31 portable AI-powered skills that turn Claude or Codex into a hands-on analytics partner
No setup required · Works for any company or industry
A structured library of skills (reusable instruction sets) that Claude Code or Codex 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. Skills follow the open Agent Skills standard (a plain SKILL.md format), so they also work with other compatible agents like Cursor and Windsurf.
Note
Traditional AI assistants require extensive upfront configuration — schemas, metric definitions, business rules — before they're useful. These skills work on-demand.
| Traditional approach | These skills |
|---|---|
| Needs prep before use | Zero setup required |
| Breaks when business rules change | Adapts naturally |
| Company-specific, hard to share | Portable across any org |
| Silent on assumptions | Teaches you what context matters |
Each skill asks targeted questions to gather exactly what it needs, then executes a complete, structured workflow.
🔍 01 · Data Quality & Validation 3 skills
Foundation — start here whenever you're working with new data.
| Skill | What it does |
|---|---|
| programmatic-eda | Systematic exploratory data analysis with automated sanity checks |
| data-quality-audit | Comprehensive quality assessment against business rules and schema |
| query-validation | SQL review for correctness, performance, and edge cases |
📝 02 · Documentation & Knowledge 7 skills
Build reusable context so you never explain the same thing twice.
| Skill | What it does |
|---|---|
| semantic-model-builder | Create a shared semantic layer for key metrics and dimensions |
| analysis-documentation | Document findings with reproducible methodology |
| data-catalog-entry | Standardized metadata and descriptions for data assets |
| sql-to-business-logic | Translate complex SQL into plain business language |
| analysis-assumptions-log | Track every assumption and decision in an analysis |
| metric-reconciliation | Trace and resolve discrepancies when metric sources disagree |
| schema-mapper | Column-level mapping between source and target schemas |
📊 03 · Data Analysis & Investigation 7 skills
Core workflows for the analytical heavy lifting.
| Skill | What it does |
|---|---|
| cohort-analysis | Time-based cohort tracking with retention curves |
| segmentation-analysis | Customer/user segmentation with actionable profiles |
| funnel-analysis | Conversion funnel with drop-off root-cause |
| time-series-analysis | Trend detection, seasonality, and forecasting |
| root-cause-investigation | Structured diagnosis of unexpected metric changes |
| ab-test-analysis | Rigorous experiment analysis with significance testing |
| business-metrics-calculator | Standard business metric calculation with benchmarks |
🎨 04 · Data Storytelling & Visualization 5 skills
Turn raw findings into insights that drive decisions.
| Skill | What it does |
|---|---|
| insight-synthesis | Structure analysis outputs into clear business insights |
| visualization-builder | Chart type selection, design guidance, and spec generation |
| executive-summary-generator | Concise executive-ready summaries of complex analysis |
| dashboard-specification | Full dashboard requirements with metrics and layout |
| data-narrative-builder | Craft a compelling story arc from analytical findings |
🤝 05 · Stakeholder Communication 5 skills
Bridge the gap between technical depth and business understanding.
| Skill | What it does |
|---|---|
| technical-to-business-translator | Reframe technical findings for a business audience |
| stakeholder-requirements-gathering | Structured elicitation to clarify what stakeholders actually need |
| analysis-qa-checklist | Pre-delivery quality gate before sharing results |
| methodology-explainer | Explain analysis approach to any audience level |
| impact-quantification | Estimate and frame the business impact of findings |
⚙️ 06 · Workflow Optimization 4 skills
Work smarter across every project.
| Skill | What it does |
|---|---|
| analysis-planning | Structure the approach before diving in |
| context-packager | Package context efficiently for AI-assisted analysis |
| peer-review-template | Structured peer review checklist for analytical work |
| analysis-retrospective | Post-analysis learning and process improvement |
Caliboard — visual plan review for Claude Code and Codex. See what your agent plans before it writes code: review exact steps, challenge decisions, and approve the revision that becomes code.
Version: 1.2.0 · Maintainer: Nimrod Fisher · Last Updated: September 2026
Each skill is a folder containing a SKILL.md (plus optional scripts/, references/, and assets/). Clone the repo and copy the skills you want into your agent's skills directory:
git clone https://github.com/nimrodfisher/data-analytics-skills.gitClaude Code: personal skills (all projects) go in ~/.claude/skills/, project skills in .claude/skills/ inside your project:
cp -r 01-data-quality-validation/programmatic-eda ~/.claude/skills/Codex: user skills (all repos) go in ~/.agents/skills/, repo skills in .agents/skills/ at the repository root:
cp -r 01-data-quality-validation/programmatic-eda ~/.agents/skills/New here? QUICKSTART.md walks you through your first skill in 5 minutes, and STRUCTURE.md explains how every skill is packaged.
[!TIP] Describe your task to Claude or Codex 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"
Agent: [activates root-cause-investigation, asks for metric data and context]
You: [provides data and business context]
Agent: [runs structured investigation with hypothesis testing]
| You need to... | Start here |
|---|---|
| Explore an unfamiliar dataset | programmatic-eda → data-quality-audit |
| Write or review SQL | query-validation + schema-mapper |
| Understand a metric drop/spike | root-cause-investigation |
| Analyze experiment results | ab-test-analysis |
| Build a dashboard | dashboard-specification + visualization-builder |
| Present to leadership | executive-summary-generator + insight-synthesis |
| Document your methodology | analysis-documentation + analysis-assumptions-log |
| Start a complex analysis | analysis-planning first, always |
Each skill follows the same on-demand context pattern:
- Request minimum viable context — your agent asks only what's essential to start
- Execute the workflow — structured, step-by-step analytical process
- Surface assumptions — anything uncertain is flagged, not silently assumed
- Deliver a consistent output — templated result you can share or iterate on
[!NOTE] Skills degrade gracefully: if you can't provide everything, your agent states what it's assuming and proceeds.
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.
Your agent will pull this context automatically when the skill runs.
Week 1 — Get comfortable
- Run
programmatic-edaon a familiar dataset - Practice providing context when your agent asks
- Use
analysis-planningat the start of your next project
Week 2–3 — Add your core toolkit
- Set up
semantic-model-builderfor your key metrics (saves time forever) - Add
query-validationto 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