Individual skill

google-ads-write-safety

Use this skill when an AI agent or automation is about to make a write change to a live Google Ads account — pausing something, moving a bid, adding negatives, editing a budget, launching a campaign. Produces a change that's previewed, confirmed, and provably executed, instead of a plausible-sounding claim. Triggers: agent making Google Ads changes, autonomous bidding, automated negative keywords, AI campaign management, bulk account edits, "did that actually run."

skills/john-williams/google-ads-write-safety/SKILL.md

Read pinned source

Source commit 5d786aad0c7b2ca59b1abf1f601f9407ca261996

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Instructions only
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): 237
Repository last updated: Oct 20, 2026
License: MIT

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

revops Declared skill tag
marketing Derived category
finance Derived category
writing 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 · 4,013 bytes

Read excerpt


# Write Safety for AI Agents on Google Ads Accounts

Applies the moment an agent moves from reading an account to writing to it. The
account is real money and the advertiser's livelihood — a hallucinated success
message isn't a rough edge, it's a trust catastrophe the first time it happens.

## The play

1. Classify the request by blast radius before touching anything: read-only,
   low-risk (a single keyword, negative, or bid move within a tight band), or
   account-level (budget swings, conversion tracking, campaign creation or deletion).
2. Default to propose-only — pull data, calculate, recommend, but execute nothing
   without an explicit go-ahead. An authorization covers the specific action just
   approved, never the rest of the session.