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 personalization-enginegit 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/personalization-engine)<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/personalization-engine"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/personalization-engine/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/personalization-engine"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/personalization-engine.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 | $0.00023 | $0.02991 |
| Opus 5 | $0.00012 | $0.01496 |
| Sonnet 5 | $0.00005 | $0.00598 |
| Haiku 4.5 | $0.00002 | $0.00299 |
Grade A, and why
personalization-engine 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 10d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personalization Engine
Overview
Personalized product recommendations increase average order value and session depth by surfacing the most relevant products for each customer. "Frequently Bought Together", "You Might Also Like", and personalized homepage sections are all forms of recommendation. Every major platform has apps that handle collaborative filtering and recommendation algorithms without custom code. Only build a custom recommendation engine if your catalog size, traffic volume, or recommendation logic exceeds what app-based solutions support.
When to Use This Skill
- When adding "Frequently Bought Together" or "You Might Also Like" carousels to product pages
- When implementing a personalized homepage for returning customers
- When building a recommendation API for a mobile app or headless storefront
- When cold-start recommendations (no history) are returning irrelevant products
- When A/B testing the impact of personalization on AOV and revenue per session
Core Instructions
Step 1: Determine platform and choose the right recommendation tool
| Platform | Recommended Tool | Why |
|---|---|---|
| Shopify | LimeSpot or Frequently Bought Together by Code Black Belt | LimeSpot provides personalized homepage, PDP, cart, and post-purchase recommendations powered by ML; Frequently Bought Together is purpose-built for the PDP |
| WooCommerce | YITH WooCommerce Frequently Bought Together or LimeSpot | YITH is the most popular; LimeSpot supports WooCommerce with ML-based recommendations |
| BigCommerce | LimeSpot or Boost AI Search & Discovery | Both provide personalized recommendations and are available on the BigCommerce App Marketplace |
| Custom / Headless | Build with co-purchase matrix + cosine similarity | Required for full control over algorithm, exclusion logic, and API response format |
Step 2: Platform-specific setup
Shopify
Option A: LimeSpot (recommended — full personalization suite)
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/browsing-history-recommendations-with-co/criteria.json 3.0 KB
- evals/browsing-history-recommendations-with-co/task.md 2.2 KB
- evals/co-purchase-matrix-and-fbt-recommendatio/criteria.json 3.0 KB
- evals/co-purchase-matrix-and-fbt-recommendatio/task.md 2.0 KB
- evals/unified-recommendation-api-with-redis-ca/criteria.json 2.7 KB
- evals/unified-recommendation-api-with-redis-ca/task.md 1.9 KB
- tile.json 240 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.
- 10d ago First seen · 270 lines · 23 tokens per session scan A f080a4b4a313
personalization-engine is a skill published in the GitHub repository finsilabs/awesome-ecommerce-skills (52 stars, last pushed 6mo ago), licensed MIT. It adds 23 tokens to every session and 2,991 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
algolia-mcp
Search Algolia indices via the Algolia MCP server, retrieve analytics (top searches, no-result rates, click positions, user counts), and get product recommendations (bought-together, related, trending). Triggers on search, indexing, analytics, Algolia, recommendations, MCP.
algolia-data-modeling
Algolia data modeling and indexing guidance. Use before or alongside indexing records or building Algolia search UI for net-new search, browse, autocomplete, ecommerce, personalization, Dynamic Re-Ranking, recommendations, or analytics-aware implementations. Makes record shape, objectID, display fields, facets…
algolia-search-implementation
Execution checklist for net-new Algolia search, browse, autocomplete, ecommerce search, recommendations, personalization, Dynamic Re-Ranking, or search UI builds. Use during a greenfield build to keep data contract, event taxonomy, index configuration, UI, and release QA visible as explicit checkpoints with completion…
digital-storefront-requirements
Use when gathering or evaluating requirements for a Salesforce Commerce Cloud digital storefront — including branding strategy, content management approach, personalization, mobile experience, and accessibility compliance. Trigger keywords: SFRA branding, PWA Kit storefront, composable storefront, storefront…
add-wish
Save any product to a universal wishlist. Converts any product URL into a one-click "save for later" link. Works with any retailer, any AI platform, zero setup.
hugging-face-paper-publisher
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.