Traffic Analysis logo

Traffic Analysis

Community
kostja94
traffic-analysis

When the user wants to analyze website traffic sources, attribution, or dark traffic. Also use when the user mentions "traffic sources," "dark traffic," "direct traffic," "UTM parameters," "traffic attribution," "channel attribution," "attribution optimization," "channel analysis," "traffic analysis," "traffic diversification," "natural traffic benchmark," or "organic vs paid traffic." For GA4 setup, use analytics-tracking.

Overview

Publisherkostja94
Repositorymarketing-skills
Skill nametraffic-analysis
Stars
979
Forks
137
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 kostja94 on GitHub. Read the source before you install it.

Installation

Install the Traffic Analysis 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.
  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/kostja94/marketing-skills.git /tmp/marketing-skills
mkdir -p .claude/skills
cp -r /tmp/marketing-skills/skills/analytics/sources/traffic .claude/skills/traffic-analysis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Traffic Analysis 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 Traffic Analysis 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 Traffic Analysis 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.

Analytics: Traffic

Guides website traffic analysis across all channels (organic, paid, social, referral, direct). Covers traffic source attribution, dark traffic identification, and multi-channel reporting.

When invoking: On first use, if helpful, open with 1-2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.

Scope

  • Traffic sources: Organic, paid, social, referral, direct, email
  • Dark traffic: Unattributed visits labeled as "Direct / None"
  • Attribution: UTM tagging, segmenting, reporting accuracy

Branded vs. Non-Branded Traffic (Organic)

TypeCharacteristics
BrandedHigher CTR, conversion, purchase intent; users closer to funnel bottom
Non-brandedTouchpoint with future users; most sites get more non-brand traffic; competition fiercer

Brand traffic grows over time as brand awareness increases.

Bot Traffic

A large share of traffic can be bot traffic—RPA, search crawlers, spiders, scrapers. Exclude or segment when evaluating real user behavior; use GA4 filters or segments to isolate human traffic.

Traffic Channels

ChannelTypical SourcesAttribution
OrganicGoogle, Bing, other searchReferrer preserved
Paid (web)Google Ads, Meta Ads, etc.UTM required
Paid (app)App install ads; Google App Campaigns, Apple Search AdsUTM; in-app events
Paid (TV/CTV)Streaming ads; Hulu, Roku, YouTube TVUTM for QR/URL; brand lift
SocialPublic posts (Facebook, LinkedIn, etc.)Often preserved
ReferralExternal sites, backlinksReferrer preserved
DirectTyped URL, bookmarksNo referrer
EmailNewsletters, campaignsOften dark without UTM

Dark Traffic

What It Is

Traffic without clear origin--analytics tools default to "Direct" when referrer is missing. Common causes:

  • Private/dark social: WhatsApp, Messenger, Slack, Discord, TikTok shares
  • Email clients: Many strip referrer headers
  • HTTPS->HTTP: Referrer not passed
  • Mobile apps: In-app browsers often omit referrer
  • Ad blockers, privacy tools: Block tracking

Misattribution (Research)

When traffic was sent from known sources, analytics often misattributed:

  • 100% as direct: TikTok, Slack, Discord, WhatsApp, Mastodon
  • 75%: Facebook Messenger
  • 30%: Instagram DMs
  • 14%: LinkedIn public posts
  • 12%: Pinterest

Mitigation

ActionPurpose
UTM parametersTag links in emails, social, campaigns: ?utm_source=X&utm_medium=Y&utm_campaign=Z
Block internal IPsExclude company visits from reports
Segment direct trafficSplit by page type to estimate dark vs. genuine direct

Segmenting Direct Traffic

  1. Expected direct: Homepage, short URLs, brand pages--likely real direct
  2. Unexpected direct: Long URLs, deep pages, product pages--likely dark traffic
  3. Report separately: Use segments in GA4/analytics to avoid overcounting direct

Attribution for Channel Optimization

Ads, growth channels, and medium can be optimized by viewing attribution data. Clean UTM + conversion tracking feeds attribution models; reliable attribution drives budget allocation and channel decisions.

