semantic-overlap-detection

semantic-overlap-detection is a skill for Claude Code, Codex from fabioc-aloha/Alex_Skill_Mall. It costs 99 tokens per session (6,350 once invoked), scanned A, a copy of semantic-model-disambiguation, MIT.

An analysis workflow for finding columns in a Power BI semantic model whose values overlap and may be mistaken for one another by AI tools.

In plain words
What is it for?
Use it to inspect a model, suggest descriptions or exclusions, and create an Excel workbook for expert review.
Why use it?
It exposes ambiguous data definitions before Copilot or a Fabric data agent uses the model and produces misleading answers.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it to inspect a model, suggest descriptions or exclusions, and create an Excel workbook for expert review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fabioc-aloha/alex_skill_mall/semantic-overlap-detection
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 fabioc-aloha/Alex_Skill_Mall --skill semantic-overlap-detection
Clone the repo
git clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_Mall

Made for: Claude Code, Codex.

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 semantic-overlap-detection

README.md
[![agentmods](https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/semantic-overlap-detection/github.svg)](https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/semantic-overlap-detection)
Your own site
<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/semantic-overlap-detection"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/semantic-overlap-detection/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 semantic-overlap-detection

Your own site · 80×15
<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/semantic-overlap-detection"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/semantic-overlap-detection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,350 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 88% copy Near-identical to another mod 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 $0.00099 $0.06350
Opus 5 $0.00049 $0.03175
Sonnet 5 $0.00020 $0.01270
Haiku 4.5 $0.00010 $0.00635

Measured 8d ago against content hash 5ef274db189f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

semantic-overlap-detection 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate_disambiguation_excel.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

88% identical to semantic-model-disambiguation — 219 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/data-analytics/semantic-overlap-detection/skills/semantic-overlap-detection/SKILL.md · 428 lines

How it starts

The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Semantic Overlap Detection

Analyze a semantic model (via MCP connection or TMDL export) to find columns whose value domains overlap, classify ambiguity types, generate proposed fixes, and produce a review Excel workbook for domain expert review. This skill covers the full analysis pipeline through Excel generation and async handoff.

Next step after this skill: Once the domain expert has reviewed the Excel, use the semantic-disambiguation skill to apply approved changes to the live model.

When to Use

  • A semantic model has multiple columns that could plausibly match the same natural-language query
  • A Fabric data agent or Copilot is silently picking the wrong column
  • You need to prepare a model for the "Prep data for AI" workflow
  • You want to audit a TMDL export for disambiguation gaps before connecting a data agent

Procedure

Phase 0: Read Model Metadata via MCP (preferred) or TMDL files

MCP tool naming: This skill references tools by their VS Code MCP integration names (mcp_powerbi-modeling-mcp_*). In other environments (Agency CLI, Claude Code), find the equivalent Power BI Modeling MCP server tools — the operations and parameters are the same, only the tool name prefix may differ.

If MCP tools are available, connect to the live model and read metadata directly. This is preferred over TMDL file parsing because it reflects the current model state, includes runtime metadata (hidden flags, descriptions), and avoids stale exports.

  1. Connect via mcp_powerbi-modeling-mcp_connection_operations:

    • Fabric: ConnectFabric with workspace and dataset names
    • Desktop: Connect with port number
  2. List all tables via mcp_powerbi-modeling-mcp_table_operations (operation: List). For each table, record:

    • name, isHidden, description
    • Skip tables where isHidden = true
  3. List columns per table via mcp_powerbi-modeling-mcp_column_operations (operation: List, filter by tableNames). For each column, record:

    • name, tableName, dataType, isHidden, description, sourceProviderType
    • Skip columns where isHidden = true or dataType is not string/text

Read the full file on GitHub · 428 lines

Files

What ships with it

5 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.

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. 8d ago First seen · 428 lines · 99 tokens per session scan A 5ef274db189f

Subscribe to this mod's changes

semantic-overlap-detection is a skill published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (4 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 6,350 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to semantic-model-disambiguation, differing in 219 lines, and is treated as a copy.

Related

Other skills, from other repositories