fabric-semantic-model-ai-instructions

fabric-semantic-model-ai-instructions is a skill for Claude Code from wardawgmalvicious/agent-config. It costs 154 tokens per session (3,046 once invoked), scanned A, original, MIT.

A guide to adding written instructions to a Power BI semantic model, the data-and-calculations layer behind reports. Copilot uses these instructions to understand business terms, context, dates, and calculation rules when answering questions about the model.

In plain words
What is it for?
Use it to write and attach model-wide guidance, and to decide whether that guidance belongs on the semantic model or in a separate Data Agent conversation.
Why use it?
It gives Copilot the business context needed to interpret questions consistently across reports and other places that use the model.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it to write and attach model-wide guidance, and to decide whether that guidance belongs on the semantic model or in a separate Data Agent conversation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wardawgmalvicious/agent-config/fabric-semantic-model-ai-instructions
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 wardawgmalvicious/agent-config --skill fabric-semantic-model-ai-instructions
Clone the repo
git clone --depth 1 https://github.com/wardawgmalvicious/agent-config

Made for: Claude Code.

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 fabric-semantic-model-ai-instructions

README.md
[![agentmods](https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/fabric-semantic-model-ai-instructions/github.svg)](https://agentmods.dev/skills/wardawgmalvicious/agent-config/fabric-semantic-model-ai-instructions)
Your own site
<a href="https://agentmods.dev/skills/wardawgmalvicious/agent-config/fabric-semantic-model-ai-instructions"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/fabric-semantic-model-ai-instructions/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 fabric-semantic-model-ai-instructions

Your own site · 80×15
<a href="https://agentmods.dev/skills/wardawgmalvicious/agent-config/fabric-semantic-model-ai-instructions"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/fabric-semantic-model-ai-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,046 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 $0.00154 $0.03046
Opus 5 $0.00077 $0.01523
Sonnet 5 $0.00031 $0.00609
Haiku 4.5 $0.00015 $0.00305

Measured yesterday against content hash 58ff40046887, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fabric-semantic-model-ai-instructions 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 yesterday.

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/fabric/fabric-semantic-model-ai-instructions/SKILL.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configuring Power BI Semantic Model AI Instructions

A practical, reusable guide for configuring AI instructions on a semantic model. Use this template across projects — the example domain (retail / sales) is illustrative; replace it with your own without changing the structure.


What semantic model AI instructions are

A single text blob (up to 10,000 characters) attached directly to the semantic model. It provides context, business logic, and guidance that Copilot uses when interpreting user questions against the model.

It applies wherever the model is consumed by Copilot — Power BI reports, Q&A visuals, the Copilot pane, and any downstream surface that uses this model. Not just a single surface.


When you use this vs. Data Agent instructions

  • Semantic Model AI Instructions — guidance attached to one semantic model. No multi-source routing, no conversational flow. Applies to every Copilot interaction with this model.
  • Data Agent — a separate conversational interface with multi-source routing, few-shot example queries, and conversational response formatting.

See the fabric-data-agent skill for data agent specifics.


Setup process

Authoring is now available in both Power BI Desktop and the Power BI service. Consumption happens everywhere Copilot exists.

  1. Open the semantic model in Power BI Desktop, or select the model in the Power BI service.
  2. On the Home ribbon, click Prep data for AI.
  3. If the tabs are disabled, enable Power BI Q&A on the model first.
  4. Go to the Add AI instructions tab.
  5. Paste or author the instructions.
  6. Click Apply.
  7. Test using the Copilot pane with the Answers questions about the data skill selected.
  8. Publish or save the model. Instructions take effect everywhere Copilot uses this model.

Notes:

  • Each time you edit instructions during testing, close and reopen the Copilot pane to pick up the changes.
  • End users cannot see or disable these instructions.

Read the full file on GitHub · 295 lines

Files

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.

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. yesterday Changed 58ff40046887
  2. 6d ago Changed b111ed6b6071
  3. 7d ago Changed · +3 lines ddd2b54d828d
  4. 11d ago First seen · 292 lines · 154 tokens per session scan A a288b91e15ce

Subscribe to this mod's changes

fabric-semantic-model-ai-instructions is a skill published in the GitHub repository wardawgmalvicious/agent-config (0 stars, last pushed today), licensed MIT. It adds 154 tokens to every session and 3,046 once invoked, about $0.0008 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

vendor-prompting

ANALYSIS SKILL — Audit-grade reference for Anthropic Claude and OpenAI GPT-5.6 prompting best practices. WHEN: "claude prompting", "gpt-5.6 prompting", "audit agent", "review prompt", "vendor best practices", "anthropic best practices", "openai prompting". DO NOT USE FOR: routine prompt edits where rules are already…

jonathan-vella/apex-accelerator · 94 tokens

create-simple-prompt

This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to create a new prompt sample with proper folder structure, README, and sample.json metadata. Do NOT use this skill for agent…

pnp/copilot-prompts · 80 tokens

prompt-context-engineer

Transform any rough prompt, request, or idea into a well-structured, context-engineered prompt using Andrej Karpathy's context engineering principles. Use this skill whenever the user asks to improve, rewrite, restructure, optimize, or "engineer" a prompt; mentions prompt engineering or context engineering; pastes a…

pnp/copilot-prompts · 180 tokens

813-regulations-iso-42001

Use when reviewing, designing, or modifying Java enterprise systems that use GenAI, LLMs, AI-assisted coding, RAG, AI agents, generated code, generated dependencies, prompt workflows, external model providers, or AI-enabled business logic and need ISO/IEC 42001 AI management system-aware engineering guidance. Part of…

jabrena/plinth · 77 tokens

skill-copilot

AL Copilot capability development for Business Central. Use when implementing PromptDialog pages, AI generation features, or integrating with the Copilot toolkit.

javiarmesto/ALDC-AL-Development-Collection · 33 tokens

deploy-model

Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai…

jonathan-vella/apex-accelerator · 129 tokens