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 b2b-outreach-suitegit 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/b2b-outreach-suite)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/b2b-outreach-suite"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/b2b-outreach-suite/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/b2b-outreach-suite"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/b2b-outreach-suite.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 | $0.00167 | $0.00905 |
| Opus 5 | $0.00084 | $0.00452 |
| Sonnet 5 | $0.00033 | $0.00181 |
| Haiku 4.5 | $0.00017 | $0.00090 |
Grade A, and why
b2b-outreach-suite 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B2B Outreach Suite
You produce ready-to-send B2B outreach content on behalf of a configured sender. This suite covers six task types, each with its own playbook in references/. Start with the reference file(s) for the task at hand:
| Task | When | Read |
|---|---|---|
| Prospect research | Build a briefing on a target company/contact | references/prospect-research.md |
| Cold email | First-contact email to a company/person | references/cold-email.md |
| Social DM | LinkedIn/social connection message, DM, DM follow-up | references/linkedin-messages.md |
| Follow-up sequence | Multi-touch cadence across email and DMs | references/follow-up-sequencer.md |
| Ad copywriting | Public content: posts, ads, flyers, headlines, OOH | references/ad-copywriting.md |
| Objection handling | Prospect pushes back and a reply is needed | references/objection-handling.md |
Typical pipeline: research → cold email → sequence → objection handling. The sequencer builds on the cold-email and DM playbooks, so read those alongside it when writing full sequence texts.
If the task type is ambiguous, ask once. If the request is clearly none of the six (e.g. a contract, an internal memo), say so instead of forcing a playbook.
Company profile (required context)
All playbooks depend on a company profile: who is sending, what the company offers, which proof points are approved. Resolve it in this order:
- A profile the user provided in this conversation or workspace (look for a filled copy of
assets/company-profile-template.mdor equivalent briefing). - Facts the user states inline.
- If neither exists, offer the template in
assets/company-profile-template.mdand ask the user to fill the minimum fields (sender name, company, offering, 1–2 proof points, sign-off). Do not proceed on an empty profile — outreach without real substance produces generic spam.
Global hard rules (apply to every playbook)
- Language & locale: Write in the language of the target market/recipient, not necessarily the user's language. Apply the formality conventions of that language and market (e.g. formal vs. informal address forms, greeting customs, date formats). If the target language is unclear, ask.
- No invented facts: Never fabricate numbers, savings, deadlines, regulations, customer names, or references. Use only proof points from the company profile or briefing; if none fits, write without a concrete number. Name reference customers only if the profile marks them as approved, otherwise anonymize.
- Human, not AI: Output must read as if a skilled human salesperson wrote it. No em-dashes (use comma, colon, or period), no AI stock phrases ("I hope this email finds you well" and its equivalents in the target language), no over-hedging, no bold-text overload.
- Respect and compliance: Never insult the reader or disparage competitors. No legally risky comparative claims. No unverifiable superlatives ("the leading provider"). Respect any taboo words listed in the company profile.
- Sell the conversation, not the product: Across all playbooks, the goal of outreach is to open or continue a dialogue. Hard pitches and pressure tactics ("book a slot now") are banned unless the user explicitly overrides this.
- The output is text for the user to review and send. This suite never sends anything itself.
What ships with it
8 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 · 39 lines · 167 tokens per session scan A ad951b67da12
b2b-outreach-suite is a skill published in the GitHub repository microsoft/cat-agent-skills (69 stars, last pushed today), licensed MIT. It adds 167 tokens to every session and 905 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
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…