Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add finsilabs/awesome-ecommerce-skills --skill attribution-modelinggit clone --depth 1 https://github.com/finsilabs/awesome-ecommerce-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/attribution-modeling)<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/attribution-modeling"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/attribution-modeling/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/attribution-modeling"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/attribution-modeling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.02602 |
| Opus 5 | $0.00013 | $0.01301 |
| Sonnet 5 | $0.00005 | $0.00520 |
| Haiku 4.5 | $0.00003 | $0.00260 |
Grade A, and why
attribution-modeling scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attribution Modeling
Overview
Attribution modeling determines which marketing touchpoints receive credit for a conversion, enabling informed decisions about where to allocate ad spend. Every ad platform (Meta, Google, TikTok) reports attribution using its own model — typically claiming 100% credit — which means the sum of all platform-reported revenue routinely exceeds your actual revenue.
This skill guides you through setting up first-party attribution on your platform, comparing attribution models side by side, and using dedicated attribution tools that do this automatically without building custom pipelines.
When to Use This Skill
- When marketing channels (Google Ads, Meta, email) each claim different shares of the same revenue
- When needing to make budget allocation decisions across acquisition channels
- When moving beyond last-click attribution to understand the full customer journey
- When building a marketing analytics report that compares channel performance under multiple attribution models
- When implementing first-party attribution to replace data lost from iOS tracking changes
- When affiliate, influencer, and paid search all contributed to the same order and each claims 100% credit
Core Instructions
Step 1: Determine your platform and choose the right attribution tool
| Platform | Recommended Tool | Why |
|---|---|---|
| Shopify | Triple Whale or Northbeam | Both built specifically for Shopify DTC brands; pull order data via API, de-duplicate cross-platform attribution, and show first-party blended ROAS |
| Shopify (budget) | Shopify Analytics built-in attribution + UTM tracking | Free; shows last-click attribution by UTM source for all orders |
| WooCommerce | Metorik + GA4 attribution | Metorik adds UTM tracking to WooCommerce orders; GA4 provides data-driven attribution model |
| BigCommerce | Rockerbox or Northbeam | Both support BigCommerce via API integration; provide multi-touch attribution dashboards |
| All platforms (mid-market) | Rockerbox or Affluent | Platform-agnostic; pull ad spend from all channels and match to first-party order data |
| Custom / Headless | Build on Segment + dbt or use Triple Whale's pixel API | Capture touchpoints with Segment, store in warehouse, model attribution in dbt |
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/attribution-model-implementations/criteria.json 2.6 KB
- evals/attribution-model-implementations/task.md 4.3 KB
- evals/markov-chain-data-driven-attribution/criteria.json 2.7 KB
- evals/markov-chain-data-driven-attribution/task.md 4.9 KB
- evals/touchpoint-capture-and-conversion-path-l/criteria.json 3.0 KB
- evals/touchpoint-capture-and-conversion-path-l/task.md 1.5 KB
- tile.json 218 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 195 lines · 25 tokens per session scan A a71f5beee532
attribution-modeling is a skill published in the GitHub repository finsilabs/awesome-ecommerce-skills (52 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 2,602 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
content-angle-ranker
Rank content angles by engagement data, competition level, and platform fit. Data-driven angle selection instead of guesswork. Use this skill when the user has a keyword or product and needs to decide WHAT to create, which angle to take, which format to use, or which platform to target. Triggers on: "what angle should…
Katalon Studio Testing
Comprehensive testing patterns for Katalon Studio including codeless record-and-playback, Groovy scripted testing, custom keywords, data-driven testing, cross-browser execution, and CI/CD integration with Katalon TestOps.
ab-test-generator
Reads page analytics and click data from Humblytics, generates A/B test hypotheses with element selectors, and launches no-code split tests via the Humblytics MCP. Use when creating A/B tests, split tests, multivariate tests, or when you need to test headlines, CTAs, layouts, or pricing. Triggers: A/B test, split…
cro-optimizer
CRO specialist that pulls live analytics data via the Humblytics MCP, analyzes conversion funnels, identifies drop-off points, and generates prioritized A/B test hypotheses. Use when analyzing conversion rates, diagnosing funnel leaks, optimizing signup flows, or creating test roadmaps. Triggers: CRO, conversion rate…
cloudwatch_logs
Query and search AWS CloudWatch Logs and run Logs Insights queries.
email-sequences
Email sequence specialist that designs multi-email drip campaigns — onboarding, lead nurture, re-engagement, abandoned cart — with timing, branching logic, subject lines, and full copy. Applies Kennedy and Hormozi frameworks. Use when writing drip sequences, onboarding flows, nurture campaigns, re-engagement emails…