powerbi-dashboard-verify

powerbi-dashboard-verify is a skill for Claude Code from HamadYMarafi/powerbi-agent-mcp. It costs 94 tokens per session (1,421 once invoked), scanned A, original, MIT.

A verification workflow for Power BI and Microsoft Fabric reports after deployment. Power BI reports are interactive dashboards that display data, while deployment publishes them to a target environment.

In plain words
What is it for?
Use it after deploying a report to validate its JSON structure, compare definitions, check DAX results, inspect page screenshots, and test slicers.
Why use it?
A report can deploy without errors yet show blank pages, wrong numbers, clipped labels, or broken filters. This checks structure, calculations, screenshots, and filter states before the work is considered finished.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the powerbi-agent plugin — 3 skills shipped together

Good fit Use it after deploying a report to validate its JSON structure, compare definitions, check DAX results, inspect page screenshots, and test slicers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hamadymarafi/powerbi-agent-mcp/powerbi-dashboard-verify
Install

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.

Any agent
npx skills add HamadYMarafi/powerbi-agent-mcp --skill powerbi-dashboard-verify
Clone the repo
git clone --depth 1 https://github.com/HamadYMarafi/powerbi-agent-mcp

Made for: Claude Code.

Or install powerbi-agent, the plugin that ships this one along with the rest of its 3 skills.

Wrote 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.

agentmods badge for powerbi-dashboard-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/hamadymarafi/powerbi-agent-mcp/powerbi-dashboard-verify/github.svg)](https://agentmods.dev/skills/hamadymarafi/powerbi-agent-mcp/powerbi-dashboard-verify)
Your own site
<a href="https://agentmods.dev/skills/hamadymarafi/powerbi-agent-mcp/powerbi-dashboard-verify"><img src="https://agentmods.dev/badge/skills/hamadymarafi/powerbi-agent-mcp/powerbi-dashboard-verify/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.

agentmods 80×15 button for powerbi-dashboard-verify

Your own site · 80×15
<a href="https://agentmods.dev/skills/hamadymarafi/powerbi-agent-mcp/powerbi-dashboard-verify"><img src="https://agentmods.dev/badge/skills/hamadymarafi/powerbi-agent-mcp/powerbi-dashboard-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,421 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.01421
Opus 5 $0.00047 $0.00711
Sonnet 5 $0.00019 $0.00284
Haiku 4.5 $0.00009 $0.00142

Measured 11d ago against content hash 625282110e85, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

powerbi-dashboard-verify 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.

skills/powerbi-dashboard-verify/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Power BI dashboard verify

A report that deploys cleanly and renders blank looks identical from the API. This skill is the post-deploy check that catches what structural validation cannot see — docs/reference/PLAYBOOK.md 1.3. Run it after every deploy, not just the first one: any deploy re-opens the loop.

The four verification levels

Each level catches what the one before it cannot (docs/reference/PLAYBOOK_PART3.md Step 10):

Level Tool Catches Cannot see
1 Offline JSON validate_report schema errors, overlaps, out-of-canvas, missing date pins, theme drift, banned filter kinds, saved slicer picks field errors the service only resolves at render time
2 DAX tie-out run_dax wrong numbers, a broken last-year basis, measure bugs layout, formats, labels
3 Screenshots capture_pages clipping, label truncation, wrong sort, error tiles, wrong series, a weekly value on a daily axis slicer behaviour
4 Slicer-state capture capture_pages, one state per pass blank pages, filters that ignore context, broken sync, a reset that does not reset, persisted state

Run them in order — levels 1 and 2 are free (no render, no capacity cost). Never jump to level 3 or 4 to save time: a page can fail level 1 or 2 in a way that makes the screenshot round pointless.

Procedure

  1. validate_report(folder, baseline) — do not continue past a nonzero error count. Read the warnings too; a warning outside the two known kinds (duplicate filter names by design, an unreachable offline schema URL) means look closer before dismissing it.
  2. Structural diff: get_report_definition(report, out_dir, workspace) on the just-deployed item, then compare its JSON against the local folder that was deployed. They should match part for part — a difference here is a deploy problem, not a design problem, and it is cheaper to catch here than in a wrong screenshot.
  3. run_dax(query, ...) — one batched query — only if no tie-out table already exists from the build; otherwise reuse it rather than re-deriving it.
  4. capture_pages(target, out_dir, headless=True, settle_seconds=60) for every page, in every state a user can put it in:

Read the full file on GitHub · 100 lines

Changes

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.

  1. 11d ago First seen · 100 lines · 94 tokens per session scan A 625282110e85

Subscribe to this mod's changes

powerbi-dashboard-verify is a skill published in the GitHub repository HamadYMarafi/powerbi-agent-mcp (1 stars, last pushed 13d ago), licensed MIT. It adds 94 tokens to every session and 1,421 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

dashboard-design

Use this skill first when the user wants to design or plan a dashboard, especially Vizro dashboards. Enforces a 3-step workflow (requirements, layout, visualization) before implementation. Activate when the user asks to create, design, or plan a dashboard. For implementation, use the dashboard-build skill after…

mckinsey/vizro · 71 tokens

wiring-vizro-actions

Use this skill when adding cross-filter, cross-highlight, drill-through, or data export interactions to a Vizro dashboard — both for choosing the right interaction pattern during design and for implementing actions in code. Activate when the user wants clicks on a chart or table to filter or highlight other charts…

mckinsey/vizro · 86 tokens

writing-vizro-yaml

Use this skill when writing or debugging Vizro YAML dashboard configurations — component syntax, datamanager registration, custom function wiring, filter/parameter setup, or AG Grid tables. Activate when the user is building a Vizro app, encountering YAML or runtime errors, or asking about Vizro component patterns.

mckinsey/vizro · 66 tokens

selecting-vizro-charts

Use this skill when choosing chart types, applying Plotly Express conventions, configuring colors, building KPI cards, or adding tables (AG Grid) to Vizro dashboards. Activate when the user asks which chart fits their data, needs custom chart functions, wants to set colors or palettes, is creating KPI metric cards, or…

mckinsey/vizro · 78 tokens

designing-vizro-layouts

Use this skill when designing or building Vizro dashboard layouts — grid configuration, component sizing, filter/parameter placement, selector types, or container patterns. Activate when the user is creating wireframes, defining page structure, placing controls, or sizing charts.

mckinsey/vizro · 58 tokens

dashboard-build

Use this skill to build, implement, and test Vizro dashboards (Phase 2). Activate when the user wants to create a working app, says "just build it", or has data ready for implementation. Requires spec files from the dashboard-design skill (Phase 1), or user confirmation to skip design.

mckinsey/vizro · 65 tokens