Analytics pattern discovery in a codebase
Discover how analytics tracking calls are actually written in a codebase — SDK calls, wrappers, event and property naming conventions
- What
- Discover how analytics tracking calls are actually written in a codebase — SDK calls, wrappers, event and property naming conventions
- Cost
- Free
- Needs
- a codebase with (or without) analytics tracking to discover patterns in; the Amplitude MCP server connected for catalog-based naming evidence (recommended, falls back to grep)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — Amplitude's official skill for discovering how analytics tracking is actually written in a codebase. It greps for tracking-call signals (`.track(`, `ampli.`, `amplitude.track`, custom wrappers like `trackEvent()` or `useAnalytics()`), groups call sites into patterns by SDK/method/argument-structure — treating each custom wrapper as its own pattern — and resolves event- and property-naming conventions in a strict precedence order: repo instrumentation context file first, then the Amplitude MCP catalog, then real code, then the taxonomy skill as a last resort, refusing to guess when the evidence is thin. Output is a deduplicated pattern list with generalized examples and file paths, ordered most-common-first, plus the dominant naming conventions. By @amplitude, listed here with credit to its creator. Honest caveats: a discovery skill — it documents patterns, it does not write new tracking code; without the Amplitude MCP server it falls back to pure codebase grep; test files and mocks are excluded unless they're the only evidence. Discovered via skills.sh. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Prerequisites: a codebase with (or without) analytics tracking to discover patterns in; the Amplitude MCP server connected for catalog-based naming evidence (recommended, falls back to grep) Install "Analytics pattern discovery in a codebase" for me. Give my agent Amplitude's official skill for discovering how analytics tracking calls are actually written — pattern grouping, naming-convention resolution, deduplicated pattern list with examples and paths Repository: https://github.com/amplitude/mcp-marketplace/blob/main/plugins/amplitude/skills/discover-analytics-patterns/SKILL.md 1. Fetch the SKILL.md file for the amplitude-mcp-marketplace-discover-analytics-patterns skill from the repository into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md into the agent's skills directory, in a folder named "amplitude-mcp-marketplace-discover-analytics-patterns". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. connect the Amplitude MCP server for catalog-based naming evidence, or point the agent at a repo to analyze). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.