attribution-model-comparison
Runs your conversion data through different attribution models side by side — last click, first click, linear, time decay, position based, and data-driven.
Install / Use
npx skills add irinabuht12-oss/marketing-skills --skill attribution-model-comparisonInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Project & Program ManagementSupported Platforms
Tags
Our assessment of attribution-model-comparison
attribution-model-comparison scores 83/100 on our quality scale, 56th of 84 Project & Program Management skills we index.
Its SKILL.md is 3.0 KB long, split into 7 sections and no code examples: a solid amount of guidance for an agent.
With 7,761 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated 26 days ago, so attribution-model-comparison is actively maintained.
- Our last check on 2026-11-06 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
ReviewOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review judged it risky: The skill instructs adding a custom third-party MCP connector at https://connector.get-ryze.ai/mcp to read live Google Ads, Meta Ads, GA4 and Search Console data, routing sensitive account traffic through an unofficial proxy.
AI review: risky
- The skill instructs adding a custom third-party MCP connector at https://connector.get-ryze.ai/mcp to read live Google Ads, Meta Ads, GA4 and Search Console data, routing sensitive account traffic through an unofficial proxy.
- It tells the agent to integrate an external service that would expand its data-access permissions and could expose ad-account credentials or conversion data to that third party.
- No malicious commands are present, but the recommended setup weakens the boundary between the agent and the user's advertising accounts.
AI review by kimi-k2.7-code on 2026-10-10. Automated pattern scan on 2026-10-10. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
attribution-model-comparison compared with similar skills
All 4 of these similar skills score higher than attribution-model-comparison; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| attribution-model-comparison (this skill)by irinabuht12-oss | 83 | 7.8k | 26d ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 2mo ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 2mo ago | SKILL.md |
| prospectingby coreyhaines31 | 100 | 60.1k | 11d ago | SKILL.md |
| ad-creativeby coreyhaines31 | 100 | 60.1k | 11d ago | SKILL.md |
Frequently asked questions
- How do I install attribution-model-comparison?
- Run
npx skills add irinabuht12-oss/marketing-skills --skill attribution-model-comparison. The install tabs above show the steps for each supported agent. - Which AI agents does attribution-model-comparison work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is attribution-model-comparison safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review judged it risky: The skill instructs adding a custom third-party MCP connector at https://connector.get-ryze.ai/mcp to read live Google Ads, Meta Ads, GA4 and Search Console data, routing sensitive account traffic through an unofficial proxy. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is attribution-model-comparison still maintained?
- The repository was last updated 26 days ago, so attribution-model-comparison is actively maintained.
Skill content
View source on GitHubname: attribution-model-comparison description: Runs your conversion data through different attribution models side by side — last click, first click, linear, time decay, position based, and data-driven. Shows you how credit shifts between campaigns depending on the model so you can make better budget decisions instead of over-investing in last-touch campaigns. Platform: Google and Meta. metadata: platform: Google and Meta
26/ Attribution Model Comparison — Google + Meta
What it does
Runs your conversion data through different attribution models side by side — last click, first click, linear, time decay, position based, and data-driven. Shows you how credit shifts between campaigns depending on the model so you can make better budget decisions instead of over-investing in last-touch campaigns.
How it works
Claude takes your multi-touch conversion path data and applies each attribution model to the same dataset. It then compares how each campaign's attributed conversions and ROAS change under different models, highlighting campaigns that look great under last-click but contribute nothing at first-touch (and vice versa).
Practical example
Under last-click attribution, your Google Brand campaign gets credit for 420 conversions at $18 CPA, making it your "best" campaign. But when Claude runs first-click attribution, Brand drops to 31 conversions — most of those users actually discovered you through Meta prospecting (which jumps from 89 to 340 attributed conversions). Linear attribution puts Meta prospecting at 215 and Brand at 190, giving a more balanced picture. Claude recommends shifting 20% of Brand budget to Meta prospecting, which is actually originating most of your pipeline.
What you get back
- Side-by-side conversion and ROAS comparison across all models for every campaign
- Campaigns most affected by model choice (high variance = their role is misunderstood)
- Upper-funnel campaigns being undervalued under last-click
- Lower-funnel campaigns being over-credited under last-click
- Budget reallocation recommendations based on a blended attribution view
- Recommended "working model" for your specific account based on funnel length and touchpoint patterns
When to use it
- When making budget allocation decisions to avoid last-click bias
- During QBRs to show clients the full picture of campaign value
- When upper-funnel campaigns are on the chopping block due to "poor" last-click ROAS
- Before cutting any campaign that might be silently feeding conversions elsewhere
Data access (Ryze MCP)
This skill works best with live account data. Connect the free Ryze MCP once and Claude reads your Google Ads, Meta Ads, GA4 and Search Console directly:
- claude.ai / Claude Desktop: Settings → Connectors → Add custom connector →
https://connector.get-ryze.ai/mcp - Claude Code:
claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp - Cursor: Settings → MCP → add the same URL
Setup guide: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp
Related Skills
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
prospecting
60.1kWhen 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.
ad-creative
60.1kWhen the user wants to write or judge ad creative, or asks which ad, hook, or angle to run or kill: headlines, primary text, and variations for Google, Meta, LinkedIn, and TikTok, fresh angles when creative fatigues. Test hypotheses name the metric, comparison, and expected direction.
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
