Individual skill

attribution-custom-dimension

Handle attribution queries sliced by a business label ("by audience" / "by region" / "by brand") that is not a native field — it lives in campaign names and only becomes queryable once a Naming Convention (NC) rule is configured.

skills/attribution-custom-dimension/SKILL.md

Read pinned source

Source commit ef1c5166a62ffcabc8092680c339e8e424b6a1f7

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: Yes
Skill scan complete: Yes
Observed behavior: Network or broad shell
Last checked: Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 9
Repository last updated: Nov 6, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
attribution Repository topic
chatgpt Repository topic
claude Repository topic
claude-plugin Repository topic
codex Repository topic
cursor Repository topic
ecommerce Repository topic
gemini-cli-extension Repository topic
incrementality Repository topic
marketing Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 10,630 bytes
examples/example-A-audience-state-c.mddoc · 3,906 bytes
references/edge-cases.mddoc · 1,841 bytes
references/failure-modes.mddoc · 2,063 bytes
references/output-template.mddoc · 1,074 bytes
references/state-routing.mddoc · 1,920 bytes
templates/01-sample-campaign-names.sqlasset · 593 bytes
templates/02-nc-sanity-check.sqlasset · 566 bytes
templates/proposal-message.mddoc · 1,300 bytes

Read excerpt


## 1. Purpose

Handle queries that slice attribution data by a **business label** (e.g., "by region", "by audience", "by brand", "by product line") where the label isn't a native field — it lives inside campaign names and only becomes a real dimension once a **Naming Convention (NC)** rule is configured for the tenant.

This skill detects NC state, guides configuration when needed in business language, and continues the original query after configuration. **The user should rarely (ideally never) have to leave the chat to set up NC themselves.**

> **Shared conventions + output mode:** the final data answer is produced by `attribution-data-query` (handoff), so it inherits that skill's conventions and **output threshold** — a "by <label>" breakdown is report-shaped and comes back as a live **artifact**, not a wall of table. Sales-platform scope + attribution model are canonical in `attribution-data-query` (`references/attribution-model.md`, `references/sales-platform-scope.md`); don't re-derive them here.

## 2. When to trigger

Trigger when the user asks for data **"by <business term>"** where the term isn't a built-in WM dimension.

**Detection rule**: after `dashboard-metrics-list` with the tenant's `tenantId`, if the requested dimension term isn't in the returned property list (built-in or NC-derived), this skill takes over.