Purple Cow Audit

What it does

When your agent uses it

• : is this product worth promoting
• Should I promote
• Remarkable product
• Is it remarkable

Example prompts

• “s worth promoting. Seth Godin”
• “is this product worth promoting”
• “should I promote”
• “/purple-cow-audit”

Requirements

• Compatibility (from SKILL.md): Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Research the Product
2. 2Score Remarkability
3. 3Make Recommendation
4. 4Identify Remarkable Angles
5. 5Self-Validation

What it can do on your machine

Read from SKILL.md and the folder at commit e43bfae. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent

  From compatibility in the SKILL.md frontmatter.

Context cost

Purple Cow Audit loads about 2.5k tokens when it runs. Until then it costs about 121 tokens; SKILL.md has 889 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~121

When it runs · the whole SKILL.md, loaded when a task matches

~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Affitor/affiliate-skills at commit e43bfae, republished under its MIT licence (© Affitor). 889 words, ~2,463 tokens.

name

purple-cow-audit

description

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".

compatibility

Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent

license

MIT

version

1.0.0

tags

affiliate-marketing, research, niche-analysis, program-discovery, differentiation, positioning

metadata.author

affitor

metadata.version

1.0

metadata.stage

S1-Research

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

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"

## 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]

© Affitor, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/research/purple-cow-audit of Affitor/affiliate-skills.

Open the folder on GitHubat commit e43bfae