When the user wants to set up, audit, or fix conversion tracking to Google Ads, Meta, GA4, LinkedIn, and TikTok, or asks why conversions are missing or doubled: GTM, pixels, CAPI, Enhanced Conversions, offline imports. Fire on confirmed success, not the submit click; verify a test conversion arrives
attribution
An AI skill for Claude Code, Cursor, Codex and other AI agents, from coreyhaines31/marketingskills. Scored by fixed code checks, no AI.
CCode 67/100Builder 0/10
When the user wants to work out which marketing drives revenue, or asks whether a channel is really working, which numbers to trust, or how to credit podcasts and dark social: attribution models, platforms that over-claim, MMM, incrementality and holdout tests, self-reported attribution. For tracking and UTMs, see analytics. For pixels and CAPI, see conversion-tracking. For CRM revenue, see revops. For AI search blind spots, see ai-seo.
Install
npx skills add coreyhaines31/marketingskills --skill attribution
Where do I paste this?
Open a terminal in your project folder, paste the command and press Enter. It needs Node.js on your computer.
Run it in your project. The skills CLI asks which agents to install it for (Claude Code, Cursor, Codex and more); add -g to install it for your user instead.
No terminal? Copy SKILL.md and give it to your AI as instructions.
SKILL.md
A skill is instructions and scripts your agent will follow, so read it before you install it. Its text loads here from GitHub; you can also read it on GitHub.
More skills from coreyhaines31/marketingskills
When the user wants to find and qualify prospects for outbound, or asks who to target first, which signal to prioritize, or where to spot buyers with the problem: buying signals, enrichment, verification, account research. Verify emails before a sequence, never scrape LinkedIn: define audiences in S
When the user wants to write or rewrite page copy (homepage, landing, pricing, feature), or asks which headline, promise, or message to lead with. Diagnoses the input first (blank brief, real voice, or point edit) and changes only what it calls for. Claims must be supportable; a declined claim names
aso
BWhen the user wants to audit or optimize an App Store or Google Play listing, or asks which title, keywords, or screenshots to pick or why downloads are low: subtitle, description, ratings, and comparing listings with competitors.
When the user wants a full marketing or go-to-market plan for a client, an advised company, or their own product, or asks how to sequence or prioritize several initiatives with a fixed team and budget: channels, budget, team, goals across AARRR, market sizing. For positioning first, see product-mark
When the user wants to add, fix, or validate schema markup (JSON-LD), or asks which type fits a page or whether some markup is allowed: product, review, recipe, FAQ, rich result eligibility (FAQ no longer earns Google rich results), Search Console errors. For broader SEO, see seo-audit. For AI searc
ads
BWhen the user wants to plan, run, or fix paid ads on Google, Meta, and LinkedIn, or asks a judgement call on them: are ads worth it, which channel or budget split, why CPA rose, kill or keep a campaign. End with facts, hypotheses, and missing data; label unavailable inputs MISSING instead of estimat
When the user wants to create, generate, edit, or optimize marketing images, or asks which approach to take (generate, design, or photograph): blog heroes, social graphics, product mockups, banners, OG images. For ad images, see ad-creative. For video, see video.