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-template-enforcergit 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-template-enforcer)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/brand-template-enforcer"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/brand-template-enforcer/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-template-enforcer"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/brand-template-enforcer.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 | $0.00113 | $0.02639 |
| Opus 5 | $0.00056 | $0.01319 |
| Sonnet 5 | $0.00023 | $0.00528 |
| Haiku 4.5 | $0.00011 | $0.00264 |
Grade A, and why
brand-template-enforcer 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 11d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent runtime instructions
Before generating a PowerPoint or Word file, select and apply a compatible
template from assets/.
Instructions
- Determine the requested output:
- PowerPoint:
.pptx - Word:
.docxor.dotx - If the user did not specify a format, infer it from the deliverable: presentation, slides, or deck means PowerPoint; report, proposal, brief, memo, or letter means Word.
- PowerPoint:
- Inventory compatible Office template binaries available in
assets/and the agent's configured knowledge sources.- Treat
assets/template-manifest.jsonas optional routing configuration. - Use fully configured enabled manifest entries when available.
- Ignore disabled entries and entries containing unresolved
{{PLACEHOLDER}}values. These starter entries MUST NOT block discovery of valid templates available elsewhere.
- Treat
- Select the template using this order:
- A template explicitly named by the user.
- Ignore every manifest entry where
enabledisfalse. - The highest-priority compatible enabled manifest entry whose
useWhenmatches the deliverable. - The compatible enabled manifest default.
- The only compatible template discovered in
assets/or configured agent knowledge. - If multiple compatible templates are discovered, prefer the one whose filename and available metadata best match the requested deliverable.
- If multiple templates remain equally suitable, ask the user to choose.
- Resolve the selected template:
- For a manifest-selected template, resolve its ordered
sources: use an existingassetfirst, then retrieve the exact configuredsharepointKnowledgefile. - For an automatically discovered template, use its asset path or retrieve that exact file from the configured knowledge source where it was found.
- Retrieve the actual Office binary. Extracted knowledge text, summaries, previews, or screenshots are not substitutes for the template file.
- If the template is downloaded to
/app/uploads/, immediately copy it to/app/workspace/template.pptxfor PowerPoint or/app/workspace/template.docxfor Word. Pass only the workspace copy to preprocessing and generation scripts. - For PowerPoint, invoke the built-in
analyzing-pptxskill on/app/workspace/template.pptxto inspect slide masters, layouts, and placeholder indices before generation. Retain the workspace binary for template-based generation. - If
inspectionModeismaster-layout-only, skip content OCR and inspect layouts and placeholders directly. If automatic analysis returns zero OCR characters for every slide, stop further OCR attempts and switch immediately to master, layout, and placeholder inspection. - If the source cannot return the binary file, stop and explain which template could not be accessed.
- For a manifest-selected template, resolve its ordered
- If no compatible template exists, stop before generating the file. Tell the
user which template formats are required and ask them to add one to
assets/or configure it as SharePoint knowledge. Generate without a template only when the user explicitly approves an unbranded exception. - Copy the selected template to a new output file. NEVER overwrite or modify the bundled template.
- Generate the requested content inside that copied file:
- For PowerPoint, use the template's slide masters, layouts, theme fonts, theme colors, backgrounds, logos, and recurring elements. Create slides from existing layouts rather than blank slides.
- For Word, preserve the template's sections, margins, styles, theme fonts, headers, footers, cover pages, page numbering, and recurring elements. Apply named styles rather than direct formatting.
- Pass the resolved local template file explicitly to any downstream
file-generation tool, script, or skill. Do not merely describe the brand or
approximate its colors in a newly created blank file. NEVER pass an
/app/uploads/path to a generation script. - Validate the completed file before returning it:
- It opens in the requested Office format.
- Template branding, layouts, styles, headers, footers, and logos remain.
- No template placeholder text remains unless the user requested it.
- Content is readable and does not visibly overflow or overlap.
- Return the branded output and identify the template filename and source used.
What ships with it
5 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.
- 11d ago First seen · 245 lines · 113 tokens per session scan A 0408c45eeb25
brand-template-enforcer is a skill published in the GitHub repository microsoft/cat-agent-skills (67 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 2,639 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
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
applying-brand-guidelines
This skill applies consistent corporate branding and styling to all generated documents including colors, fonts, layouts, and messaging.
html-ppt-obsidian-claude-gradient
OpenDesign's enterprise AI-adoption brief: local-first agents at work, the risk controls, the ROI, and the rollout plan. Built as a decision-grade AI literacy deck for leadership, IT, security.
kami
A design and typesetting guide for creating professional documents and product landing pages, such as resumes, white papers, portfolios, and slide decks.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
mermaid-tools
Extracts Mermaid diagrams from markdown files and generates high-quality PNG images using bundled scripts. Activates when working with Mermaid diagrams, converting diagrams to PNG, extracting diagrams from markdown, or processing markdown files with embedded Mermaid code.