
Discover Analytics Patterns
Before you let this run inside your instrumentation flow, know that it doesn't just read your code. It also pulls live event and property names from an Amplitude MCP server when one is connected, and it treats your `.amplitude/instrumentation-agent-context.md` as the top authority on naming. That's a sensible precedence order, but it means the output is only as good as whatever context file or MCP catalog you point it at. The skill is strict about filtering out Amplitude's bracket-prefixed system events, which keeps the naming inference honest. It separates raw SDK calls, Ampli typed methods, and custom wrappers into distinct patterns, which matters because engineers will reach for the wrapper, not the SDK. If you're about to write instrumentation code in an unfamiliar repo, run this first.
- skills.sh installs
- 55.5K
- GitHub stars
- 47
- last updated
- Oct 26, 2026
Install
$ npx -y skills add amplitude/mcp-marketplace --skill discover-analytics-patterns --agent claude-codeInstalls into .claude/skills of the current project.
Files
discover-analytics-patterns
Your goal is to find out how this codebase sends analytics events — not which events exist, but the specific code patterns engineers use to fire a tracking call. This output helps engineers add new events that look consistent with the rest of the codebase. It should also tell downstream skills how event names and property names are typically written in code here.
When determining naming conventions in this skill, use the following sources in strict order of preference:
- Customer directives in
.amplitude/instrumentation-agent-context.md(and any files it references), if present — explicit conventions the customer wants followed, so they override everything below. - Events and properties observed from the Amplitude MCP server
- Real tracking call sites in the codebase
- The
taxonomyskill at../taxonomy/SKILL.md
Step 0: Read repo instrumentation context
Sponsors
Details
- Repository
- github.com/amplitude/mcp-marketplace
- Categories
- Documentation, Code Review & Quality, AI & Agent Building, Data Science & ML, Marketing & SEO
- First seen
- Oct 26, 2026