SKILLEMALL.ai
GitHub ↗ RU Sign in

BB ai-traffic-vs-organic-search-report

Shows how much traffic answer engines like ChatGPT, Perplexity, Gemini and Claude send your site, and how it compares to normal organic search, from live GA4 data in your Coupler.io workspace — sessions, engagement, key events and revenue from AI referrals against organic, and whether AI is growing or replacing search. Use for "how much traffic does my site get from ChatGPT", "are AI answer engines sending me visitors", "AI referral vs organic search traffic", "am I getting AEO traffic to my site", "how is answer engine optimization doing for us", "should I invest in GEO", "are my AI referrals converting" — even when the user says "ranking in AI answers" or "GEO check". Important: this measures traffic AI engines already send you, not whether you appear in their answers — citation data isn't in Coupler's GA4 or GSC connectors. GA4 only.

coupler-io/skills Agent Skills author: coupler-io 1 file body ≈ 3 975 tokens Open the sourcegithub.com↗ analyzed 7 d ago

Shows how much traffic answer engines like ChatGPT, Perplexity, Gemini and Claude send your site, and how it compares to normal organic search, from live GA4…

As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions

ProcedureGoogle AnalyticsData and analyticstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
93/100
safety, quality, tests
Safety 60%
100
Quality 40%
82
Run on models
none yet
Process rating
B
67/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
55
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • 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

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 67/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 55Failures and branches. 1 branches
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. No external tools needed
    • 100Steps. 27 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3975 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 12 top-level sections: this looks like several domains in one skill

    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 848: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 9 example trigger phrases
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 27 items

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.