Skip to content
Back to search

data-analytics-skills

A comprehensive list of Claude & Codex skills for a wide range of data analytics tasks

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/nimrodfisher--data-analytics-skills/badge.svg)](/listings/nimrodfisher--data-analytics-skills)

HTML

<a href="/listings/nimrodfisher--data-analytics-skills"><img src="/api/listings/nimrodfisher--data-analytics-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Install

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.git

**Claude 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](./QUICKSTART.md) walks you through your first skill in 5 minutes, and [STRUCTURE.md](./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]

Which skill to start with?

| 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 |

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 260 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. # Data Analytics Skills for Claude & Codex
  3. **31 portable AI-powered skills that turn Claude or Codex into a hands-on analytics partner**
  4. *No setup required · Works for any company or industry*
  5. <br>
  6. [![](https://img.shields.io/badge/31_Skills-4a9eed?style=for-the-badge)](./README.md#-skill-categories)&nbsp;
  7. [![](https://img.shields.io/badge/6_Categories-8b5cf6?style=for-the-badge)](./README.md#-skill-categories)&nbsp;
  8. [![](https://img.shields.io/badge/Zero_Setup-22c55e?style=for-the-badge)](./README.md#-quick-start)&nbsp;
  9. [![](https://img.shields.io/badge/Any_Industry-f59e0b?style=for-the-badge)](./README.md#why-these-skills-are-different)
  10. </div>
  11. ---
  12. ## What's in this repo?
  13. 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.
  14. ---
  15. ## 🗺️ Skill Map
  16. ![Data Analytics Skill Map](./skill-map.svg)
  17. > [Open interactive version on Excalidraw](https://excalidraw.com/#json=wWcmLjEVHAYl4I4fynPSm,d8UC4Lexp2iSy5OPfIyJPQ)
  18. ---
  19. ## Why these skills are different
  20. > [!NOTE]
  21. > Traditional AI assistants require extensive upfront configuration — schemas, metric definitions, business rules — before they're useful. **These skills work on-demand.**
  22. | Traditional approach | These skills |
  23. |---------------------|--------------|
  24. | Needs prep before use | Zero setup required |
  25. | Breaks when business rules change | Adapts naturally |
  26. | Company-specific, hard to share | Portable across any org |
  27. | Silent on assumptions | Teaches you what context matters |
  28. Each skill asks targeted questions to gather exactly what it needs, then executes a complete, structured workflow.
  29. ---
  30. ## 📚 Skill Categories
  31. <details>
  32. <summary><b>🔍 01 &nbsp;·&nbsp; Data Quality & Validation</b> &nbsp;&nbsp; <code>3 skills</code></summary>
  33. <br>
  34. *Foundation — start here whenever you're working with new data.*
  35. | Skill | What it does |
  36. |-------|-------------|
  37. | **[programmatic-eda](01-data-quality-validation/programmatic-eda/)** | Systematic exploratory data analysis with automated sanity checks |
  38. | **[data-quality-audit](01-data-quality-validation/data-quality-audit/)** | Comprehensive quality assessment against business rules and schema |
  39. | **[query-validation](01-data-quality-validation/query-validation/)** | SQL review for correctness, performance, and edge cases |
  40. </details>
  41. <details>
  42. <summary><b>📝 02 &nbsp;·&nbsp; Documentation & Knowledge</b> &nbsp;&nbsp; <code>7 skills</code></summary>
  43. <br>
  44. *Build reusable context so you never explain the same thing twice.*
  45. | Skill | What it does |
  46. |-------|-------------|
  47. | **[semantic-model-builder](02-documentation-knowledge/semantic-model-builder/)** | Create a shared semantic layer for key metrics and dimensions |
  48. | **[analysis-documentation](02-documentation-knowledge/analysis-documentation/)** | Document findings with reproducible methodology |
  49. | **[data-catalog-entry](02-documentation-knowledge/data-catalog-entry/)** | Standardized metadata and descriptions for data assets |
  50. | **[sql-to-business-logic](02-documentation-knowledge/sql-to-business-logic/)** | Translate complex SQL into plain business language |
