Skill Detail

Audit clickstream analytics with Retentioneering agents

Use Retentioneering's Python toolkit, MCP server, and agent skills to run reproducible customer-journey and event-log analytics that agents can validate and cross-check.

Data Extraction & TransformationMCP
Data Extraction & Transformation MCP Security Reviewed
โญ 919 GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill audit-clickstream-analytics-with-retentioneering-agents Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
Python, Retentioneering toolkit, clickstream or event-log dataset, optional Retentioneering MCP server or agent skills, MCP-capable agent client
Install & setup
Install the Retentioneering Python package following the upstream documentation, prepare event data as a Retentioneering Eventstream, and configure the MCP server or provided agent skills when using an agent client for analysis and cross-checking.
Author
Retentioneering
Publisher
Open Source Project
Last updated
Sep 21, 2026
Quick brief

Use Retentioneering when an analyst or agent operator needs reproducible answers from clickstream, customer journey, or event-log data instead of one-off generated analysis scripts.

How it works

What this skill actually does

The repeatable workflow is to install Retentioneering, load timestamped event data into an Eventstream, and have an MCP-capable or skill-capable agent run validated analytics primitives for funnels, user-flow graphs, step matrices, behavioral segments, cohort differences, A/B tests, process mining, and Markov-chain simulations. The operator reviews generated visualizations and exported reports, then asks the agent to cross-check assumptions or rerun the analysis with changed cohorts.

Invoke this instead of using a product analytics dashboard normally when the work requires auditable, code-backed investigation over raw event sequences and agent-readable intermediate results. The scope boundary is reproducible clickstream/event-log analytics through Retentioneering’s toolkit and MCP/agent interfaces; it is not a generic analytics platform, BI tool, or Python library listing.

Inputs and prerequisites: Python, Retentioneering toolkit, clickstream or event-log dataset, optional Retentioneering MCP server or agent skills, MCP-capable agent client.

Setup notes: Install the Retentioneering Python package following the upstream documentation, prepare event data as a Retentioneering Eventstream, and configure the MCP server or provided agent skills when using an agent client for analysis and cross-checking.

Source and verification boundary: use https://retentioneering.com/docs/ as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a MCP workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.