Download for MacApple silicon, macOS 14+
Skill

product-analysis

@noibu Updated 2026-10-22

Analyze product and collection performance using Noibu data. Use when you want to know which products are underperforming, what your best-selling product type is, why a product isn't converting, how your collections are performing, which products get views but no sales, or where shoppers drop off in the product funnel.

Install

With your agent

Install OMGSkills skill "noibu/ai-plugin:src/skills/product-analysis" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.

Manual command

git clone https://github.com/Noibu/ai-plugin /tmp/ai-plugin && ln -s /tmp/ai-plugin/src/skills/product-analysis ~/.claude/skills/product-analysis

From README

Noibu Product & Collection Performance Analysis Surfaces which products and collections are winning or losing, and why — built from Noibu session and page data. Call metadata: on every noibu call this skill drives, pass skill: "product-analysis" and a short skillStep (see the querying-noibu-data skill). How it works Quick answer (one focused question) → run 1–2 queries, answer directly, offer to go deeper. Full analysis (broad request, bare invocation, or "yes" to the offer) → the workflow below. — before any query Work quietly. Resolving the domain, loading reference files, reading field names, and running queries all happen silently — no "let me…" commentary. The triage board widget is the first substantive output. Resolve the domain first. Use what the user gave (name or UUID). If nothing, ask via AskUserQuestion populated from their domains — don't ask about anything else. If exactly one domain, skip the question.