By gomarble-ai
AI Ads OS — a senior paid-media team in your Claude Code terminal. Meta strategists, Google Ads specialists, creative-fatigue analysts, GA4 attribution experts, Shopify ops leads. 36 expert-authored AI marketing playbooks across Google Ads, Meta (Facebook/Instagram), TikTok, LinkedIn, Bing, GA4, Shopify, Klaviyo & Search Console + 8 morning-workflow slash commands. OAuth-secured live data via the GoMarble MCP server.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Google Ads impression-share analysis to identify missed scaling opportunities and diagnose delivery constraints. Distinguishes Lost-IS (Budget) — addressable with money — from Lost-IS (Rank) — addressable with bids/quality. Disciplined: only recommends scaling on campaigns that are already profitable (≥30 conversions in 30d AND CPA at/below target). Read-only — recommends budgets, bids, holds; never executes. Use weekly or when planning where to deploy more spend.
PMax morning anomaly check — compares last 3 days vs prior 3 days across spend, conversions, and CPA/ROAS for every Performance Max campaign. Flags CPA spikes (> 25%), conversion drops (> 25%), and spend spikes without conversions. Read-only — no changes applied. Disciplined: does NOT recommend major changes unless the issue is severe, since PMax is a black box and overcorrection is the #1 killer.
Daily Google Ads Search morning briefing — compares last 3 days vs prior 3 days, segments brand vs non-brand (with different expectations for each), and surfaces specific recommendations across budget, impression share, bid adjustments, search-term waste, and query opportunities. Read-only — produces a CUT / FIX / SCALE recommendations list, never executes mutations. Use as your morning Google Search standup.
Forensic Google Ads Search-term waste audit. Pareto-filters down to the 80% of spend that matters (campaign-level, then search-term-level), then flags wasteful terms using campaign-relative triggers: low engagement (CTR ≥40% below campaign avg) and low conversion (CVR ≥40% below campaign avg, including zeros). Surfaces a "Red List" with suggested negative-keyword exclusions and identifies common "waste words" for root-level negatives. Read-only — proposes exclusions, never executes them. Use weekly for waste cleanup.
30-day comprehensive Meta Ads health audit. Checks pixel/CAPI integrity, scans creative fatigue across the account, profiles audience-segment spend split, surfaces ROAS/CPA outliers (top + bottom decile), evaluates budget allocation efficiency, and produces a professional written report. Read-only — no changes applied. Use for quarterly reviews, new-account onboarding, or any "what's actually happening in this account" deep dive.
Use when researching competitor ad creatives: find competitors, brand IDs, evergreen winners, breakout winners, pattern analysis.
Use when generating Word documents (.docx). Uses the marble_docx API.
Use when generating PDF documents. Uses the marble_pdf API.
Use when generating PowerPoint presentations (.pptx). Uses the marble_pptx API.
Use when generating Excel workbooks (.xlsx). Pandas + openpyxl patterns for multiple sheets, number formats, freeze panes, formulas.
External network access
Connects to servers outside your machine
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
A complete AI ads team in your terminal.
Built by GoMarble.
A complete AI ads team at your fingertips. Meta strategists, Google Ads specialists, creative-fatigue analysts, GA4 attribution experts, Shopify ops leads — each a specialized agent with battle-tested processes, not a generic chatbot.
AI Ads OS is the AI ads agent for Claude Code & Codex CLI — it plugs your terminal into your ad accounts and turns it into a senior performance marketer across Google Ads, Meta, TikTok, LinkedIn, Bing, GA4, Shopify, Klaviyo & Search Console. Built by GoMarble, the team that runs paid media for some of the fastest-growing DTC brands.
In a Claude Code session, paste these three commands:
/plugin marketplace add https://github.com/gomarble-ai/ai-ads-os.git
/plugin install ai-ads-os@ai-ads-os
/reload-plugins
Using the full HTTPS URL (not the
owner/reposhorthand) avoids SSH-key errors on machines where git is configured to rewrite GitHub HTTPS URLs to SSH.
Then connect the MCP server:
/mcp
Pick gomarble, click Authenticate — the browser opens, you sign in to GoMarble, you're done.
codex plugin marketplace add https://github.com/gomarble-ai/ai-ads-os.git
Start Codex, open the Plugins panel, find AI Ads OS, and install. Then:
codex mcp login gomarble
Same OAuth flow, one-time.
npx ai-ads-os
This wraps the official commands above and works on macOS / Linux / Windows.
The skills auto-invoke based on what you ask — you don't have to remember anything. Some examples:
| Ask | What happens |
|---|---|
| "Audit my Meta account act_12345 for the last 30 days." | Loads performance + creative + depth-of-analysis skills, pulls 30d data, runs Pareto analysis, flags fatiguing creatives, surfaces ROAS outliers, produces a report. |
| "How did my Google Ads Search campaigns do this week?" | Loads search-analysis skill, classifies queries Q1–Q5, diagnoses CPC inflation or rank pressure, returns a decision matrix. |
| "Create a Meta ad set for this creative targeting US iOS users." | Loads create/master + adset skills, verifies parent campaign, detects pixel, builds the propose payload, asks you to confirm before posting. |
| "Pull a 7d Shopify sales report and compare to GA4 conversions." | Loads Shopify order-discipline + GA4 source-of-truth skills, queries both, reconciles the difference. |
| "Generate a PPTX summarizing all my paid-media performance." | Loads pptx skill + the relevant analytics skills, produces a deck. |
8 read-only morning-workflow commands. Each produces analysis + recommendations — never executes mutations. Mutations happen separately via Agent Mode if the user explicitly opts in. Click any command name to view its source.
📊 Meta (4)
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub gomarble-ai/ai-ads-os --plugin ai-ads-osAI Media Buyer — a senior media-buying agent for Claude Code. 36 expert-authored playbooks across Google Ads, Meta (Facebook/Instagram), TikTok, LinkedIn, Bing, GA4, Shopify, Klaviyo & Search Console + 8 morning-workflow slash commands. OAuth-secured live data via the GoMarble MCP server.
AI Ads Agent — a senior paid-media agent for Claude Code. 36 expert-authored playbooks across Google Ads, Meta (Facebook/Instagram), TikTok, LinkedIn, Bing, GA4, Shopify, Klaviyo & Search Console + 8 morning-workflow slash commands. OAuth-secured live data via the GoMarble MCP server.
AI Marketing Agency — a full-service AI marketing agency for Claude Code. 36 expert-authored playbooks across Google Ads, Meta (Facebook/Instagram), TikTok, LinkedIn, Bing, GA4, Shopify, Klaviyo & Search Console + 8 morning-workflow slash commands. OAuth-secured live data via the GoMarble MCP server.
Marketing Agent — AI marketing automation for Claude Code. 36 expert-authored playbooks across Google Ads, Meta (Facebook/Instagram), TikTok, LinkedIn, Bing, GA4, Shopify, Klaviyo & Search Console + 8 morning-workflow slash commands. OAuth-secured live data via the GoMarble MCP server.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.