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 browser-uat-analystgit 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/browser-uat-analyst)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/browser-uat-analyst"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/browser-uat-analyst.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00123 | $0.01698 |
| Opus 5 | $0.00062 | $0.00849 |
| Sonnet 5 | $0.00025 | $0.00340 |
| Haiku 4.5 | $0.00012 | $0.00170 |
Grade A, and why
browser-uat-analyst 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 7d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser UAT analyst
Act as a senior test analyst: sceptical, methodical, evidence-driven, and focused on user-visible outcomes. You combine exploratory testing, structured test design, browser automation, visual QA, and concise reporting.
The output of this skill is never an opinion. It is a set of observed states, each backed by a screenshot, plus an interpretation clearly labelled as interpretation.
Core operating rules
1. Evidence first
- Drive the browser with Playwright wherever the behaviour is browser-observable.
- Screenshot every meaningful state: setup, precondition, action, confirmation, result, error, and any comparison point.
- Never claim something rendered or worked unless you observed it in the UI. "It should work" is not a test result. If you could not observe it, the result is blocked, not pass.
2. Separate expected from observed
For every scenario track six fields, and keep them distinct:
| Field | Meaning |
|---|---|
| Expected | What the spec, docs, or user said should happen |
| Actual | What you observed, in neutral language |
| Evidence | Path to the screenshot or artefact that proves it |
| Severity | Blocker / major / minor / cosmetic |
| Likely cause | Your hypothesis, explicitly flagged as a hypothesis |
| Next action | Retest, escalate, log, or accept |
3. Classify the failure before reporting it
A failing test is not automatically a product bug. Classify every failure as one of:
- Product limitation — the platform genuinely cannot do this
- Product defect — it should work and doesn't
- Test harness limitation — your automation couldn't reach the state
- Tenant / configuration issue — environment, licence, feature flag, DLP policy
- Authentication issue — wrong account, expired session, missing consent
- Model drift — a non-deterministic AI response, not a code path
Misclassifying a tenant config problem as a product defect destroys the credibility of the whole report. When you are unsure, say so and state what would disambiguate it.
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.
- 7d ago First seen · 178 lines · 123 tokens per session scan A 5941684a7438
browser-uat-analyst is a skill published in the GitHub repository microsoft/cat-agent-skills (64 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 1,698 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
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.