Agent skill

Google Ads Pmax

by TheMattBerman in TheMattBerman/google-ads-copilot

Analyze Performance Max through the lens of intent contamination, cannibalization, weak control surfaces, and what can still be learned despite PMax opacity.

MITAuto-check passedMarketing & SEO

Install Google Ads Pmax

skills CLI

$ npx skills add TheMattBerman/google-ads-copilot --skill google-ads-pmax -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install TheMattBerman/google-ads-copilot google-ads-pmax --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/TheMattBerman/google-ads-copilot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/google-ads-pmax .claude/skills/google-ads-pmax && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "google-ads-pmax" agent skill from https://github.com/TheMattBerman/google-ads-copilot/tree/main/skills/google-ads-pmax into .claude/skills/google-ads-pmax/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "google-ads-pmax", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/TheMattBerman/google-ads-copilot/tree/main/skills/google-ads-pmax

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add TheMattBerman/google-ads-copilot --skill google-ads-pmax -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install TheMattBerman/google-ads-copilot google-ads-pmax --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/TheMattBerman/google-ads-copilot.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/google-ads-pmax .agents/skills/google-ads-pmax && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "google-ads-pmax" agent skill from https://github.com/TheMattBerman/google-ads-copilot/tree/main/skills/google-ads-pmax into .agents/skills/google-ads-pmax/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "google-ads-pmax", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add TheMattBerman/google-ads-copilot --skill google-ads-pmax -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install TheMattBerman/google-ads-copilot google-ads-pmax --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/TheMattBerman/google-ads-copilot.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/google-ads-pmax .cursor/skills/google-ads-pmax && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "google-ads-pmax" agent skill from https://github.com/TheMattBerman/google-ads-copilot/tree/main/skills/google-ads-pmax into .cursor/skills/google-ads-pmax/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "google-ads-pmax", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/TheMattBerman/google-ads-copilot.git --path skills/google-ads-pmax

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add TheMattBerman/google-ads-copilot --skill google-ads-pmax -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install TheMattBerman/google-ads-copilot google-ads-pmax --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/TheMattBerman/google-ads-copilot.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/google-ads-pmax .gemini/skills/google-ads-pmax && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "google-ads-pmax" agent skill from https://github.com/TheMattBerman/google-ads-copilot/tree/main/skills/google-ads-pmax into .gemini/skills/google-ads-pmax/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "google-ads-pmax", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install TheMattBerman/google-ads-copilot google-ads-pmax

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add TheMattBerman/google-ads-copilot --skill google-ads-pmax -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/TheMattBerman/google-ads-copilot.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/google-ads-pmax .github/skills/google-ads-pmax && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "google-ads-pmax" agent skill from https://github.com/TheMattBerman/google-ads-copilot/tree/main/skills/google-ads-pmax into .github/skills/google-ads-pmax/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "google-ads-pmax", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add TheMattBerman/google-ads-copilot --skill google-ads-pmax -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install TheMattBerman/google-ads-copilot google-ads-pmax --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/TheMattBerman/google-ads-copilot.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/google-ads-pmax .opencode/skills/google-ads-pmax && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "google-ads-pmax" agent skill from https://github.com/TheMattBerman/google-ads-copilot/tree/main/skills/google-ads-pmax into .opencode/skills/google-ads-pmax/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "google-ads-pmax", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: google-ads-pmax
GitHub stars: 238
Token cost: ~1.1k tokens
SKILL.md length: 378 words
Files: 1
Skills in repo: 16
Repo updated: Jun 10, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Analyze Performance Max through the lens of intent contamination, cannibalization, weak control surfaces, and what can still be learned despite PMax opacity.

Works in 8 steps: Announce mode (connected/export). → Pull PMax and Search campaign data. → Compare PMax vs. Search on shared… → …
Tasks that involve Paid advertising
SKILL.md covers Data Acquisition, Core Questions, Process and Draft Output, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Google Ads Pmax is an agent skill from TheMattBerman/google-ads-copilot. Analyze Performance Max through the lens of intent contamination, cannibalization, weak control surfaces, and what can still be learned despite PMax opacity. Pulls live data via MCP or works with manual exports.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO, covering Paid advertising. It works with Google Ads and Model Context Protocol. The repository describes itself as: Google Ads Copilot: operator kit for audits, MCP-connected reads, export-mode analysis, and draft/apply workflows. The licence is MIT.

When your agent uses it

Tasks that involve Paid advertising

Example prompts

“/google-ads-pmax”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

Announce mode (connected/export).
Pull PMax and Search campaign data.
Compare PMax vs. Search on shared conversion actions.
Look for branded cannibalization signals.
Assess asset group quality.
Attempt PMax query visibility recovery using Steps 5/5b from the shared retrieval ladder (data/search-term-retrieval.md).
Separate direct evidence from inference. Query rows from PMax are useful, but they do not automatically carry the same term-level cost /…
Identify what should be protected in dedicated Search campaigns.

What it can do on your machine

Read from SKILL.md and the folder at commit 2c253ee. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are sql).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Google Ads Pmax loads about 1.1k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 378 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~57
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from TheMattBerman/google-ads-copilot at commit 2c253ee, republished under its MIT licence (© TheMattBerman). 378 words, ~1,103 tokens.

Download SKILL.mdSave it as .claude/skills/google-ads-pmax/SKILL.md (or your agent's skills folder).

name: google-ads-pmax
description: Analyze Performance Max through the lens of intent contamination, cannibalization, weak control surfaces, and what can still be learned despite PMax opacity. Pulls live data via MCP or works with manual exports.

Google Ads PMax

Read first:

google-ads/references/operator-thesis.md
google-ads/references/intent-map.md
google-ads/references/query-patterns.md
google-ads/references/structure-playbook.md
google-ads/references/benchmarks.md
google-ads/references/deliverable-templates.md

Read workspace if available:

workspace/ads/account.md
workspace/ads/goals.md
workspace/ads/intent-map.md
workspace/ads/findings.md
workspace/ads/change-log.md
workspace/ads/learnings.md

Data Acquisition

Connected Mode (MCP available)

Pull via the search tool on google-ads-mcp:

Primary: PMax campaign performance:

sql

SELECT
  campaign.name,
  campaign.status,
  metrics.impressions,
  metrics.clicks,
  metrics.cost_micros,
  metrics.conversions,
  metrics.conversions_value,
  metrics.cost_per_conversion
FROM campaign
WHERE campaign.advertising_channel_type = 'PERFORMANCE_MAX'
  AND campaign.status = 'ENABLED'
  AND segments.date DURING LAST_30_DAYS

Primary: Asset group performance:

sql

SELECT
  campaign.name,
  asset_group.name,
  asset_group.status,
  metrics.impressions,
  metrics.clicks,
  metrics.cost_micros,
  metrics.conversions
FROM asset_group
WHERE campaign.advertising_channel_type = 'PERFORMANCE_MAX'
  AND segments.date DURING LAST_30_DAYS

Supplementary: Compare with Search campaign performance (cannibalization check):

sql

SELECT
  campaign.name,
  campaign.advertising_channel_type,
  metrics.impressions,
  metrics.clicks,
  metrics.cost_micros,
  metrics.conversions,
  metrics.cost_per_conversion
FROM campaign
WHERE campaign.status = 'ENABLED'
  AND segments.date DURING LAST_30_DAYS
ORDER BY metrics.cost_micros DESC

See data/gaql-recipes.md for additional queries.

Export Mode (no MCP)

Ask the user for:

PMax campaign metrics
Asset group list with performance
Search campaign performance (for comparison)
Any listing group or audience signal notes

Core Questions

Is PMax cannibalizing branded or clean high-intent traffic?
Is it helping discover net-new signal, or just absorbing existing demand?
What can we infer about intent quality despite limited visibility?
What should be protected outside PMax?
What should be fixed in feeds, exclusions, or surrounding structure?

Process

Announce mode (connected/export).
Pull PMax and Search campaign data.
Compare PMax vs. Search on shared conversion actions.
Look for branded cannibalization signals.
Assess asset group quality.
Attempt PMax query visibility recovery using Steps 5/5b from the shared retrieval ladder (data/search-term-retrieval.md).
Separate direct evidence from inference. Query rows from PMax are useful, but they do not automatically carry the same term-level cost / CPA detail as classic Search reports.
Identify what should be protected in dedicated Search campaigns.

