agentsclimarketplace

Analytics

Skill t0ddharris/compound-marketing/.claude/skills/analytics

Scale your marketing without sacrificing quality.

Install
npx -y skills add t0ddharris/compound-marketing --skill analytics

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Pull performance metrics from HubSpot, LinkedIn, X, and YouTube. Use when the user asks 'how are we doing,' 'what's our engagement,' 'show me metrics,' 'analytics,' 'email performance,' 'landing page stats,' 'campaign results,' 'LinkedIn analytics,' 'X analytics,' 'Twitter stats,' 'YouTube metrics,' or any question about marketing performance that real data can answer.

SKILL.md

5.7 KB, as published. Nobody here has run it

Analytics

Unified marketing analytics skill. Pulls real data from HubSpot, LinkedIn, X, and YouTube via CLI scripts.

How It Works

Each platform has a standalone TypeScript script in scripts/. Run them with npx tsx from the repo root. They read credentials from .env and output markdown tables to stdout.

All scripts live in: .claude/skills/analytics/scripts/

Platform Status

PlatformStatusEnv Vars Needed
HubSpotReadyHUBSPOT_PRIVATE_APP_TOKEN
LinkedInNeeds setupLINKEDIN_ACCESS_TOKEN, LINKEDIN_ORG_ID
X / TwitterNeeds setupX_BEARER_TOKEN, X_USERNAME
YouTubeNeeds setupYOUTUBE_ACCESS_TOKEN, YOUTUBE_CHANNEL_ID

Setup instructions for each platform are in setup/.

Commands

HubSpot Email Performance

npx tsx .claude/skills/analytics/scripts/hubspot-emails.ts [period] [limit]
  • period: 7d, 30d, 90d, all (default: 30d)
  • limit: number of top emails to show (default: 10)
  • Output: aggregate metrics (sent, delivered, open rate, click rate, CTOR, bounce rate) + top emails table

HubSpot Landing Page Analytics

npx tsx .claude/skills/analytics/scripts/hubspot-pages.ts [period] [limit]
  • period: 7d, 30d, 90d (default: 30d)
  • limit: number of pages to show (default: 10)
  • Output: summary (views, submissions, conversion rate) + page breakdown + traffic sources

HubSpot Campaign Performance

npx tsx .claude/skills/analytics/scripts/hubspot-campaigns.ts [period] [limit]
  • period: 7d, 30d, 90d, all (default: 30d)
  • limit: number of campaigns to show (default: 5)
  • Output: campaign overview + per-campaign asset metrics (emails, pages, forms, blog posts)

LinkedIn Analytics

npx tsx .claude/skills/analytics/scripts/linkedin.ts [command] [period] [limit]
  • command: overview, posts, followers (default: overview)
  • period: 7d, 30d, 90d (default: 30d)
  • limit: number of posts to show (default: 10)
  • Output: follower count + follower growth + post performance (impressions, clicks, likes, engagement)

X (Twitter) Analytics

npx tsx .claude/skills/analytics/scripts/x-analytics.ts [command] [period] [limit]
  • command: posts, profile (default: posts)
  • period: 7d, 30d, 90d (default: 30d)
  • limit: number of tweets to show (default: 20)
  • Output: profile stats + aggregate tweet metrics + top tweets by impressions

YouTube Analytics

npx tsx .claude/skills/analytics/scripts/youtube.ts [command] [period] [limit]
  • command: channel, videos (default: channel)
  • period: 7d, 30d, 90d (default: 30d)
  • limit: number of videos to show (default: 10)
  • Output: channel overview + period metrics (views, watch time, subs, engagement) + top videos

Dispatch Logic

When the user asks a performance question, run the appropriate script(s):

User asks about...Script to run
Email open rates, click rates, email performancehubspot-emails.ts
Landing page views, conversions, bounce rateshubspot-pages.ts
Campaign results, which campaign performed besthubspot-campaigns.ts
LinkedIn engagement, post performance, followerslinkedin.ts
Twitter/X metrics, tweet impressions, follower countx-analytics.ts
YouTube views, subscribers, watch time, video performanceyoutube.ts
"How are we doing?" / "What's working?" / cross-platformRun all configured platforms
Baseline metrics before creating new contentRun the relevant platform script
Comparing channelsRun multiple platform scripts and summarize

Proactive Usage

Don't wait for the user to ask "show me analytics." Run the appropriate script whenever:

  • Planning new content: Pull current metrics to set baselines
  • Evaluating what worked: Show real numbers, not guesses
  • CRO work: Pull landing page data before making recommendations
  • Social content planning: Check what posts performed best before drafting new ones
  • Email sequence work: Pull email performance to establish benchmarks
  • Reporting or reviews: Always lead with real data

Interpreting Results

When presenting analytics data, don't just dump the table. Add context:

  1. Call out standouts (best/worst performers, unusual spikes or drops)
  2. Compare to benchmarks when relevant (B2B SaaS averages: email open 20-25%, click 2-3%, landing page conversion 3-5%)
  3. Connect to actions ("Our top post was about X, suggesting the audience responds to Y")
  4. Note data gaps ("LinkedIn analytics not yet configured, so we can only compare HubSpot and X")

Error Handling

If a script fails with a missing env var error, check the setup doc for that platform and guide the user through configuration. Don't guess at credentials or make up data.

Output Location

Output location: marketing/reports/[report-slug]/ — confirm the project slug with the user before creating files.

Related Skills

  • tracking-setup: For setting up website analytics tracking (GA4, GTM, events, consent mode)
  • social-content: For creating social posts informed by analytics data
  • page-cro: For optimizing pages based on landing page analytics
  • email-sequence: For designing email flows using email performance baselines

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.