Individual skill

attribution-anomaly-diagnosis

Diagnose "why" questions about attribution anomalies — attribution=0 (no attributed orders), and sudden drops, spikes or retroactive changes in attributed numbers. Do NOT use for "show me numbers" — that's attribution-data-query.

skills/attribution-anomaly-diagnosis/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
data 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 · 10,709 bytes
examples/example-A-meta-roas-drop.mddoc · 2,951 bytes
references/basic-checks.mddoc · 2,439 bytes
references/edge-cases.mddoc · 816 bytes
references/failure-modes.mddoc · 1,439 bytes
references/fallback-structure.mddoc · 915 bytes
references/model-branches.mddoc · 4,244 bytes
references/output-template.mddoc · 3,047 bytes
references/scenario-snippets.mddoc · 2,225 bytes
templates/01-scope-lookup.sqlasset · 2,148 bytes
templates/02-spend-vs-attribution.sqlasset · 977 bytes
templates/03-measurement-readiness.sqlasset · 477 bytes
templates/04-utm-health.sqlasset · 720 bytes
templates/05-click-distribution.sqlasset · 1,210 bytes
templates/06-dda-vs-anyclick.sqlasset · 982 bytes
templates/07-lift-test-results.sqlasset · 726 bytes

Read excerpt


## 1. Purpose

Diagnose **"why" questions** about attribution anomalies — specifically **attribution = 0** (a tactic shows no attributed orders) and **attribution swings** (sudden drops / spikes / retroactive changes to historical numbers). 5-step diagnostic tree → internal report + client-facing explanation.

> **Shared conventions (canonical elsewhere — don't re-derive):** attribution model default + aliases and sales-platform scope + measurement identity live in **`attribution-data-query`** (`references/attribution-model.md`, `references/sales-platform-scope.md`); follow those (load the `attribution-data-query` skill from this plugin if it isn't loaded). Note this skill reads MMM-calibrated measures (`calibrated_*`) for some checks — a *different* measure from the `attr_*` the other skills use; keep them clearly labeled so a $ figure here is never confused with an attributed-sales figure. (Open question flagged to DS — see the team doc.)

**Do NOT use this skill for "show me the numbers" queries** — those belong to `attribution-data-query`.

## 2. When to trigger

Trigger when user is asking **why** attribution looks wrong, not just **what** the numbers are.

**Do NOT trigger**: