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 santoshkanthety/powerbi-agent --skill powerbi-medallion-architecturegit clone --depth 1 https://github.com/santoshkanthety/powerbi-agentWrote 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/santoshkanthety/powerbi-agent/powerbi-medallion-architecture)<a href="https://agentmods.dev/skills/santoshkanthety/powerbi-agent/powerbi-medallion-architecture"><img src="https://agentmods.dev/badge/skills/santoshkanthety/powerbi-agent/powerbi-medallion-architecture/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/santoshkanthety/powerbi-agent/powerbi-medallion-architecture"><img src="https://agentmods.dev/badge/skills/santoshkanthety/powerbi-agent/powerbi-medallion-architecture.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 | $0.00000 | $0.00940 |
| Opus 5.5 | $0.00000 | $0.00376 |
| Sonnet 5.5 | $0.00000 | $0.00188 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
powerbi-medallion-architecture 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Medallion Architecture Design & Setup
Trigger
Activate when the user mentions: medallion, bronze, silver, gold, lakehouse, data lake, data architecture, layer design, raw layer, curated layer, semantic layer, OneLake
What You Know
You embody the experience of a 20+ year data architect who has designed and delivered enterprise medallion architectures on Microsoft Fabric and Azure Data Lake. You know every trade-off, every failure mode, and every shortcut worth taking.
The Three-Layer Medallion Pattern
OneLake
├── Bronze/ (Raw Ingestion)
│ ├── crm/
│ ├── erp/
│ └── files/
├── Silver/ (Cleaned & Conformed)
│ ├── dim_customer/
│ ├── dim_product/
│ └── fact_sales/
└── Gold/ (Business-Ready)
├── semantic_model/
├── finance_reporting/
└── marketing_analytics/
Bronze Layer — Raw Zone
- Never transform, never filter — store exactly as received
- Partition by ingestion date:
year=YYYY/month=MM/day=DD/ - Store as Parquet or Delta — never CSV (no schema enforcement)
- Preserve source system identifiers and timestamps
- Add metadata columns:
_ingested_at,_source_system,_file_name - Retain for minimum 7 years (audit trail, replays)
Silver Layer — Conformed Zone
- Apply data quality rules: nulls, duplicates, referential integrity
- Standardize data types (e.g., all dates as UTC timestamps)
- Resolve naming conflicts across source systems
- Implement slowly changing dimensions (SCD Type 1, 2, 6)
- Add surrogate keys — never expose natural keys to Gold
- Validate with Great Expectations or Fabric Data Quality
Gold Layer — Business Zone
- Optimized for analytical consumption
- Star Schema preferred for Power BI (see star-schema skill)
- Pre-aggregated rollup tables for large fact tables (>100M rows)
- Semantic layer aligned to business vocabulary
- RLS policies applied at this layer
- Delta tables with V-Order optimization for Power BI DirectLake
Fabric-Specific Guidance
DirectLake Performance — Gold Layer Rules
- Enable V-Order on all Delta tables:
OPTIMIZE table VORDER - Target file size: 128MB–1GB per Parquet file
- Partition only when cardinality > 10M rows and filter patterns are clear
- Avoid over-partitioning — it kills DirectLake scan performance
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 · 100 lines · 0 tokens per session scan A fef5eae34710
powerbi-medallion-architecture is a skill published in the GitHub repository santoshkanthety/powerbi-agent (3 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 940 tokens. 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.
Other skills, from other repositories
umap-learn
Applies UMAP-learn to nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows.
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…
shap
Explain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature attributions, handling multi-output explanations, and producing local or global SHAP visualizations.
torchdrug
Builds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
transformers
Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Applies when working with AutoModel, pipelines, tokenizers, generation configs, or TrainingArguments within Transformers.
deepspot-m
Generates transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Used for predicted log1p-CPM expression from 224x224 tiles at about 20x, querying the released protein-coding gene panel by symbol, and whole-slide prediction after resolution-aware tiling with histolab.