Show full SKILL.md (163 more words)Show less

Draft Output

PMax analysis typically does not produce its own draft type — its findings feed into:

Structure drafts (if PMax is cannibalizing, recommend brand exclusions or campaign restructure)
Negative drafts (if account-level negatives can help contain PMax)
Budget drafts (if PMax is absorbing budget that should go to proven Search campaigns)

When PMax-specific actions are needed, use the structure draft template and note the PMax context.

Always update workspace memory:

workspace/ads/findings.md — PMax observations (inference vs. direct evidence)
workspace/ads/learnings.md — what we learned about PMax behavior in this account

Output Format

Use operator summary, then add:

Cannibalization risks (with evidence level)
Useful signal PMax may still be surfacing
What should be protected in Search or other buckets
What is direct evidence vs inference

Rules

Treat PMax as useful but not self-explanatory.
Look for contamination before celebrating efficiency.
Protect clean branded and high-intent buckets when needed.
Be explicit about what is inference versus direct evidence.
If visibility is weak, say that clearly instead of pretending certainty.

Files

Just SKILL.md in skills/google-ads-pmax of TheMattBerman/google-ads-copilot.

Open the folder on GitHubat commit 2c253ee

Compare with similar skills

Google Ads Pmax next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Google Ads Pmax compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Google Ads Pmax this skillTheMattBerman/google-ads-copilot	238	—	~1.1k	Automated safety check: Pass	MIT	4 mo ago
Google Ads Landing Page Auditnowork-studio/notfair-plugin	3.9k	—	~306	Automated safety check: Pass	MIT	today
Google Ads API MCP Setupgoogle/skills	21k	—	~6.1k	Automated safety check: Notes	Apache-2.0	today
21 Audit Ads Performanceminhnv0807/ai-business-skills	610	—	~4.6k	Automated safety check: Pass	MIT	27 days ago
Connectindranilbanerjee/digital-marketing-pro	859	1 repos	~2k	Automated safety check: Pass	MIT	5 days ago
Launch Ad Campaignindranilbanerjee/digital-marketing-pro	859	1 repos	~3.9k	Automated safety check: Pass	MIT	5 days ago

Similar skills

Google Ads Landing Page Audit
nowork-studio/notfair-plugin
Scores Google Ads landing pages on five weighted dimensions and diagnoses why high-CTR ad groups convert poorly, with concrete fixes for each page.
3.9k GitHub stars~306 tokensUpdated today
Marketing & SEOAuto-check passed
Google Ads API MCP Setup
google/skills
Official
Guides developers through downloading, configuring, and installing the official open-source Google Ads MCP Server.
21k GitHub stars~6.1k tokensUpdated today
Marketing & SEOAuto-check: notes
21 Audit Ads Performance
minhnv0807/ai-business-skills
Dung khi can ra soat CAU HINH tai khoan quang cao mot cach he thong — 6 khau tu account, campaign, adset, creative, landing den tracking, cham Health Score 0-100 va liet ke Quick Wins.
610 GitHub stars~4.6k tokensUpdated 27 days ago
Marketing & SEOAuto-check passed
Connect
indranilbanerjee/digital-marketing-pro
Guide the connection of a known MCP integration to the plugin — looks up the connector registry via connector-status.py, checks current status, and returns transport-specific setup steps (OAuth for…
859 GitHub starsUsed in 1 repo~2k tokens
Marketing & SEOAuto-check passed
Launch Ad Campaign
indranilbanerjee/digital-marketing-pro
Create and launch a paid ad campaign on Google, Meta, LinkedIn, or TikTok through the connected ad-platform MCP — campaign structure, audience targeting, bid strategy, negative targeting, creative…
859 GitHub starsUsed in 1 repo~3.9k tokens
Marketing & SEOAuto-check passed
Blog Google
AgriciDaniel/claude-blog
Google API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity…
2.3k GitHub starsUsed in 1 repo~3.3k tokens
Marketing & SEOAuto-check: notes

