Purple Cow Audit logo

Purple Cow Audit

Organization
Affitor
purple-cow-audit

Score product remarkability 1-10 to decide if it's worth promoting. Seth Godin's Purple Cow test. Triggers on: "is this product worth promoting", "should I promote", "product audit", "purple cow", "remarkable product", "is it remarkable", "rate this product", "product quality check", "worth my reputation", "product evaluation", "would I recommend without commission", "product remarkability score", "evaluate this affiliate product", "quality gate for promotion".

Overview

PublisherAffitor
Repositoryaffiliate-skills
Skill namepurple-cow-audit
Stars
705
Forks
209
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Affitor on GitHub. Read the source before you install it.

Installation

Install the Purple Cow Audit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Affitor/affiliate-skills/tree/main/skills/research/purple-cow-audit
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Affitor/affiliate-skills.git /tmp/affiliate-skills
mkdir -p .claude/skills
cp -r /tmp/affiliate-skills/skills/research/purple-cow-audit .claude/skills/purple-cow-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Purple Cow Audit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Purple Cow Audit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Purple Cow Audit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Purple Cow Audit

Quality gate for affiliate marketers: score a product's remarkability 1-10 before promoting it. Based on Seth Godin's Purple Cow — if the product isn't remarkable, no amount of marketing skill will make it convert sustainably. The key question: "Would I recommend this to a friend WITHOUT earning a commission?"

Stage

S1: Research — Evaluating a program's worthiness IS part of research and discovery. This is a quality gate before you invest time creating content, landing pages, and email sequences.

When to Use

  • User is considering promoting a specific product
  • User asks "is this product worth promoting?"
  • User wants to evaluate product quality before investing time
  • User says "purple cow", "remarkable", "audit", "evaluate", "quality check"
  • Before investing time in S2-S5 skills for a specific product
  • User has a list of programs from affiliate-program-search and needs to pick the best

Input Schema

yaml
product:                    # REQUIRED
  name: string              # Product name
  url: string               # Product website
  description: string       # OPTIONAL — what it does
  reward_value: string      # OPTIONAL — commission rate
  tags: string[]            # OPTIONAL — categories

comparison_products: string[] # OPTIONAL — competitors to compare against
                              # Default: auto-discovered

Chaining from S1 affiliate-program-search: If run, evaluate the recommended_program.

Workflow

Step 1: Research the Product

  1. web_search: "[product] review 2024 2025" — find recent reviews
  2. web_search: "[product] vs" OR "[product] alternative" — find competitors
  3. web_search: "[product] complaints" OR "[product] problems" — find issues
  4. Check product website for: pricing transparency, unique features, social proof

Step 2: Score Remarkability

Rate each dimension 1-10:

DimensionQuestionWeight
UniquenessDoes it do something no competitor does?20%
QualityIs it genuinely excellent at its core job?20%
StoryDoes using it make you feel/look different?15%
Word of mouthWould users tell friends unprompted?15%
DesignIs the experience delightful, not just functional?10%
Problem fitDoes it solve a real, painful problem?10%
TrustTransparent pricing, good support, real social proof?10%

Composite score = weighted average (1-10)

Step 3: Make Recommendation

Based on composite score:

  • 8-10: PROMOTE — This is a Purple Cow. Go all in.
  • 6-7: PROMOTE WITH ANGLE — Good product, needs strong positioning. Identify your unique angle.
  • 4-5: CAUTION — Mediocre product. Only promote if commission is exceptional AND you can add significant value through bonuses.
  • 1-3: SKIP — Not remarkable. Promoting this will damage your reputation. Find an alternative.

Step 4: Identify Remarkable Angles

For products scoring 6+, identify:

  1. The 1-2 features that ARE remarkable (Purple Cow elements)
  2. The angles that make it share-worthy
  3. The audience segment for whom this IS a Purple Cow (even if not for everyone)

Step 5: Self-Validation

  • Score is evidence-based (cited reviews, features, data)
  • Recommendation is honest (not inflated by high commission)
  • Remarkable angles are specific (not generic praise)
  • Comparison with competitors is fair
  • The "would I recommend without commission" test was honestly applied

Output Schema

yaml
output_schema_version: "1.0.0"
purple_cow_audit:
  product_name: string
  composite_score: number       # 1-10 weighted
  recommendation: string        # "promote" | "promote_with_angle" | "caution" | "skip"
  scores:
    uniqueness: number
    quality: number
    story: number
    word_of_mouth: number
    design: number
    problem_fit: number
    trust: number

  remarkable_angles: string[]   # What makes it a Purple Cow (for 6+)
  red_flags: string[]           # Concerns identified
  alternative_products: string[] # Better options if score < 6

remarkability_score: number     # Alias for composite_score (for chaining)

chain_metadata:
  skill_slug: "purple-cow-audit"
  stage: "research"
  timestamp: string
  suggested_next:
    - "affiliate-program-search"
    - "grand-slam-offer"
    - "viral-post-writer"
    - "monopoly-niche-finder"