  51. | **[analysis-assumptions-log](02-documentation-knowledge/analysis-assumptions-log/)** | Track every assumption and decision in an analysis |
  52. | **[metric-reconciliation](02-documentation-knowledge/metric-reconciliation/)** | Trace and resolve discrepancies when metric sources disagree |
  53. | **[schema-mapper](02-documentation-knowledge/schema-mapper/)** | Column-level mapping between source and target schemas |
  54. </details>
  55. <details>
  56. <summary><b>📊 03 &nbsp;·&nbsp; Data Analysis & Investigation</b> &nbsp;&nbsp; <code>7 skills</code></summary>
  57. <br>
  58. *Core workflows for the analytical heavy lifting.*
  59. | Skill | What it does |
  60. |-------|-------------|
  61. | **[cohort-analysis](03-data-analysis-investigation/cohort-analysis/)** | Time-based cohort tracking with retention curves |
  62. | **[segmentation-analysis](03-data-analysis-investigation/segmentation-analysis/)** | Customer/user segmentation with actionable profiles |
  63. | **[funnel-analysis](03-data-analysis-investigation/funnel-analysis/)** | Conversion funnel with drop-off root-cause |
  64. | **[time-series-analysis](03-data-analysis-investigation/time-series-analysis/)** | Trend detection, seasonality, and forecasting |
  65. | **[root-cause-investigation](03-data-analysis-investigation/root-cause-investigation/)** | Structured diagnosis of unexpected metric changes |
  66. | **[ab-test-analysis](03-data-analysis-investigation/ab-test-analysis/)** | Rigorous experiment analysis with significance testing |
  67. | **[business-metrics-calculator](03-data-analysis-investigation/business-metrics-calculator/)** | Standard business metric calculation with benchmarks |
  68. </details>
  69. <details>
  70. <summary><b>🎨 04 &nbsp;·&nbsp; Data Storytelling & Visualization</b> &nbsp;&nbsp; <code>5 skills</code></summary>
  71. <br>
  72. *Turn raw findings into insights that drive decisions.*
  73. | Skill | What it does |
  74. |-------|-------------|
  75. | **[insight-synthesis](04-data-storytelling-visualization/insight-synthesis/)** | Structure analysis outputs into clear business insights |
  76. | **[visualization-builder](04-data-storytelling-visualization/visualization-builder/)** | Chart type selection, design guidance, and spec generation |
  77. | **[executive-summary-generator](04-data-storytelling-visualization/executive-summary-generator/)** | Concise executive-ready summaries of complex analysis |
  78. | **[dashboard-specification](04-data-storytelling-visualization/dashboard-specification/)** | Full dashboard requirements with metrics and layout |
  79. | **[data-narrative-builder](04-data-storytelling-visualization/data-narrative-builder/)** | Craft a compelling story arc from analytical findings |
  80. </details>
  81. <details>
  82. <summary><b>🤝 05 &nbsp;·&nbsp; Stakeholder Communication</b> &nbsp;&nbsp; <code>5 skills</code></summary>
  83. <br>
  84. *Bridge the gap between technical depth and business understanding.*
  85. | Skill | What it does |
  86. |-------|-------------|
  87. | **[technical-to-business-translator](05-stakeholder-communication/technical-to-business-translator/)** | Reframe technical findings for a business audience |
  88. | **[stakeholder-requirements-gathering](05-stakeholder-communication/stakeholder-requirements-gathering/)** | Structured elicitation to clarify what stakeholders actually need |
  89. | **[analysis-qa-checklist](05-stakeholder-communication/analysis-qa-checklist/)** | Pre-delivery quality gate before sharing results |
  90. | **[methodology-explainer](05-stakeholder-communication/methodology-explainer/)** | Explain analysis approach to any audience level |
  91. | **[impact-quantification](05-stakeholder-communication/impact-quantification/)** | Estimate and frame the business impact of findings |
  92. </details>
  93. <details>
  94. <summary><b>⚙️ 06 &nbsp;·&nbsp; Workflow Optimization</b> &nbsp;&nbsp; <code>4 skills</code></summary>
  95. <br>
  96. *Work smarter across every project.*
  97. | Skill | What it does |
  98. |-------|-------------|
  99. | **[analysis-planning](06-workflow-optimization/analysis-planning/)** | Structure the approach before diving in |
  100. | **[context-packager](06-workflow-optimization/context-packager/)** | Package context efficiently for AI-assisted analysis |
