change-history-checker
Skill72 starsChanged 4 months agoMITView on GitHub
Query Google Ads account change history up to 90 days back using the `change_status` resource (vs the 30-day limit of `change_event`). Auto-invoke when user says "what changed in [account]", "change history for [account]", "what did I do in [month]", "audit account changes", or "review optimization history".
- Installs packages
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Vibha-Ramprakash/automate-google-adsword for word, first seen Sep 14, 2026
Other versions1 project uses a version of this.
Word for word · 1
- Vibha-Ramprakash/automate-google-ads★ 0100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository41 other files it gives its agents.
- account-diagnosticSkill
- ad-copy-generation-frameworkSkill
- ad-copy-verification-standardSkill
- add-account-negative-keywordsSkill
- ads-checkerSkill
- budget-guardianSkill
- budget-recommendation-calculatorSkill
- client-communication-standardsSkill
- competitor-analysis-v2Skill
- conversion-tracking-healthSkill
- dgen-automation-disableSkill
- fair-housing-complianceSkill
- ga4-campaign-cross-referenceSkill
- ga4-cross-analysisSkill
- ga4-lead-quality-investigationSkill
- gaql-query-patternsSkill
- geo-conflict-analyzerSkill
- google-ads-api-setupSkill
- google-ads-querySkill
- google-ads-samplesSkill
- impression-share-diagnosticsSkill
- investigation-methodologySkill
- lead-quality-pattern-analysisSkill
- lead-quality-recommendation-prioritizationSkill
- markdown-to-sheets-presenterSkill
- mcc-hack-auditSkill
- mutation-safetySkill
- neg-conflict-finderSkill
- non-serving-keyword-scannerSkill
- pmax-asset-automationSkill
- pmax-builderSkill
- portfolio-health-prioritizationSkill
- portfolio-pacing-rulesSkill
- rsa-bulk-editSkill
- rsa-refreshSkill
- rsa-single-accountSkill
- shared-budget-updaterSkill
- sqr-classifierSkill
- sqr-pipelineSkill
- underspending-investigationSkill
- youtube-placement-auditSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 66
Run with no arguments (or with a CID but missing --start/--end) and it prints usage help instead of a traceback
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Change History Checker
Owns one workflow: answer "what changed in this account?" from the API —
grouped what-changed-when counts up to 90 days back (the API's hard cap for
change_status), with an explicit escalation ladder for the questions the
counts can't answer (who did it, what the old values were, anything older).
The judgment layer — routine vs investigate, the attribution ladder, flag
decisions — is rules.md. The two-resource window semantics,
API-enforced query rules, and standalone patterns are
references/history-windows.md.
Prerequisites
google-ads.yamlat project root — see the google-ads-api-setup skill for creating it. The script loads it by that literal filename from the directory you run in (no--configflag), and--list-accountsadditionally needslogin_customer_idset in it.- Python with the
google-adspackage (pip install google-ads pyyaml)
When to Use
Auto-invoke when:
- User asks "what changes were made to [account]"
- User asks "what did I do in [month]"
- User wants to see optimization history
- User needs to audit account changes
- Reviewing past work on accounts
Deliberately does NOT do
- No actor attribution — the script queries
change_status, which carries no user email. "Who did this?" is the attribution ladder inrules.md(change_eventinside 30 days, the web UI beyond). - No old/new values — counts and types only. Value-level forensics is
change_event(≤ 30 days) or the UI export. - No history past 90 days — the API rejects older start dates. The web UI's Change History goes back 2 years and exports CSV; route there.
- No mutations — read-only, always.
- Nothing written to disk — console output is the whole artifact (status-leg note below).
- No scheduling or watchdog mode — one manual run per invocation.
Two resources, one script
Google Ads has TWO change-history resources: change_event (30 days, full
detail including who) and change_status (90 days, counts only). The
shipped script queries change_status — wider window, thinner payload.
The full table, the API's enforced query rules (finite range + LIMIT
required), and copy-ready patterns for both resources live in
references/history-windows.md.
Shipped Script
scripts/check_change_history.py (the README install block fetches it)
groups results by date and resource type with change counts and statuses:
--types— filter to specific resource types (when to narrow:rules.md)--detailed/-d— show asset details (sitelink text, callout text, snippet headers) for extension changes; scope nuances inrules.md--list-accounts— list ENABLED client accounts under your MCC (useslogin_customer_idfromgoogle-ads.yaml)- Run with no arguments (or with a CID but missing
--start/--end) and it prints usage help instead of a traceback
Usage
# A month, bounded with the day after (date bounds read as midnight — reference)
python scripts/check_change_history.py 1234567890 --start 2026-06-01 --end 2026-07-01
# Extension changes only
python scripts/check_change_history.py 1234567890 --start 2026-06-01 --end 2026-07-01 --types ASSET CUSTOMER_ASSET
# With asset text (sitelinks, callouts, snippets)
python scripts/check_change_history.py 1234567890 --start 2026-06-01 --end 2026-07-01 --detailed
# Find a CID by account name first
python scripts/check_change_history.py --list-accountsThe CID is passed through as-is — 10 digits, no dashes (the script does not strip them; a dashed CID fails at the API).
After a Run (status leg)
Nothing lands on disk — the console output IS the run record, so paste the
relevant groups into whatever you're working in before they scroll away.
The durable record is the account's change history itself: a re-run
reproduces any read inside the 90-day window, shifted by whatever changed
since. Findings route onward per the table below; triage every surprise
against the false-alarm table in rules.md first.
Files in this skill
| File | Role |
SKILL.md | This file — workflow + routing |
rules.md | Judgment: routine-vs-investigate, attribution ladder, flag decisions, false alarms |
examples.md | Three worked reads (routine month, the Saturday cluster, the 90-day wall) |
references/history-windows.md | Window semantics, API-enforced query rules, resource/status tables, standalone patterns |
scripts/check_change_history.py | The change_status query + grouping engine |
Runtime artifacts: none — console only (your google-ads.yaml stays outside
the skill).
When to load sibling skills
| Load | When |
mcc-hack-audit | Changes attribute to an actor you can't identify, or access itself is the question — that's the "who has access" map; this skill is the "what changed" log |
google-ads-query | The question is performance ("how did it do"), not history ("what changed") |
account-diagnostic | "What changed?" was really "why did it break?" — run the inspection instead of archaeology |
google-ads-api-setup | First run, or any credentials error |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

