How do I install the Add Analytics Instrumentation skill?

Run npx skillmds@latest add rpatel05/add-analytics-instrumentation in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Add Analytics Instrumentation safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Add Analytics Instrumentation?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Add Analytics Instrumentation free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Add Analytics Instrumentation?

rpatel05 (@rpatel05) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Add Analytics Instrumentation by rpatel05

Name: Add Analytics Instrumentation
Rating: 4.5 (4 reviews)
Author: rpatel05

Add Analytics Instrumentation

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. Use this skill whenever a user wants to add analytics to a PR or feature.

rpatel05 Updated Sep 22, 2026

File contents

add-analytics-instrumentation

Orchestrator for the analytics instrumentation pipeline. Your job is to figure out what the user wants to instrument, gather the relevant code, and run the pipeline to produce a tracking plan.

Pipeline

Step 0: Capture intent

Determine what the user wants to instrument:

Input type	How to recognize it
PR	A PR URL, PR number, or phrases like "this PR", "my PR"
Branch	A branch name or "this branch", "my branch"
File / Directory	A file path, directory path, or glob pattern
Feature	A natural-language description of functionality

If ambiguous, ask the user what they want to instrument.

Step 1: diff-intake (PR or Branch)

Invoke the diff-intake skill with the PR or branch reference.

It produces a change_brief YAML block.

Step 1a: Direct file read (File / Directory)

Build the change_brief YAML by reading files directly:

Resolve the input (directory → all source files, file → that file)
Read each file and summarize what it does
Scan for existing instrumentation patterns
Build change_brief YAML

Step 1b: Feature search (Feature)

The user described a feature. Find the relevant code:

Search git commit history for related commits
Search codebase for files related to feature
Build change_brief YAML

Step 2: discover-event-surfaces

Invoke discover-event-surfaces with the change_brief YAML.

It produces an event_candidates YAML block.

If empty, stop and tell user nothing to instrument.

Step 3: instrument-events

Invoke instrument-events with the event_candidates YAML.

It produces a trackingPlan JSON with:

Exact file locations
Tracking code
Property definitions

Presenting the result

Walk through each event:

What it tracks and why
Where tracking call goes
What properties it sends

Then ask if they want to adjust or proceed.

Error handling

If any step fails, surface the error and stop. Don't continue with incomplete data.

---name: add-analytics-instrumentationdescription: 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. Use this skill whenever a user wants to add analytics to a PR or feature.---# add-analytics-instrumentationOrchestrator for the analytics instrumentation pipeline. Your job is to figure out what the user wants to instrument, gather the relevant code, and run the pipeline to produce a tracking plan.## Pipeline### Step 0: Capture intentDetermine **what** the user wants to instrument:| Input type | How to recognize it || -------------------- | ------------------------------------------------------------------------------ || **PR** | A PR URL, PR number, or phrases like "this PR", "my PR" || **Branch** | A branch name or "this branch", "my branch" || **File / Directory** | A file path, directory path, or glob pattern || **Feature** | A natural-language description of functionality |**If ambiguous**, ask the user what they want to instrument.### Step 1: diff-intake (PR or Branch)Invoke the `diff-intake` skill with the PR or branch reference.It produces a `change_brief` YAML block.### Step 1a: Direct file read (File / Directory)Build the `change_brief` YAML by reading files directly:1. Resolve the input (directory → all source files, file → that file)2. Read each file and summarize what it does3. Scan for existing instrumentation patterns4. Build `change_brief` YAML### Step 1b: Feature search (Feature)The user described a feature. Find the relevant code:1. Search git commit history for related commits2. Search codebase for files related to feature3. Build `change_brief` YAML### Step 2: discover-event-surfacesInvoke `discover-event-surfaces` with the `change_brief` YAML.It produces an `event_candidates` YAML block.If empty, stop and tell user nothing to instrument.### Step 3: instrument-eventsInvoke `instrument-events` with the `event_candidates` YAML.It produces a `trackingPlan` JSON with:- Exact file locations- Tracking code- Property definitions## Presenting the resultWalk through each event:- What it tracks and why- Where tracking call goes- What properties it sendsThen ask if they want to adjust or proceed.## Error handlingIf any step fails, surface the error and stop. Don't continue with incomplete data.

Frequently asked questions