Menu

Individual skill

investigation-methodology

0upvotes

Structured hypothesis-driven investigation framework for diagnosing Google Ads performance issues. Auto-invoke when user says "investigate," "why is [account] performing poorly," "dig into," or asks to diagnose a performance issue.

investigation-methodology/SKILL.md

Read pinned source

Source commit 90f0e419f2d820789d5e50eee1237ab9fd14dfc6

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 11, 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)
80
Repository last updated
Aug 25, 2026
License
MIT

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

Files and excerpt

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

Browse files
Read excerpt

# Investigation Methodology

Structured framework for diagnosing Google Ads performance issues. Follow this process for every investigation — no exceptions.

## What This Skill Deliberately Does NOT Do

- **Replace domain judgment.** Step 4's recommendation must be specific, but the domain rules that make it safe live in their own skills — a budget fix still goes through [`budget-recommendation-calculator`](../budget-recommendation-calculator/)'s conservative caps; a live-account change still goes through [`mutation-safety`](../mutation-safety/)'s approval gate.
- **Pull data for you.** The framework sequences WHICH evidence to gather at each layer; it works with the API, exports, or screenshots — whatever access exists.
- **Format the client deliverable.** Findings presented to a client go through [`client-communication-standards`](../client-communication-standards/) (Background → Analysis → Conclusions); Step 4 here is the internal analytical output that feeds it.
- **Guarantee an answer.** Inconclusive is a valid verdict — the Rules require saying so over inventing a cause.

## Step 1: Define the Problem Statement

Start with the specific question. Do not generalize.
Back to top