Skillget

analytics-skills

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Gecti
  • Code scan — Scanned 3 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This project provides a collection of instruction sets (skills) and tool-maps for AI agents, allowing them to analyze web analytics like a senior analyst. It supports platforms like GA4, Amplitude, and Mixpanel, teaching the AI how to accurately diagnose traffic, evaluate funnels, and read A/B tests.

Security Assessment
The overall risk is Low. The light code audit found no dangerous patterns, hardcoded secrets, or requests for risky permissions. Because this acts as an MCP server that reads analytics data, it inherently requires access to your analytics platforms, which often contain sensitive business metrics. However, the tool itself appears to act as an analytical framework rather than executing arbitrary shell commands or making independent, malicious network requests.

Quality Assessment
The project is very new and currently has low community visibility (only 5 GitHub stars). Despite the lack of widespread adoption, it is under active development (last updated today). It is properly licensed under the standard MIT license, making it safe for commercial and private use. It features extensive, high-quality documentation and clear instructions for setup.

Verdict
Safe to use.
SUMMARY

Skills for AI agents to read web analytics like a senior analyst: diagnose traffic, judge channels, read funnels, declare typed events, and read A/B tests. Tool-maps for Amplitude, Clamp, GA4, Mixpanel, and PostHog.

README.md

analytics-skills

Analytics skills for Claude, Cursor, and other AI agents. Read web analytics like a senior analyst: diagnose traffic changes, judge channel quality, read funnels, declare typed events, and read A/B tests without the usual rookie mistakes. Ships with tool-maps for Amplitude, Clamp, GA4, Mixpanel, and PostHog; add your own under tool-maps/. The schema-authoring and experiment-reading skills are built on the open Event Schema spec.

What's in the box

Skill What it does
analytics-profile-setup One-time interview that captures your business context (model, primary conversion, traffic range, ICP, data stack) into a local analytics-profile.md. Every other skill reads this file so answers are calibrated to your industry and scale. Run this first.
analytics-diagnostic-method The spine. Five-step method: load profile, frame the question, build a MECE hypothesis tree, triangulate, present with the Pyramid Principle. Covers signal vs noise and Simpson's paradox. Referenced by every other skill.
traffic-change-diagnosis Drill path for "why did traffic change". Fingerprints for tracking regressions, bot spikes, deploy-correlated drops, campaign ramps, SEO decay, and platform changes. Measurement checks first, always.
channel-and-funnel-quality Volume × engagement × conversion as a matrix. Vanity-traffic detection. Expected drop-off ranges per funnel step type. Mix-shift handling. Industry-specific benchmarks.
metric-context-and-benchmarks What's a good bounce / engagement / duration / CVR / churn / LTV:CAC / activation, by model. When each metric lies. Minimum sample sizes before trusting a rate.
event-schema-author Authors event-schema.yaml from existing track() calls. A portable, typed declaration of every product analytics event the codebase fires. The CLI generates a TypeScript type so call sites are autocompleted and type-checked at build time. Vendor-neutral; works with any analytics SDK.
experiment-result-reader Read a running A/B test honestly. Pulls per-variant exposure and conversion counts, computes lift, applies sample-size and sequential-testing discipline, checks for mix-shift and sample-ratio mismatch, and returns a verdict with caveats instead of a false-positive. Reads the experiment from the experiments: section of event-schema.yaml when present.

Built on real research

Frameworks and benchmarks the skills lean on, with sources:

Install

Pick whichever fits your setup. All three install the same skills.

Claude Code, plugin (recommended)

# Add the marketplace once
/plugin marketplace add clamp-sh/analytics-skills

# Install
/plugin install analytics-skills@clamp-sh

Skills become available as /analytics-skills:<name> and are auto-invoked when the task matches.

Any agent (Cursor, Claude Code, Copilot, others)

Install via Vercel's open skills CLI:

npx skills add clamp-sh/analytics-skills

Works with any tool that supports the Agent Skills spec.

Claude Code, standalone (no plugin machinery)

Clone into your personal skills directory:

git clone https://github.com/clamp-sh/analytics-skills.git /tmp/analytics-skills
cp -R /tmp/analytics-skills/skills/* ~/.claude/skills/

Or run the bundled installer which symlinks each skill (so git pull updates them):

git clone https://github.com/clamp-sh/analytics-skills.git ~/.analytics-skills
~/.analytics-skills/scripts/install-personal.sh

For a single project, clone into .claude/skills/ inside the repo instead.

Codex CLI

Same SKILL.md format, different location. User-level install:

git clone https://github.com/clamp-sh/analytics-skills.git /tmp/analytics-skills
cp -R /tmp/analytics-skills/skills/* ~/.codex/skills/

For a project, copy into .agents/skills/ at the repo root instead. Codex auto-detects new skills; restart if needed.

claude.ai

Build the per-skill zips and upload each via Settings → Features → Skills:

./scripts/build-claude-ai-zips.sh
# Produces dist/analytics-diagnostic-method.zip etc.

Pre-built zips for each release are also attached to the GitHub release page.

Usage

These are model-invoked skills. You don't need to call them by name; just ask real analytics questions and Claude will load the relevant skill.

First run, on a new project:

Set me up. I want the skills calibrated to my business.

This loads analytics-profile-setup, walks a 5-minute interview, and writes analytics-profile.md to the repo root. Every subsequent question gets industry-aware answers.

After setup, ask real questions:

Traffic dropped 30% on Tuesday. What happened?

Loads traffic-change-diagnosis. Walks the hypothesis tree (measurement → time-shape → channel → cohort → content), pulls numbers from your analytics source, returns a diagnosis. Not a screenshot of a chart.

Is our signup funnel broken? Pricing → checkout is converting at 14%.

Loads channel-and-funnel-quality and metric-context-and-benchmarks. Compares against expected step drop-off, slices by cohort, flags whether 14% is low, normal, or suspicious given your sample size and model.

Our bounce rate is 68%. Is that bad?

Loads metric-context-and-benchmarks. Handles the GA4 vs UA definition gotcha, looks up the relevant page-type range, flags the sample-size caveat if needed.

Supported analytics platforms

The skills are platform-neutral; per-platform MCP invocations live in tool-maps/. One file per supported analytics tool, all covering the same canonical 17-row workflow taxonomy.

Tool Tool-map Surface
Amplitude amplitude.md query_amplitude_data covers most rows; cohorts and experiments are dedicated tools
Clamp clamp.md dedicated MCP tool per row of the canonical taxonomy
GA4 ga4.md run_report for aggregate rows; funnels and cohort retention not exposed by the wrapper
Mixpanel mixpanel.md Run-Query types (insights, funnels, flows, retention)
PostHog posthog.md Trends/Funnels/Retention/Paths insights plus HogQL

The full row-by-row coverage matrix is at tool-maps/capability-matrix.md. analytics-profile-setup records the active platform in analytics-profile.md under tool_map:; downstream skills load the matching tool-map automatically.

Using a different analytics source? The method still applies. Add a tool-map for it (see tool-maps/README.md for the template).

Contributing

Issues and PRs welcome. See CONTRIBUTING.md for how to add a skill and the style conventions we follow.

License

MIT. See LICENSE.

Yorumlar (0)

Sonuc bulunamadi