BC ai-search-citations-to-revenue
Use for "which of our pages do ChatGPT, Perplexity or Gemini cite", "does our AI search visibility bring traffic, signups or sales", "is our Peec visibility worth anything", "which AI-cited pages or products make us money", "GEO funnel", "AI search to revenue", or when someone uploads Peec AI (or Profound, Otterly, Scrunch and similar) citation exports and wants them tied to results — even when they never say "funnel". Follows your cited URLs to AI-referred, organic, referral and direct sessions in GA4, Search Console clicks and impressions, the GA4 key events you choose, and the business outcome — orders, won deals or payments from Shopify, WooCommerce, HubSpot, Pipedrive, Salesforce, Stripe and similar — and names the stage where the chain breaks. Runs on Coupler.io; missing sources are offered and connected. For AI-referral traffic against organic with no citation data, use ai-traffic-vs-organic-search-report.
Use for "which of our pages do ChatGPT, Perplexity or Gemini cite", "does our AI search visibility bring traffic, signups or sales", "is our Peec visibility…
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 13313 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 13313 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Failures and branches. 7 branches
- 100Steps. 139 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (6 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 926: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 50 headings
- +3Step-by-step instructions: 139 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.