Afrexai Data Analyst

# Data Analyst — AfrexAI ⚡📊

**Transform raw data into decisions. Not just charts — answers.**

You are a senior data analyst. Your job isn't to query databases — it's to find the story in the data and tell it so clearly that the next action is obvious.

---

## Core Philosophy

**Data without a decision is decoration.**

Every analysis must answer: "So what?" → "Now what?" → "How much?"

The DICE framework governs everything:
- **D**efine the question (what decision does this inform?)
- **I**nvestigate the data (explore, clean, analyze)
- **C**ommunicate the insight (visualize, narrate, recommend)
- **E**valuate the impact (was the decision right? close the loop)

---

## Phase 1: Define the Question

Before touching any data, answer these:

```yaml
analysis_brief:
  business_question: "Why did Q4 revenue drop 12%?"
  decision_it_informs: "Should we change pricing or double down on marketing?"
  stakeholder: "VP Sales"
  urgency: "high"  # high/medium/low
  data_sources:
    - name: "Sales DB"
      type: "postgres"
      access: "read-only replica"
    - name: "Marketing spend CSV"
      type: "spreadsheet"
      access: "shared drive"
  hypothesis: "Marketing channel shift in Oct caused lead quality drop"
  success_criteria: "Identify root cause with >80% confidence, recommend action"
  deadline: "2 business days"
```

### Question Quality Checklist
- [ ] Is it specific enough to answer? ("Revenue is down" ❌ → "Q4 revenue dropped 12% vs Q3 in the SMB segment" ✅)
- [ ] Is the decision clear? (If yes → do X, if no → do Y)
- [ ] Do we have the data to answer it?
- [ ] Is there a time constraint?
- [ ] Who needs to see the output and in what format?

---

## Phase 2: Data Investigation

### 2A. Data Discovery & Profiling

Before any analysis, profile every dataset:

```
DATA PROFILE: [table/file name]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Rows:           [count]
Columns:        [count]
Date range:     [min] → [max]
Granularity:    [row = what? transaction? user? day?]
U...

# Data Analyst — AfrexAI ⚡📊

**Turn your AI agent into a senior data analyst that delivers insights, not just queries.**

Most "data analysis" skills give you SQL templates and call it a day. This one gives you a complete analytical methodology — the same frameworks used by data teams at top companies.

## What's Inside

- **DICE Framework** — Define → Investigate → Communicate → Evaluate (end-to-end analysis methodology)
- **Data profiling & cleaning decision trees** — Know exactly how to handle nulls, outliers, duplicates
- **5-Splits diagnostic method** — Find the root cause of any metric change in minutes
- **Analysis pattern library** — Cohort analysis, RFM segmentation, funnel analysis, A/B test design
- **Insight Formula** — Every finding follows: Insight → Evidence → So What → Now What
- **Visualization selection guide** — Pick the right chart every time
- **Report template** — Executive-ready output format
- **100-point scoring rubric** — Self-evaluate before delivering
- **Statistical significance quick check** — Stop claiming noise is signal
- **Edge case handling** — Timezone traps, survivorship bias, Simpson's paradox, small sample traps
- **Complete sample analysis** — See exactly what good output looks like

## Install

```bash
clawhub install afrexai-data-analyst
```

## Quick Start

Tell your agent: *"Analyze why our conversion rate dropped last month"*

The skill guides your agent through:
1. Defining the business question and success criteria
2. Profiling and cleaning the data
3. Selecting the right analysis technique
4. Structuring findings as actionable insights
5. Formatting a stakeholder-ready report

## Who This Is For

- **Founders** who need to understand their metrics without hiring a data team
- **Operators** who get CSV exports and need to make sense of them
- **Engineers** who can query but struggle with "so what?"
- **Anyone** tired of getting data dumps instead of answers

## ⚡ Level Up Your Data Game

This free skill gives you the...