Microsoft Fabric Skills is a collection of reusable instructions and MCP systems that help AI assistants work with Microsoft Fabric workloads, APIs, queries, and operations. It is intended for users of GitHub Copilot CLI and compatible coding tools; the catalogue entries are the skills, agents, instructions, MCP systems, plugins, and rules distributed by the project.
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/skills-for-fabric --skill powerbi-report-designgit clone --depth 1 https://github.com/microsoft/skills-for-fabricWrote 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/skills-for-fabric/powerbi-report-design)<a href="https://agentmods.dev/skills/microsoft/skills-for-fabric/powerbi-report-design"><img src="https://agentmods.dev/badge/skills/microsoft/skills-for-fabric/powerbi-report-design/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/skills-for-fabric/powerbi-report-design"><img src="https://agentmods.dev/badge/skills/microsoft/skills-for-fabric/powerbi-report-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00153 | $0.03714 |
| Opus 5 | $0.00077 | $0.01857 |
| Sonnet 5 | $0.00031 | $0.00743 |
| Haiku 4.5 | $0.00015 | $0.00371 |
Grade A, and why
powerbi-report-design 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- powerbi-report-design — 95% identical, 17 lines differ
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power BI Report Design Skill
This skill provides design guidance for Power BI reports. It commits a design identity (tone + signature), routes user requests to the right archetype per page, and applies cross-cutting design principles (color, typography, iconography, layout, interactivity, accessibility).
Scope boundary — This skill decides what a report should look like and why. It does not write PBIR files. After producing a design contract, hand off to powerbi-report-authoring for all file mechanics: page/visual creation, theme registration, expression encoding, formatting objects, and validation.
Must/Prefer/Avoid
MUST
- Inspect the semantic model or available fields before making design decisions.
- Produce concrete design choices: tone, signature, page archetype, chart rationale, layout direction, color, typography, and accessibility considerations.
- Hand off file mechanics to
powerbi-report-authoring; this skill does not edit PBIR.
PREFER
- Ask only for missing design inputs that materially affect the outcome.
- Use reference files on demand instead of loading the full design catalog.
- Emit a structured
Design Brief:when the design will be implemented.
AVOID
- Do not create pages, visuals, filters, themes, or PBIR files directly.
- Do not provide vague "make it modern" guidance without concrete layout/color/chart decisions.
- Do not replace the planning workflow for broad create/build requests.
Topic Files and Examples
This root file covers the end-to-end workflow, theme, gotchas, and the design contract template. Read the topic files as needed:
| File | When to read |
|---|---|
references/tone-catalog.md |
Read when the prompt lacks a specific tone or needs concrete downstream palette/type choices |
references/signatures.md |
Read when selecting or refining the report's signature visual move |
references/archetype-composition.md |
Read for multi-page reports when page roles or variant rotation are unclear |
references/archetypes/<name>.md |
Read before laying out each page — layout template, density, chart mix |
references/chart-selection.md |
Read before selecting a chart type — encoding hierarchy, purpose matching |
references/visual-cookbook.md |
Read before configuring any visual — sort, color, labels, CF per type |
references/layout.md |
Read before placing visuals on canvas — 8-px grid, composition templates |
references/color.md |
Read if defining palette, color semantics, gradients, or conditional formatting |
references/typography.md |
Read if overriding font sizes, type pairings, or weight conventions |
assets/base.json |
Read before theme work for generated reports — preserve its textbox/card/table per-type safeguards when adapting a custom theme |
references/interactivity.md |
Read if adding drill-through, bookmarks, or cross-filter rules |
references/brownfield.md |
Read for redesigns, restyles, theme swaps, or brand application |
references/accessibility.md |
Read before finalizing any report — WCAG checklist, alt text, contrast |
references/anti-patterns.md |
Read before finalizing any report — common failures and how to fix them |
references/pre-flight-checklist.md |
Read for the full checklist before handoff/final audit |
references/design-brief.md |
Read before handoff — full Design Brief: template, mechanical layout_contract schema, page title/header band, slicer placement, non-overlap rules, and validation checklist |
What ships with it
20 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.
- assets/base.json 7.5 KB
- references/accessibility.md 10 KB
- references/anti-patterns.md 18 KB
- references/archetype-composition.md 3.4 KB
- references/archetypes/analytical-canvas.md 16 KB
- references/archetypes/comparative-benchmark.md 20 KB
- references/archetypes/executive-summary.md 14 KB
- references/archetypes/narrative-story.md 17 KB
- references/archetypes/operational-monitor.md 16 KB
- references/brownfield.md 5.3 KB
- references/chart-selection.md 9.2 KB
- references/color.md 9.6 KB
- references/design-brief.md 21 KB
- references/interactivity.md 6.5 KB
- references/layout.md 11 KB
- references/pre-flight-checklist.md 10 KB
- references/signatures.md 11 KB
- references/tone-catalog.md 14 KB
- references/typography.md 8.7 KB
- references/visual-cookbook.md 27 KB
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 · 231 lines · 153 tokens per session scan A 038d10f6b6f6
powerbi-report-design is a skill published in the GitHub repository microsoft/skills-for-fabric (1,140 stars, last pushed yesterday), licensed MIT. It adds 153 tokens to every session and 3,714 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.