Token导航 LogoToken导航

Agent Skill · 研究检索

traffic-analysis(流量分析)

traffic-analysis 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

traffic-analysis 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为操作浏览器;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 9,602。

总安装 13,942周安装 564GitHub Stars 409下载 4,377核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:traffic-analysis(流量分析)
来源仓库:https://github.com/kostja94/marketing-skills
仓库路径:skills/traffic-analysis
安装命令:
npx skills add https://github.com/kostja94/marketing-skills --skill traffic-analysis
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/kostja94/marketing-skills --skill traffic-analysis

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

traffic-analysis 用于查找和筛选与流量相关的信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果或分析用户行为数据。适用于 SEO 优化、广告投放效果评估或用户路径研究等场景,可根据关键词或任务线索检索相关案例、工具或指标说明。

通过 npx skills add 命令从指定 GitHub 仓库安装,需结合原始 README 核验具体用法和输入参数格式。使用前应确认权限范围、维护状态,并注意是否会触发联网或外部 API 调用,避免产生意外费用或安全风险。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/traffic-analysis

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/kostja94/marketing-skills --skill traffic-anal…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要操作浏览器,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

traffic-analysis 怎么安装?

在终端执行 npx skills add https://github.com/kostja94/marketing-skills --skill traffic-analysis。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

traffic-analysis 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

traffic-analysis 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

traffic-analysis 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

traffic-analysis 用的人多吗?

公开数据是累计安装 13,942 次,近一周安装 564 次,下载 4,377 次,GitHub 409 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

traffic-analysis 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
traffic-analysis

流量分析 · 本页

13,942409操作浏览器未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

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

平台分布

Codex

35.01%
按下载量换算1,532

Claude

32.91%
按下载量换算1,440

Cursor

17.84%
按下载量换算781

Gemini CLI

9.42%
按下载量换算412

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills