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 anonymised-case-study-writergit 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/anonymised-case-study-writer)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/anonymised-case-study-writer"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/anonymised-case-study-writer/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/anonymised-case-study-writer"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/anonymised-case-study-writer.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 | $0.00042 | $0.00770 |
| Opus 5 | $0.00021 | $0.00385 |
| Sonnet 5 | $0.00008 | $0.00154 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
anonymised-case-study-writer 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anonymised Case Study Writer
Use this skill to create credible, anonymised case studies from engagement notes, interview notes, project summaries, outcomes, or source documents.
Core rules
- Protect confidentiality. Remove or generalise names, client identifiers, locations, internal programme names, system names, and commercially sensitive details unless the user explicitly says they are public.
- Do not invent outcomes. Only include outcomes, metrics, timelines, and benefits that appear in the source material or are supplied by the user.
- Preserve credibility. Prefer specific operational detail over vague marketing claims, while keeping the client anonymised.
- Make the story reusable. Structure the case study so it can be used in proposals, webpages, thought leadership, sales conversations, and internal learning.
- Separate unknowns. If outcomes or proof points are missing, include a short "Evidence gaps" section rather than fabricating.
Default anonymisation pattern
Use neutral descriptors such as:
- A large public sector organisation.
- A global consumer goods company.
- A regulated financial services organisation.
- A national healthcare provider.
- A multinational energy business.
Only describe sector, scale, geography, and technology where the source material supports it and doing so does not identify the client.
Workflow
- Read all supplied source material.
- Extract the engagement context, problem, constraints, intervention, outcomes, and lessons.
- Identify any confidential or identifying details and replace them with safe descriptors.
- Draft the case study using the structure below.
- Check every claim against the source material.
- Add evidence gaps or suggested follow-up questions only where needed.
- Return copy-ready Markdown.
Default structure
# [Case study title]
## At a glance
| Field | Summary |
|---|---|
| Client type | [Anonymised descriptor] |
| Sector | [Sector if known] |
| Challenge | [One-sentence challenge] |
| Work delivered | [One-sentence intervention] |
| Outcome | [Evidence-backed outcome or "Outcome evidence not provided"] |
## Context
[What was happening and why it mattered.]
## The challenge
[The specific business, operating, adoption, governance, delivery, or technology problem.]
## What we did
[Practical work performed. Use bullets only where they improve clarity.]
## What changed
[Evidence-backed outcomes, capability shifts, decisions enabled, delivery improvements, or learning generated.]
## Why it mattered
[Business relevance and wider lesson.]
## Reusable insight
[The portable lesson other organisations can learn from this case.]
## Evidence gaps
- [Only include if relevant.]
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 · 108 lines · 42 tokens per session scan A 31272d202046
anonymised-case-study-writer is a skill published in the GitHub repository microsoft/cat-agent-skills (66 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 770 once invoked, about $0.0002 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…