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 power-bi-model-reviewgit 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/power-bi-model-review)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/power-bi-model-review"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/power-bi-model-review/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/power-bi-model-review"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/power-bi-model-review.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 | $0.00075 | $0.01055 |
| Opus 5 | $0.00037 | $0.00528 |
| Sonnet 5 | $0.00015 | $0.00211 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
power-bi-model-review 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review the semantic model structure and DAX, report findings by category, and propose corrected DAX where relevant.
Instructions
-
Get the model definition. Accept a TMDL folder/export, a
.bim/JSON model definition, or a pasted description of tables, columns, relationships, and measures. If given only a screenshot or vague description, ask for the relationships and measure list directly. A review needs the actual expressions, not a summary of them. -
State this limit up front, in the first response: this is a static review of the model definition. It cannot connect to the live model, cannot see data volumes or cardinality, and cannot measure real query performance. Findings about likely performance impact are structural inference, not profiling results, so say so.
-
Check the model against each category below. Skip a category cleanly if the model doesn't contain what it checks (e.g. no bi-directional relationships to review).
-
Report findings grouped by category, worst-impact first:
Category Object Issue Fix Relationships Sales to Customer Bi-directional, both dimension tables Set to single-direction; use CROSSFILTER(..., BOTH)inside the one measure that needs itFor any DAX fix, show the corrected expression in full, not a diff.
-
On request, rewrite the flagged DAX or produce a prioritized backlog the user can hand to whoever maintains the model.
Review categories
Relationships
- Bi-directional relationships between two dimension tables, or wherever a
single-direction relationship plus a
CROSSFILTER(..., BOTH)inside the one measure that needs it would give the same answer with less filter-context ambiguity across the rest of the model. - Many-to-many relationships without a documented reason.
- Inactive relationships with no
USERELATIONSHIPreference anywhere in the model's measures. That's dead weight. - Missing or inconsistent relationship cardinality (e.g. many-to-many where one-to-many is intended).
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.
- 7d ago First seen · 106 lines · 75 tokens per session scan A 03c5f9ca3b21
power-bi-model-review is a skill published in the GitHub repository microsoft/cat-agent-skills (67 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 1,055 once invoked, about $0.0004 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.