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 persona-reaction-panelgit 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/persona-reaction-panel)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/persona-reaction-panel"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/persona-reaction-panel/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/persona-reaction-panel"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/persona-reaction-panel.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 | $0.00134 | $0.01175 |
| Opus 5 | $0.00067 | $0.00588 |
| Sonnet 5 | $0.00027 | $0.00235 |
| Haiku 4.5 | $0.00013 | $0.00118 |
Grade A, and why
persona-reaction-panel 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona Reaction Panel
Simulate how each defined persona will react to the user's draft artefact, then synthesise domain-level risks and concrete edits, ending with a SHIP / REVISE / HOLD verdict.
Personas file (required): load the user's personas file from references/ (or the path the user provides). Each persona provides: role / what they do, motivations, pain points, how the tool or change helps them, comms anchors, and a confidence flag (fully defined or draft). Personas are grouped into domains. If no completed personas file is available, stop and ask the user to supply one (references/personas.template.md is the blank template — do not run the panel against the template's example personas).
Scope guard: if the artefact is a 1:1 private communication, an HR/performance matter, or legal/contractual language, decline and state why. Only react to a draft the user supplies — do not write one.
How a run works
Step 1 — Load the personas file (in full)
Read the personas file completely before reacting. It is the ONLY source of truth for how each persona responds — never simulate from memory or generic assumptions.
Step 2 — Read the artefact
Read the draft in full. Identify: what is asked, what is claimed, what is implied, what is left out, the audience it assumes, and which of the user's domains it actually serves.
Step 3 — Per-persona reaction (repeat for each persona)
Six short answers per persona, each anchored to a quoted attribute from the personas file:
- Will they read it? — would it land so they'd engage? (anchor: their role / pain point / motivation)
- What do they take away? — first-read interpretation. (anchor)
- What do they push back on? — the line, claim, or omission that stops them. (anchor a real pain point — do not invent a fear the file does not support)
- What did it miss for them? — the defined need that isn't addressed.
- What would make them tick and stick? — the specific, artefact-applied addition that converts neutral/negative to engaged. (anchor)
- Does it move them? — net effect (up / flat / down), one sentence.
What ships with it
3 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 · 59 lines · 134 tokens per session scan A da931ae230bb
persona-reaction-panel is a skill published in the GitHub repository microsoft/cat-agent-skills (67 stars, last pushed today), licensed MIT. It adds 134 tokens to every session and 1,175 once invoked, about $0.0007 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 2026-09-03.
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…