powerbi
Skill4 starsChanged 7 days agoMITView on GitHub
Build and edit Power BI dashboards as code via PBIP projects — semantic model in TMDL, report pages and visuals in PBIR, theme JSON, deterministic validation, and publishing. Use when the team's BI tool is Power BI and a dashboard, measure, or model needs building, fixing, or reviewing.
4 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- robertoamoreno/powerbi-mcp-claudetheir own version, first seen Nov 8, 2026
- NewbieCoderLearnThings/Claude_skillstheir own version, first seen Oct 13, 2026
- link7373/agentic-pmoedited, first seen Aug 9, 2026
- francoisbgdw/claude-skillstheir own version, first seen Mar 19, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- link7373/agentic-pmo★ 153% same
Wrote their own version · 3
- robertoamoreno/powerbi-mcp-claude★ 1same name
- francoisbgdw/claude-skills★ 0same name
- NewbieCoderLearnThings/Claude_skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analyzeSkill
- build-dashboardSkill
- build-modelSkill
- build-pipelineSkill
- causal-analysisSkill
- connect-dataSkill
- define-kpisSkill
- evalSkill
- experimentSkill
- forecastSkill
- health-checkSkill
- investigate-metricSkill
- make-deliverableSkill
- privacy-reviewSkill
- research-domainSkill
- scorecardSkill
- setup-teamSkill
- tableauSkill
- triageSkill
- upgradeSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Spec before building: Do not re-derive the requirements here — /build-dashboard steps 1–4 own the audience, the 1–3 questions, the metrics …
- Distinctive: line 26
Validate before anyone opens it: Run the checker:
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Power BI — PBIP Authoring & Validation
Owner: dashboard-developer, with powerbi-validator for the validation gate and analytics-engineer for the data layer. Args describe the work, e.g. /powerbi build the exec revenue dashboard.
A PBIP project is plain text — TMDL for the model, JSON for the report. That makes a Power BI dashboard an ordinary code artifact: spec'd, built, diffed, reviewed, and version-controlled like everything else the team ships. Work it as code, not as a GUI you can't reach.
Procedure
- Check this is the right path. This skill applies when
{{BI_TOOL}}is Power BI, or the user explicitly asked for Power BI. If the team's tool is Tableau, Looker, Excel, or nothing yet, stop and return to/build-dashboard— none of the guidance below transfers. If{{BI_TOOL}}is still an unfilled placeholder, ask which tool the team uses before building anything. - Detect what you can actually do. Read
references/tooling-tiers.mdand run the detection commands. State the tier you're working in before you start — it determines whether you can bulk-format, publish, or only author files. Never install anything yourself; recommend, and say what the licence costs are, then let the user decide. - Spec before building. Do not re-derive the requirements here —
/build-dashboardsteps 1–4 own the audience, the 1–3 questions, the metrics (which must already exist inknowledge/metrics-catalog.md), the filters, and the layout sketch. This skill owns implementation only. If there's nodashboards/<name>/SPEC.mdyet, go write one first. - Build the model layer. Star schema, one dedicated date table, marts as the source — no heavy transformation inside Power BI (
standards/powerbi-standards.md). Author TMDL perreferences/semantic-model-tmdl.md; write measures perreferences/dax-patterns.md, named exactly asknowledge/metrics-catalog.mdnames them. A measure whose name or logic drifts from the catalog is a defect, not a variation — route conflicts tometrics-steward. - Build the report layer. Pages and visuals per
references/pbir-visuals.md. Chart choice, colour, layout, and decluttering come fromstandards/dashboard-standards.md— that file is the single source of truth for design and this skill does not restate or override it. Name every page and visual folder in[A-Za-z0-9_-]only; anything else is silently discarded by Desktop (references/gotchas.md). - Set the theme once. Encode the palette, semantic status colours, and typography in a theme file rather than formatting visuals individually (
references/theme-json.md). Theme-first is what makes the design standard hold across every page without hand-editing each visual — and what makes a rebrand a one-file change. - Validate before anyone opens it. Run the checker:
Fix every ERROR — those either block Desktop from opening or cause pages and visuals to vanish silently. Triage WARNs, don't ignore them. At Tier 2+, also runpython .claude/skills/powerbi/scripts/validate_pbip.py dashboards/<name>pbir validate. For anything stakeholder-facing, hand off topowerbi-validatorfor an independent pass. - Reconcile, then ship. Open the project in Power BI Desktop and confirm it renders — validation proves the files are well-formed, only Desktop proves the report works. Cross-check every displayed number against an independent direct query, saved in
dashboards/<name>/checks/. Screenshot intodashboards/<name>/, update thedashboards/README.mdinventory. Publishing to a broad or external audience → confirm with the user first (references/publishing.md). - Record what you learned. New model quirks or source oddities →
knowledge/data-sources.md. Methodological choices (exclusions, measure semantics, fiscal handling) →knowledge/decision-log.md. Anything materially off-trend you noticed while reconciling → the Observations section there too.
Hard rules
- Write every file as UTF-8 without BOM. A BOM anywhere in the project — including the gitignored
.pbi/localSettings.json— stops Desktop opening it entirely. On Windows,Set-Content -Encoding utf8,Out-File, and>in PowerShell 5.1 all add one; write from Python withencoding="utf-8"instead. - Never hand-edit a
.pbix. It is a binary. Convert to PBIP, or work through Desktop. - Never generate a
.platformfile. ItslogicalIdis assigned by Fabric; a hand-written one corrupts the Git link. Missing is a warning, not something to fix. - Never rewrite a DAX measure silently. Surface the change and the reason.
- Restart Desktop after external edits. It does not watch the filesystem and will overwrite your work from its in-memory copy.
Created by Colin Beck — https://www.linkedin.com/in/beckcolin/
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