UseAction
Optimize adsCompare paid channels (Google, Meta, LinkedIn) by attributed conversions; reallocate budget to winners
Optimize growth channelsIdentify which medium (cpc, email, social, referral) drives conversions; scale what works
Multi-touch attributionRequires clean UTM data; inconsistent tagging (e.g., facebook vs Facebook) fragments reports and misattributes

GA4 Default Channel Grouping: Align utm_medium and utm_source with GA4's rules to avoid "Unassigned" traffic. ~30% of campaigns lack proper UTM markup, leading to wasted ad spend; teams standardizing UTM see 29% improvement in attribution accuracy.

Reference: UTM.io – utm_medium, utm_campaign & utm_source Optimization, UTMs for Marketing Attribution

UTM Best Practices

ParameterUseExample
utm_sourceOriginnewsletter, facebook, google
utm_mediumChannel typeemail, cpc, social
utm_campaignCampaign namesummer_sale, product_launch
utm_contentVariant (optional)banner_a, cta_button
utm_termPaid keyword (optional)running_shoes

GA4 alignment (avoid Unassigned):

Channelutm_mediumutm_source
Paid Searchcpcgoogle, bing
Paid Socialpaid-social, cpcfacebook, instagram
Emailemailnewsletter, mailchimp
Organic Socialsocialtwitter, linkedin
App installcpc, appgoogle, facebook, apple
CTV / Streamingvideo, ctvhulu, roku, youtube
Display / Bannerdisplay, cpcPublisher or network name
Directory adspaid, cpctaaft, shopify, g2, capterra
  • Consistent naming: Lowercase, hyphens; document conventions; never tag internal links (overwrites session attribution)
  • Apply everywhere: Every link in emails, social posts, ads
  • Avoid: Typos, inconsistent values; causes fragmentation

Traffic Diversification

PrincipleGuideline
Search shareKeep organic search below ~75% of total traffic
HealthHigher direct + referral share = healthier profile
Brand sitesDiversified traffic is common for strong brands
EngagementContent, email, social, free tools drive return visits

See seo-monitoring for full SEO data analysis framework.

Natural Traffic Benchmark

Location: GA4 > Reports > Acquisition > Traffic acquisition

  1. Review organic traffic trend
  2. Record baseline (e.g., monthly total)
  3. Compare periodically to detect growth or decline

Output Format

  • Traffic source breakdown
  • Dark traffic estimate and actions
  • UTM tagging recommendations
  • Segmentation approach for reporting

Related Skills

  • analytics-tracking: Implement UTM, events, conversions; attribution models
  • google-ads, paid-ads-strategy: Paid channels; attribution informs budget allocation
  • ai-traffic-tracking: AI search traffic
  • google-search-console: GSC performance and indexing analysis
  • seo-monitoring: Full SEO data analysis system, benchmark, article database
  • email-marketing: Email strategy; UTM for email links

Frequently asked questions

What does the Traffic Analysis AI skill do?

When the user wants to analyze website traffic sources, attribution, or dark traffic. Also use when the user mentions "traffic sources," "dark traffic," "direct traffic," "UTM parameters," "traffic attribution," "channel attribution," "attribution optimization," "channel analysis," "traffic analysis," "traffic diversification," "natural traffic benchmark," or "organic vs paid traffic." For GA4 setup, use analytics-tracking.

Why use Traffic Analysis on TypingMind?

Because you install it once and use it with any model. Traffic Analysis 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 Traffic Analysis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kostja94/marketing-skills/tree/main/skills/analytics/sources/traffic. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Traffic Analysis?

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 Traffic Analysis?

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

Is the Traffic Analysis AI skill free?

Yes. It is published on GitHub by kostja94 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 👇