Compare User Journeys
Compares how two user groups behave differently by analyzing Amplitude Session Replays and metrics side by side. Produces a behavioral diff showing what one group does that the other doesn't. Use when a PM or growth lead asks "what do converters do differently", "how do power users behave", "why do churned users leave", "compare these cohorts", "what separates segment A from B", or wants to understand the qualitative behavioral gap between two user populations.
Install
/plugin marketplace add amplitude/mcp-marketplaceThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add amplitude/mcp-marketplace --skill compare-user-journeysgit clone --depth 1 https://github.com/amplitude/mcp-marketplace.git /tmp/mcp-marketplace
mkdir -p ~/.claude/skills
cp -r /tmp/mcp-marketplace/plugins/amplitude/skills/compare-user-journeys ~/.claude/skills/compare-user-journeysPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Compare User Journeys Investigate what distinguishes two user groups by pulling session replays and metrics for each, then producing a behavioral diff. This skill answers "what do winners do differently?" with concrete evidence from real sessions. --- ## CRITICAL: Tool Reference **Primary tools:** - **`Amplitude:get_amp_session_replay_info`** with `action: "search"` — Find sessions for each user group using event count filters and user property filters. Run this twice — once per group. - **`Amplitude:get_amp_session_replay_info`** with `action: "events"` — Decode replays into interaction timelines. Run this for sessions from both groups. **Supporting tools:** - **`Amplitude:search_amp_entities`** — Search for existing charts, funnels, dashboards, and cohorts relevant to the comparison. Always check for existing analysis before building from scratch. - **`Amplitude:use_amplitude_cohorts`** with `action: "list"` — Discover existing cohorts that define the groups (e.g., "power users", "churned", "converted"). - **Available taxonomy reader** — Inspect the connected catalog and use its event and property read capabilities to discover valid names and scopes. - **`Amplitude:get_amplitude_charts`** with `include: "data"` — Pull quantitative metrics segmented by the two groups for statistical grounding. - **`Amplitude:use_amplitude_ai_feedback`** with `facet: "insights"` / `facet: "mentions"` — Check if feedback themes differ between groups. --- ## Instructions
Details
- Skill name
compare-user-journeys- Repository
- amplitude/mcp-marketplace
- Path
plugins/amplitude/skills/compare-user-journeys/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Compare User Journeys skill do?
Compares how two user groups behave differently by analyzing Amplitude Session Replays and metrics side by side. Produces a behavioral diff showing what one group does that the other doesn't. Use when a PM or growth lead asks "what do converters do differently", "how do power users behave", "why do churned users leave", "compare these cohorts", "what separates segment A from B", or wants to understand the qualitative behavioral gap between two user populations.
How do I install the Compare User Journeys skill?
Claude Code plugin: /plugin marketplace add amplitude/mcp-marketplace. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Compare User Journeys popular?
It lives in amplitude/mcp-marketplace, which has 48 GitHub stars and 12 forks.
Related skills
Add Analytics Instrumentation
48amplitude/mcp-marketplace
End-to-end analytics instrumentation workflow for a PR, branch, file, directory, or feature. Reads the code, discovers what events should be tracked, and produces a concrete instrumentation plan — all in one shot. Use this skill whenever a user wants to add analytics to a PR, asks "instrument this PR", "add tracking to this branch", "what analytics does this file need", "instrument the checkout flow", "run the full instrumentation workflow", or any request that implies going from code changes to a tracking plan. Also trigger when the user gives you a PR link, branch name, file path, or feature
Analyze Account Health
48amplitude/mcp-marketplace
Summarizes B2B account health by analyzing usage patterns, engagement trends, risk signals, and expansion opportunities. Use for customer success reviews, renewal preparation, QBRs, or account prioritization.
Analyze AI Topics
48amplitude/mcp-marketplace
Analyzes what users ask AI agents about and how well each topic is served. Only use when the user has Amplitude Agent Analytics instrumented in their project. Use when the user asks "what are people asking the AI", "top AI topics", "where is the AI struggling", "AI coverage gaps", "what should we improve in our AI", or wants product insights from AI conversation patterns.
Hipaa
33scytale-labs/GRC-Claude-Skills
Use when the user asks about HIPAA — Privacy Rule, Security Rule (administrative, physical, technical safeguards), Breach Notification Rule, Business Associate Agreements (BAAs), the HITECH Act, OCR audits, or determining whether an organisation is a covered entity or business associate. For US healthcare providers, health plans, clearinghouses, and their business associates and subcontractors.
Analyze Feedback
48amplitude/mcp-marketplace
Synthesizes customer feedback into actionable themes including feature requests, bugs, pain points, and praise. Use when planning product roadmap, understanding user sentiment, investigating specific issues, or preparing voice-of-customer reports.
Responding to Review
33okgrit/done-is-a-claim
Resolve incoming code-review feedback against the current revision and user contract. Use to assess comments, implement authorized fixes, explain supported disagreement and verify item status; review does not authorize posting replies.
Browse the most popular Claude skills, all marketing, sales & business skills, or write your own with the skills generator.