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 jonathan-pap/powerbi-report-mcp --skill design-power-bi-reportgit clone --depth 1 https://github.com/jonathan-pap/powerbi-report-mcpWrote 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/jonathan-pap/powerbi-report-mcp/design-power-bi-report)<a href="https://agentmods.dev/skills/jonathan-pap/powerbi-report-mcp/design-power-bi-report"><img src="https://agentmods.dev/badge/skills/jonathan-pap/powerbi-report-mcp/design-power-bi-report/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/jonathan-pap/powerbi-report-mcp/design-power-bi-report"><img src="https://agentmods.dev/badge/skills/jonathan-pap/powerbi-report-mcp/design-power-bi-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00067 | $0.00898 |
| Opus 5 | $0.00034 | $0.00449 |
| Sonnet 5 | $0.00013 | $0.00180 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
design-power-bi-report 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design a Power BI Report
Most "bad" Power BI reports aren't broken because of formatting or colors. They're broken because nobody decided what question the page answers before placing visuals. Design starts with a mental model, not a color picker.
Mental model — before you place a single visual
- Name the page's one job. Every page answers exactly one question. "How did we do last quarter?" "Which customers are at risk?" If you can't write it in one sentence, ask the user. Two-question pages become two pages.
- Pick the headline number. The page's job translates to one most-important metric. It goes in the largest, leftmost, top-most card. Everything else is context or breakdown for that number.
- Context before detail. Headline first; then trend/variance row; then breakdown by segment; then detail tables at the bottom. This is the 3-30-300 rule expressed as layout.
- Delete rather than add. Every visual competes for attention. A 5-visual page where all 5 matter reads better than an 8-visual page where 5 matter.
- Pre-attentive attributes are a budget. Position, size, color, motion — you have roughly one of each to spend per page. If every card is red, nothing is urgent. Spend the color budget on the one thing the viewer should notice.
- Stop at the theme. Polish belongs to the developer. Set
pbir_set_report_themeonce and let it cascade. Avoid per-visualpbir_format_visualunless the user explicitly asked. Inline only titles, bindings, and semantic colors (gains green / losses red).
Typography (Segoe UI defaults)
| Element | Size | Weight |
|---|---|---|
| Page title (banner) | 20-24pt | SemiBold |
| Section header | 14-16pt | SemiBold |
| Card value | 24-32pt | Bold |
| Card label | 10-12pt | Regular |
| Axis / data labels | 9-12pt | Regular |
| Footnote / source | 8-9pt | Regular |
Color budget
- Neutral base (greys, off-white) for chrome — banners, borders, backgrounds.
- One brand accent for the headline metric and primary CTAs.
- Two semantic colors — green for gains, red for losses. Never use red for "important" — only for "bad."
- Categorical palette of 4-6 muted hues for breakdown charts. Avoid rainbow.
What ships with it
1 file 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 · 57 lines · 67 tokens per session scan A f96b302a0c8e
design-power-bi-report is a skill published in the GitHub repository jonathan-pap/powerbi-report-mcp (19 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 898 once invoked, about $0.0003 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
flint-theme-author
Use when: creating, translating, refining, reviewing, or validating a custom Flint ThemeSpec from brand guidelines, websites, slide decks, publication references, design tokens, or an existing visual identity. Produce a reusable ThemeSpec JSON object for Flint Theme Lab without inventing fields or changing chart…
b123d-modeling
Use this skill when asked to model, build, or modify a 3D part or assembly with build123d — from a text description, a technical drawing (image or PDF), dimensions in a spec, or an existing STEP/STL file.
openclaw-color-palette
Design-grade color processing suite — generate harmonious palettes from any seed color, check WCAG 2.1 AA/AAA contrast accessibility, convert between hex/RGB/HSL/HSV/CMYK, simulate 8 color blindness types, and extract dominant colors from images. Use when: (1) user says 'generate a color palette' or 'give me a color…
frontend-ui-engineering
Build user-facing UI with responsive behavior, accessibility, runtime validation, and design-system consistency.
conversational-ux
Design voice and conversational interfaces — dialog flows, error recovery, and persona. Use when the interface speaks and listens rather than being tapped. For graphical input collection, use form-design.
critique-color
Critique a rendered screen's colour — contrast ratios, palette coherence, and semantic meaning. Use when reviewing one screen. For a product-wide WCAG audit use accessibility-audit (design-systems); for building the palette use color-system (ui-design).