Output Format

## Purple Cow Audit: [Product Name]

### The Question
Would I recommend [product] to a friend WITHOUT earning a commission?
**Answer:** [Yes/No/With caveats]

### Remarkability Scorecard

| Dimension | Score | Evidence |
|---|---|---|
| Uniqueness | X/10 | [specific evidence] |
| Quality | X/10 | [specific evidence] |
| Story | X/10 | [specific evidence] |
| Word of Mouth | X/10 | [specific evidence] |
| Design | X/10 | [specific evidence] |
| Problem Fit | X/10 | [specific evidence] |
| Trust | X/10 | [specific evidence] |
| **Composite** | **X/10** | |

### Recommendation: [PROMOTE / PROMOTE WITH ANGLE / CAUTION / SKIP]

[Reasoning — 2-3 sentences]

### Remarkable Angles (what to emphasize)
1. [Specific remarkable feature/aspect]
2. [Specific remarkable feature/aspect]

### Red Flags (what to be honest about)
1. [Concern]
2. [Concern]

### If Score < 6: Better Alternatives
- [Alternative 1] — [why it's more remarkable]
- [Alternative 2] — [why it's more remarkable]

Error Handling

  • No product provided: "Tell me the product name and I'll audit its remarkability. Or run affiliate-program-search first."
  • Product is too new/no reviews: Score based on available data, flag low confidence. "Limited data — revisit this audit in 3 months."
  • User disagrees with score: "The score is a starting framework. If you have personal experience that changes the picture, tell me and I'll adjust."
  • No alternatives found: Suggest running affiliate-program-search in the same category.

Examples

Example 1: "Is HeyGen worth promoting?" → Research reviews, features, competitors. Score across 7 dimensions. Result: 8/10 PROMOTE — remarkable for AI avatar quality, unique lip-sync tech, strong word of mouth.

Example 2: "Evaluate these 3 programs from my search results" → Score all 3 side-by-side. Compare composite scores. Recommend the Purple Cow.

Example 3: "Should I promote this random SaaS tool?" (generic tool, many competitors) → Research reveals: 5/10 CAUTION — competent but unremarkable. 4 competitors do the same thing. Suggest finding a more remarkable alternative or targeting a micro-audience where it IS remarkable.

Revenue & Action Plan

Expected Outcomes

  • Revenue potential: Choosing an 8+/10 product vs a 5/10 product means 3-5x higher conversion rates. At the same traffic, that's $300-1,500/month vs $100-300/month. Product selection is the highest-leverage decision in affiliate marketing
  • Benchmark: Products scoring 8+ convert at 3-5% CTR, while 4-5 products convert at 0.5-1%. The difference compounds over months
  • Key metric to track: EPC (Earnings Per Click) — after 30 days of promotion, compare your EPC against the program's network average. If yours is below average, the product may not resonate with YOUR audience

Do This Right Now (15 min)

  • If PROMOTE (8-10): Run grand-slam-offer immediately — design your irresistible offer around the remarkable angles identified. Then start creating content today
  • If PROMOTE WITH ANGLE (6-7): Run monopoly-niche-finder to find the specific audience segment where this IS remarkable. Don't promote to a general audience
  • If CAUTION/SKIP (1-5): Run affiliate-program-search to find a better product in the same niche. Don't waste months promoting a mediocre product

Track Your Results

After promoting for 30 days: check EPC. If below $0.50, re-audit the product — the market may not find it as remarkable as the audit suggested. Switch products early; sunk cost is the biggest affiliate mistake.

Next step — copy-paste this prompt: "Design an irresistible offer for [product] using these remarkable angles: [list from audit]" → runs grand-slam-offer

Flywheel Connections

Feeds Into

  • grand-slam-offer (S4) — remarkable angles become the offer's core messaging
  • viral-post-writer (S2) — remarkable elements are what makes content shareable
  • affiliate-blog-builder (S3) — audit insights inform honest review content
  • landing-page-creator (S4) — remarkable features highlighted on the page

Fed By

  • affiliate-program-search (S1) — products to evaluate
  • competitor-spy (S1) — competitive landscape for comparison

Feedback Loop

  • ab-test-generator (S6) reveals which remarkable angles resonate with audience → refine what "remarkable" means for your specific audience

References

  • shared/references/case-studies.md — Real affiliate success stories
  • shared/references/affiliate-glossary.md — Terminology
  • shared/references/flywheel-connections.md — Master connection map

Frequently asked questions

What does the Purple Cow Audit AI skill do?

Score product remarkability 1-10 to decide if it's worth promoting. Seth Godin's Purple Cow test. Triggers on: "is this product worth promoting", "should I promote", "product audit", "purple cow", "remarkable product", "is it remarkable", "rate this product", "product quality check", "worth my reputation", "product evaluation", "would I recommend without commission", "product remarkability score", "evaluate this affiliate product", "quality gate for promotion".

Why use Purple Cow Audit on TypingMind?

Because you install it once and use it with any model. Purple Cow Audit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Purple Cow Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Affitor/affiliate-skills/tree/main/skills/research/purple-cow-audit. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Purple Cow Audit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Purple Cow Audit?

As many as you like. As long as a model supports skills, you can use Purple Cow Audit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Purple Cow Audit AI skill free?

Yes. It is published on GitHub by Affitor under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