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:
Quick answer
Analytics pattern discovery in a codebase is a free Muse skill that discovers how analytics tracking calls are actually written in a codebase, covering SDK calls, wrappers, and event and property naming conventions, so new tracking follows the patterns already in use instead of inventing a second, conflicting naming scheme.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit e61691fStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. 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://raw.githubusercontent.com/amplitude/mcp-marketplace/e61691f81196cfd9f4314a347f6d2b1c6106f780/plugins/amplitude/skills/discover-analytics-patterns/SKILL.md Pinned version: install the code at commit e61691f81196cfd9f4314a347f6d2b1c6106f780 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file for the amplitude-mcp-marketplace-discover-analytics-patterns skill from the repository into a temporary folder 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.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- e61691f · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill 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 skill before installing it.