Agent skill · Data & Analytics

pulsecheck

Query your analytics in plain language via Telegram. Ask 'how many signups yesterday?' and get instant answers from Google Analytics, Plausible, Fathom, Mixpanel, or PostHog. Use when: checking metrics without opening dashboards, quick performance checks, or comparing time periods. NOT for: building custom dashboards, exporting raw data, or real-time streaming analytics.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill pulsecheck --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 8 KB
Bundled scripts: none
Path: skills/analysis/pulsecheck/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# PulseCheck 📊 Query your analytics dashboards using natural language. No more logging in, clicking through tabs, or squinting at charts at 2 AM. ## When to Use ✅ **USE this skill when:** - "How many signups did we get yesterday?" - "Show me bounce rate for the homepage" - "Compare this week's revenue to last week" - "What's our top traffic source today?" - "Did the blog post launch move the needle?" - Quick metric checks without context switching - Checking numbers from your phone - Sharing quick stats with the team ## When NOT to Use ❌ **DON'T use this skill when:** - Building custom dashboards → use the analytics platform directly - Exporting raw event data → use platform APIs or data warehouse - Real-time streaming analytics → use dedicated monitoring tools - Complex funnel analysis → use the full analytics interface - Attribution modeling → requires specialized tools - Creating visualizations → use Looker, Tableau, etc. ## Setup Install the PulseCheck CLI: ```bash npm install -g @pawhub/pulsecheck ``` Connect your analytics platform (choose one or more): ```bash # Google Analytics pulsecheck connect google-analytics --property-id UA-12345678-1 # Plausible pulsecheck connect p

What's inside
Steps it walks through
  1. When to Use
  2. When NOT to Use
  3. Setup
  4. Example Interactions
  5. Quick Metrics
  6. Commands
  7. Quick Queries
  8. Scheduled Reports
  9. Custom Metrics
  10. Telegram Integration
  11. Natural Language Processing
  12. Supported Platforms
  13. Configuration
  14. Tips from Paw
Ships with 1 file
  • metadata.json
Commands it runs
npm install -g @pawhub/pulsecheck
Google Analytics
pulsecheck connect google-analytics --property-id UA-12345678-1
Plausible
pulsecheck connect plausible --site-id example.com --api-key your-api-key
Fathom
pulsecheck connect fathom --site-id ABC123 --api-key your-api-key
Mixpanel
pulsecheck connect mixpanel --project-id 12345 --api-key your-api-key
PostHog
More from claude-skill-registry
All skills →
About this skill
What does the pulsecheck skill do?

Query your analytics in plain language via Telegram. Ask 'how many signups yesterday?' and get instant answers from Google Analytics, Plausible, Fathom, Mixpanel, or PostHog. Use when: checking metrics without opening dashboards, quick performance checks, or comparing time periods. NOT for: building custom dashboards, exporting raw data, or real-time streaming analytics.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill pulsecheck --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going