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 competitive-battlecard-buildergit 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/competitive-battlecard-builder)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/competitive-battlecard-builder"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/competitive-battlecard-builder/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/competitive-battlecard-builder"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/competitive-battlecard-builder.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 | $0.00116 | $0.04352 |
| Opus 5 | $0.00058 | $0.02176 |
| Sonnet 5 | $0.00023 | $0.00870 |
| Haiku 4.5 | $0.00012 | $0.00435 |
Grade A, and why
competitive-battlecard-builder 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitive Battlecard Builder
Compatibility
The interactive app output and the PowerPoint export both require Code Interpreter available to the agent. Without it, present the battlecard as formatted chat text instead.
When writing Python for Code Interpreter, avoid building scripts through shell heredocs or string concatenation that has to escape the battlecard data inline, especially once brand colors, hex codes, or parenthesized function calls like RGBColor(...) are involved, unbalanced quotes or parens in the data will break the heredoc before your code ever runs. Write the JSON data to its own file (json.dump) and have the script json.load it, or write the whole script as a single Python file directly rather than assembling it through shell quoting.
Step 1: Gather the inputs
- Which kind of comparison this is — ask first, before anything else: is this a sales battlecard advocating for one specific product against competitors, or a neutral, unbiased comparison with no side taken? This determines the entire shape of what you build next, not just the wording:
- Battlecard: one product is "ours," the rest are competitors, compared pairwise (us vs. each one). Objection handling applies (Step 3's
objectionsarray), since that's inherently a sales concept, what a prospect pushes back with and how to respond. - Neutral comparison: there is no "ours." Every item is a peer, laid out as one shared matrix, all items as columns, one set of dimensions as rows, no anchor item privileged over the others. Never use the word "competitor" anywhere in this mode, not in what you say to the person, not in the data. Skip objection handling entirely, there's no seller position to defend. Gather comparably balanced detail on every item.
- Battlecard: one product is "ours," the rest are competitors, compared pairwise (us vs. each one). Objection handling applies (Step 3's
- The items being compared — for a battlecard: your product/company (name and a one-line positioning statement) plus one or more competitors. For a neutral comparison: two or more named items, genuinely peers, no ordering implication.
- What the person already knows — pitch, strengths, weaknesses for each item, and (battlecard only) objections prospects commonly raise. This is the primary source of truth. Ask for it directly rather than assuming you already know the landscape.
- Permission to supplement with web research (optional) — ask whether they'd like you to search for additional public information (pricing pages, marketing claims, review sites) to round out gaps. If they decline, work only from what they gave you.
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.
- 10d ago First seen · 186 lines · 116 tokens per session scan A fa6b80e25fe4
competitive-battlecard-builder is a skill published in the GitHub repository microsoft/cat-agent-skills (66 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 4,352 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
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…