/non-commodity-content

name: non-commodity-content
description: Interview the user for specific client stories, anecdotes, refusals, and real numbers — then turn them into non-commodity SEO content Google actually wants to rank. Kills generic listicle output at the source.
version: "1.0.0"
author: Cogny AI
platforms: []
user-invocable: true
argument-hint: "<topic, URL, or commodity headline>"
allowed-tools:
  - WebFetch
  - WebSearch
  - AskUserQuestion
  - Bash
  - Read
  - Write

Non-Commodity Content

Google's Danny Sullivan (Search Liaison) has explicitly said Google prefers *non-commodity* content — articles grounded in specific experience, specific clients, specific numbers, and things only *you* could have written. This skill refuses to let you publish filler. It interviews you for the real material first, then drafts the brief around it.

**Commodity (the generic version competitors and AI churn out):**

• "Top 10 Things to Consider When Buying Running Shoes"
• "7 Tips for First-Time Homebuyers"
• "2024 Kitchen Trends You Need to See"

**Non-Commodity (what Google actually ranks):**

• "Why This Customer's Shoes Collapsed After 400 Miles: A Wear Pattern Analysis"
• "Why We Waived the Inspection (And Saved $15k): A Look Inside the Sewer Line"
• "Marble vs. Grape Juice: Why I Refused to Install Stone for a Family of Five"

Notice the pattern: a specific subject + a specific number or refusal + the promise of analysis, not a listicle.

Usage

`/non-commodity-content <topic, URL, or commodity headline>`

Examples:

• `/non-commodity-content best CRM for agencies`
• `/non-commodity-content https://mybrand.com/blog/seo-tips`
• `/non-commodity-content "10 tips for better email subject lines"`

Steps

1. Frame the commodity trap

If the input is a URL, WebFetch it and identify the commodity framing (the generic headline, the listicle structure, the interchangeable advice). If the input is a plain topic or commodity-style headline, restate it in that same pattern.

Tell the user, in 3–5 lines:

• The commodity version of this topic (the generic take competitors and AI are publishing)
• Why it will lose to larger sites publishing the same generic take (domain authority beats generic content)
• What we need from them to build the non-commodity version: a real story, number, refusal, or artifact from their actual work

**Do not proceed to drafting yet.** The whole point of the skill is that the content doesn't exist until the user supplies the raw material.

2. Interview the user

Use `AskUserQuestion` to gather the raw material. Ask ONE question at a time, wait for the answer, then decide whether to ask a follow-up or move on. Use these prompts — in order, and skip any that don't apply:

• **The story prompt** — "Think of the most recent customer or project you worked on in this area. What specifically happened? What did you do that the next vendor down the street wouldn't have done?"
• **The number prompt** — "Any concrete numbers from that case? ($ saved or lost, hours, %, miles, error rate — anything measurable that a reader could fact-check.)"
• **The refusal prompt** — "Is there a time you *refused* to do the obvious thing, or talked a client *out* of what they asked for? A refusal with a reason is often the strongest angle."
• **The surprise prompt** — "What's something that surprised you in this area in the last 6 months — data that contradicted your priors, a weird customer outcome, a pattern you didn't expect?"
• **The method prompt** — "Do you have a specific test, process, or tool you use that competitors don't? (e.g. the grape-juice-on-marble test, the 400-mile wear check.) What does it reveal that a generic inspection misses?"
• **The proof prompt** — "What evidence can we attach? (Screenshots, photos, invoices, pre/post data, a redacted client quote, a measurement you personally took.)"

**Stop as soon as you have ONE specific anchor** — a story with a number, OR a refusal with a reason, OR a method with a result. You do not need all six. Keep going only if the first answer was thin.

**If the user has no anecdote** for this topic, say so plainly and stop:

> You don't have a non-commodity angle on this yet. Three honest options: > (a) Pick a sub-topic where you *do* have a story. > (b) Do the work — run the test, interview the customer, pull the data — and come back. > (c) Publish the commodity version and accept it likely won't rank. > > I'm not going to invent a client, a number, or a quote.

Never fabricate a story, client name, quote, or statistic. If something is unclear, ask a follow-up rather than filling the gap.

3. Extract the four anchors

From the interview, name these four things explicitly before writing anything:

1. **The anchor** — the single concrete thing the article is built around (a specific client, a specific measurement, a specific artifact, a specific decision). 2. **The counter-intuitive claim** — the thing an outsider or generic article would get wrong. 3. **The proof** — why the reader should believe this happened (photo, number, transcript, invoice). 4. **The lesson** — the generalizable takeaway the reader can apply to their own situation.

Show these to the user as a 4-line summary and ask if anything is off before continuing.

4. Draft 3 non-commodity headline variants

Match the pattern from the Google examples:

• Open with a **specific noun phrase or contradiction** — not a number-of-tips.
• Include a **concrete number, name, or refusal** (400 Miles, $15k, Family of Five).
• Signal **analysis or investigation**, not a roundup — "A Wear Pattern Analysis", "A Look Inside", "Why I Refused".

Produce 3 variants, each pulling on a different lever:

• **Variant A (number-led)** — headline built around the measurement.
• **Variant B (refusal-led)** — headline built around what you *didn't* do, and why.
• **Variant C (surprise-led)** — headline built around the counter-intuitive finding.

Label each variant with its lever so the user can pick.