Q0. Combine into as few core-AskUserQuestion cards as the UI allows (e.g. Q0
alone on its own card since every later question depends on it; Q1 alone on the next card since
it gates everything else; Q2+Q3 together where relevant; Q4 alone, since its answer determines
what the next card can even show; Q5 next; Q6 last) — but the fixed order below never changes,
and a question is only skipped when its own rule below says to skip it.
Q0 — Areas to include "Which areas do you want covered in this recap?" Multi-select, presented as checkboxes:
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.
- 10d ago First seen · 834 lines · 156 tokens per session scan A be11a515934f
holiday-recap is a skill published in the GitHub repository microsoft/cat-agent-skills (66 stars, last pushed yesterday), licensed MIT. It adds 156 tokens to every session and 11,943 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.