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 brand-voice-passgit 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/brand-voice-pass)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/brand-voice-pass"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/brand-voice-pass/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/brand-voice-pass"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/brand-voice-pass.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 | $0.00046 | $0.00729 |
| Opus 5 | $0.00023 | $0.00365 |
| Sonnet 5 | $0.00009 | $0.00146 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
brand-voice-pass 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 12d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Voice Pass
Use this skill to transform draft copy into a defined brand or personal voice while preserving the user's meaning, evidence, terminology, and intent.
Operating principles
- Preserve the truth. Do not invent facts, proof points, dates, clients, figures, quotes, or outcomes.
- Preserve the argument. Improve expression without changing the user's position unless they explicitly ask for a stronger or softer stance.
- Remove generic AI tells. Avoid empty intensifiers, inflated claims, tidy-but-bland phrasing, excessive signposting, and repetitive short sentences.
- Use the requested variant of English. Default to the user's language and regional spelling. If unspecified and the surrounding material uses UK English, use UK English.
- Respect the destination. Adjust length, cadence, paragraphing, and directness for the intended channel.
- Keep it usable. Return the rewritten copy first. Add notes only when useful.
Inputs to look for
- Draft text or notes to rewrite.
- Brand or personal voice guidance.
- Audience, channel, objective, and desired length.
- Words or phrases to avoid.
- Required terminology, source facts, or claims that must remain intact.
If the user has not supplied a full voice guide, infer only light stylistic choices from the draft and clearly avoid claiming a detailed brand profile exists.
Workflow
- Read the full draft before editing.
- Identify the core message, supporting evidence, and intended action.
- Apply the voice rules without adding unsupported content.
- Improve flow, transitions, sentence rhythm, and paragraph shape.
- Remove generic AI phrasing and replace it with concrete, human language.
- Check the output against the original for meaning drift.
- Return the final copy in a copy-ready format.
Default voice controls
Use these controls unless the user provides a different profile:
- Prefer concrete language over abstract positioning.
- Prefer lived-experience phrasing over consultancy jargon.
- Use natural paragraphing rather than long blocks or a list of fragments.
- Avoid repetitive, overly neat sentence structures.
- Avoid claims such as "game-changing", "revolutionary", "unlock", "seamless", "in today's fast-paced world", and similar filler unless they are in source text and must be retained.
- Keep the user's level of confidence: do not over-polish into corporate blandness.
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.
- 12d ago First seen · 83 lines · 46 tokens per session scan A 75a924270b0f
brand-voice-pass is a skill published in the GitHub repository microsoft/cat-agent-skills (69 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 729 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…