nimrodfisher/data-analytics-skills

---

What’s in this repo?

A structured library of skills (reusable instruction sets) that Claude activates on demand to help with every stage of the analyst workflow: from data quality checks and deep-dive analysis, through documentation and dashboards, all the way to stakeholder communication.

---

🗺️ Skill Map

Open interactive version on Excalidraw

---

Why these skills are different

[!NOTE] Traditional AI assistants require extensive upfront configuration — schemas, metric definitions, business rules — before they’re useful. These skills work on-demand.

Each skill asks targeted questions to gather exactly what it needs, then executes a complete, structured workflow.

---

📚 Skill Categories

---

🚀 Quick Start

[!TIP] Describe your task to Claude naturally — it will select and activate the right skill automatically. No slash commands needed.

Example:

You:    "I need to understand why our activation rate dropped 12% last week"
Claude: [activates root-cause-investigation, asks for metric data and context]
You:    [provides data and business context]
Claude: [runs structured investigation with hypothesis testing]

Which skill to start with?

---

📖 How skills work

Each skill follows the same on-demand context pattern:

1. Request minimum viable context — Claude asks only what’s essential to start
2. Execute the workflow — structured, step-by-step analytical process
3. Surface assumptions — anything uncertain is flagged, not silently assumed
4. Deliver a consistent output — templated result you can share or iterate on

[!NOTE] Skills degrade gracefully: if you can’t provide everything, Claude states what it’s assuming and proceeds.

---

🛠️ Customization

Skills work out-of-the-box. To make them company-specific, add a references/ folder inside any skill with:

skill-name/
├── SKILL.md
└── references/
    ├── company-schema.md       ← your table/column definitions
    ├── metric-definitions.md   ← standard metric formulas
    └── business-rules.md       ← thresholds, edge cases, etc.

Claude will pull this context automatically when the skill runs.

---

🎓 Suggested ramp-up

Week 1 — Get comfortable

• Run programmatic-eda on a familiar dataset
• Practice providing context when Claude asks
• Use analysis-planning at the start of your next project

Week 2–3 — Add your core toolkit

• Set up semantic-model-builder for your key metrics (saves time forever)
• Add query-validation to your SQL workflow
• Pick 2 analysis skills that match your domain

Week 4+ — Go advanced

• Chain 4–5 skills end-to-end on a full project
• Add company-specific references to the skills you use most
• Build team context documents for shared onboarding

---