More from TheMattBerman/google-ads-copilot

All 16 skills in this repo

Google Ads
TheMattBerman/google-ads-copilot
Google Ads operator system for search-term analysis, intent mapping, wasted spend control, account structure decisions, tracking diagnostics, RSA generation, budget review, account planning, and…
238 GitHub stars~4.1k tokensUpdated 4 mo ago
Auto-check passed
Google Ads Apply
TheMattBerman/google-ads-copilot
Execute approved draft actions in Google Ads accounts. An agent skill from TheMattBerman/google-ads-copilot.
238 GitHub stars~2.7k tokensUpdated 4 mo ago
Auto-check passed
Google Ads Audit
TheMattBerman/google-ads-copilot
Full Google Ads review that synthesizes tracking, search terms, intent mapping, negatives, structure, RSAs, budget decisions, and PMax context into a single operator read.
238 GitHub stars~2.7k tokensUpdated 4 mo ago
Auto-check passed
Google Ads Budget
TheMattBerman/google-ads-copilot
Review Google Ads budget allocation and scaling decisions based on signal quality, intent clarity, tracking confidence, and structural health.
238 GitHub stars~1.2k tokensUpdated 4 mo ago
Auto-check passed
Google Ads Connect
TheMattBerman/google-ads-copilot
Connected-mode onboarding, health check, and customer selection for Google Ads Copilot.
238 GitHub stars~2.2k tokensUpdated 4 mo ago
Auto-check passed
Google Ads Daily
TheMattBerman/google-ads-copilot
Daily operator review for Google Ads. An agent skill from TheMattBerman/google-ads-copilot.
238 GitHub stars~1.2k tokensUpdated 4 mo ago
Auto-check passed

Works with

Questions about Google Ads Pmax

What does Google Ads Pmax do?

Analyze Performance Max through the lens of intent contamination, cannibalization, weak control surfaces, and what can still be learned despite PMax opacity. Google Ads Pmax is an agent skill from TheMattBerman/google-ads-copilot. Analyze Performance Max through the lens of intent contamination, cannibalization, weak control surfaces, and what can still be learned despite PMax opacity.

When should I use Google Ads Pmax?

Google Ads Pmax fits situations like: tasks that involve Paid advertising.

How do I install Google Ads Pmax in Claude Code?

Run `npx skills add TheMattBerman/google-ads-copilot --skill google-ads-pmax -a claude-code`. Or copy the skill folder (skills/google-ads-pmax in TheMattBerman/google-ads-copilot) into .claude/skills/google-ads-pmax in your project. Claude Code loads it when a task matches its description.

How do I install Google Ads Pmax in Codex?

Run `npx skills add TheMattBerman/google-ads-copilot --skill google-ads-pmax -a codex`. Or copy the skill folder (skills/google-ads-pmax in TheMattBerman/google-ads-copilot) into .agents/skills/google-ads-pmax in your project. Codex loads it when a task matches its description.

Can I use Google Ads Pmax in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TheMattBerman/google-ads-copilot --skill google-ads-pmax -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/google-ads-pmax, .gemini/skills/google-ads-pmax, .github/skills/google-ads-pmax and .opencode/skills/google-ads-pmax in your project.

What does Google Ads Pmax need to run?

SKILL.md names no scripts, command-line tools or credentials: Google Ads Pmax is instructions for the agent only.

Does Google Ads Pmax access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Google Ads Pmax safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Google Ads Pmax use?

Google Ads Pmax is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Google Ads Pmax use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Google Ads Pmax?

Skills that share tags, products or a category with Google Ads Pmax: Google Ads Landing Page Audit (nowork-studio/notfair-plugin, 3.9k stars), Google Ads API MCP Setup (google/skills, 21k stars), 21 Audit Ads Performance (minhnv0807/ai-business-skills, 610 stars) and Connect (indranilbanerjee/digital-marketing-pro, 859 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Google Ads Pmax?

TheMattBerman (a GitHub user) maintains it in TheMattBerman/google-ads-copilot, which has 238 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on June 10, 2026.

Source: TheMattBerman/google-ads-copilot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Google Ads Pmax

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Google Ads PMax

Data Acquisition

Connected Mode (MCP available)

Export Mode (no MCP)

Core Questions

Process

Draft Output

Always update workspace memory:

Output Format

Rules

Files

Compare with similar skills

Similar skills

More from TheMattBerman/google-ads-copilot

Related

Questions about Google Ads Pmax