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 PBI-Guy/Power-BI-Optimization-Skill --skill powerbi-optimizationgit clone --depth 1 https://github.com/PBI-Guy/Power-BI-Optimization-SkillWrote 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/pbi-guy/power-bi-optimization-skill/powerbi-optimization)<a href="https://agentmods.dev/skills/pbi-guy/power-bi-optimization-skill/powerbi-optimization"><img src="https://agentmods.dev/badge/skills/pbi-guy/power-bi-optimization-skill/powerbi-optimization/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/pbi-guy/power-bi-optimization-skill/powerbi-optimization"><img src="https://agentmods.dev/badge/skills/pbi-guy/power-bi-optimization-skill/powerbi-optimization.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 | $0.00135 | $0.03128 |
| Opus 5.5 | $0.00054 | $0.01251 |
| Sonnet 5.5 | $0.00027 | $0.00626 |
| Haiku 4.5 | $0.00014 | $0.00313 |
Grade A, and why
powerbi-optimization 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 1mo 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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power BI Optimization Skill
Hub skill: Comprehensive Power BI analysis across DAX, model design, and report performance. Invokes specialist skills for deep-dive optimization.
When to Use This Skill
Use when:
- Analyzing Power BI performance issues (slow reports, queries, refresh)
- Optimizing DAX measures, semantic models, or report layouts
- Need triage across multiple domains (DAX + Model + Report)
- Reviewing Power BI solutions for best practices
- Troubleshooting incorrect calculations or unexpected behavior
🎯 Quick Reference: When to Use Which Specialist
| When you have... | Use specialist... | Examples |
|---|---|---|
| Slow measure/formula | @dax-mastery |
Iterators, context transitions, calculation groups, time intelligence |
| Schema/relationship issue | @model-design |
Star schema, many-to-many, storage modes, incremental refresh, unused objects |
| Slow visual/report | @report-performance |
Too many visuals, UX design, accessibility, custom visuals |
| Slow refresh/load | @powerquery-m |
Query folding, M optimization, connector issues, transformation performance |
| RLS issue | @security-rls |
Row-level security, dynamic security, performance with RLS |
Quick Start: 3-Step Workflow
1️⃣ Scope & Context
- Identify what to analyze: DAX measure, model structure, report layout, or end-to-end
- Gather context: data volume, user count, refresh frequency, current performance metrics
- Check for specific goals: performance target, business requirements, constraints
2️⃣ Detect & Prioritize
Run quick checks across domains:
- DAX: Iterators (SUMX, FILTER), context transitions, missing variables, time intelligence patterns
- Model: Star schema validation, cardinality, bi-directional relationships, storage modes
- Report: Visual count (>10 flag), expensive custom visuals, cross-highlighting, slicer design
Priority framework:
- P0 - Incorrect results, severe performance (>30s queries)
- P1 - Major performance issues (10-30s), important UX problems
- P2 - Moderate impact (5-10s), minor UX issues
- P3 - Optimization opportunities, cosmetic improvements
What ships with it
11 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.
- analysis-framework.md 16 KB
- BPA-GUIDE.md 26 KB
- handoff-patterns.md 20 KB
- mcp-config-sample.json 5.6 KB
- MCP-GUIDE.md 34 KB
- specialists/dax-mastery.md 12 KB
- specialists/model-design.md 14 KB
- specialists/powerquery-m.md 6.8 KB
- specialists/report-performance.md 9.0 KB
- specialists/security-rls.md 8.4 KB
- templates/analysis-report.md 6.7 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.
- 1mo ago First seen · 345 lines · 135 tokens per session scan A b3261ecebc67
powerbi-optimization is a skill published in the GitHub repository PBI-Guy/Power-BI-Optimization-Skill (29 stars, last pushed 4mo ago), licensed MIT. It adds 135 tokens to every session and 3,128 once invoked, about $0.0005 per session on Opus 5.5. 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
dotnet-testing-advanced-tunit-advanced
A guide for advanced TUnit testing in .NET. TUnit is a testing framework; the guide covers tests driven by data, dependency injection, integration tests, retries, time limits, and filtering.
dotnet-testing-autodata-xunit-integration
A guide for using AutoFixture, a .NET library that creates test data, with xUnit, a .NET testing framework. It explains attributes such as AutoData, InlineAutoData, and MemberAutoData for supplying values to parameterized tests.
dotnet-testing-autofixture-nsubstitute-integration
A .NET testing guide for using AutoFixture and NSubstitute to automatically create test data and substitute versions of dependencies.
dotnet-testing-bogus-fake-data
A guide to Bogus, a .NET library for generating realistic fake data such as names, addresses, phone numbers, emails, and product records. It shows how to define generation rules and create one or many records.
dotnet-testing-advanced-aspire-testing
A guide to testing .NET Aspire distributed applications, which are programs made of several coordinated services. It covers tests that run the real service setup through an AppHost, the project that describes how those services are arranged.
dotnet-testing-advanced
A guide that routes advanced .NET testing questions to the right specialist instructions. It covers API and integration tests, database and other container-based tests, microservices, .NET Aspire, and related testing tools.