  101. | **[peer-review-template](06-workflow-optimization/peer-review-template/)** | Structured peer review checklist for analytical work |
  102. | **[analysis-retrospective](06-workflow-optimization/analysis-retrospective/)** | Post-analysis learning and process improvement |
  103. </details>
  104. ---
  105. ## 📐 Also by the maintainer
  106. **[Caliboard](https://caliboard.pro/)** — 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.
  107. ---
  108. <div align="center">
  109. **Version:** 1.2.0 &nbsp;·&nbsp; **Maintainer:** Nimrod Fisher &nbsp;·&nbsp; **Last Updated:** September 2026
  110. ## 🚀 Quick Start
  111. ### Install
  112. 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:
  113. ```bash
  114. git clone https://github.com/nimrodfisher/data-analytics-skills.git
  115. ```
  116. **Claude Code:** personal skills (all projects) go in `~/.claude/skills/`, project skills in `.claude/skills/` inside your project:
  117. ```bash
  118. cp -r 01-data-quality-validation/programmatic-eda ~/.claude/skills/
  119. ```
  120. **Codex:** user skills (all repos) go in `~/.agents/skills/`, repo skills in `.agents/skills/` at the repository root:
  121. ```bash
  122. cp -r 01-data-quality-validation/programmatic-eda ~/.agents/skills/
  123. ```
  124. New here? [QUICKSTART.md](./QUICKSTART.md) walks you through your first skill in 5 minutes, and [STRUCTURE.md](./STRUCTURE.md) explains how every skill is packaged.
  125. > [!TIP]
  126. > Describe your task to Claude or Codex naturally — it will select and activate the right skill automatically. No slash commands needed.
  127. **Example:**
  128. ```
  129. You: "I need to understand why our activation rate dropped 12% last week"
  130. Agent: [activates root-cause-investigation, asks for metric data and context]
  131. You: [provides data and business context]
  132. Agent: [runs structured investigation with hypothesis testing]
  133. ```
  134. ### Which skill to start with?
  135. | You need to... | Start here |
  136. |---------------|-----------|
  137. | Explore an unfamiliar dataset | `programmatic-eda` → `data-quality-audit` |
  138. | Write or review SQL | `query-validation` + `schema-mapper` |
  139. | Understand a metric drop/spike | `root-cause-investigation` |
  140. | Analyze experiment results | `ab-test-analysis` |
  141. | Build a dashboard | `dashboard-specification` + `visualization-builder` |
  142. | Present to leadership | `executive-summary-generator` + `insight-synthesis` |
  143. | Document your methodology | `analysis-documentation` + `analysis-assumptions-log` |
  144. | Start a complex analysis | `analysis-planning` first, always |
  145. ---
  146. ## 📖 How skills work
  147. Each skill follows the same **on-demand context pattern**:
  148. 1. **Request minimum viable context** — your agent asks only what's essential to start
  149. 2. **Execute the workflow** — structured, step-by-step analytical process
  150. 3. **Surface assumptions** — anything uncertain is flagged, not silently assumed
  151. 4. **Deliver a consistent output** — templated result you can share or iterate on
  152. > [!NOTE]
  153. > Skills degrade gracefully: if you can't provide everything, your agent states what it's assuming and proceeds.
  154. ---
  155. ## 🛠️ Customization
  156. Skills work out-of-the-box. To make them company-specific, add a `references/` folder inside any skill with:
  157. ```
  158. skill-name/
  159. ├── SKILL.md
  160. └── references/
  161. ├── company-schema.md ← your table/column definitions
  162. ├── metric-definitions.md ← standard metric formulas
  163. └── business-rules.md ← thresholds, edge cases, etc.
  164. ```
  165. Your agent will pull this context automatically when the skill runs.
  166. ---
  167. ## 🎓 Suggested ramp-up
  168. **Week 1 — Get comfortable**
  169. - Run `programmatic-eda` on a familiar dataset
  170. - Practice providing context when your agent asks
  171. - Use `analysis-planning` at the start of your next project
  172. **Week 2–3 — Add your core toolkit**
  173. - Set up `semantic-model-builder` for your key metrics (saves time forever)
  174. - Add `query-validation` to your SQL workflow
  175. - Pick 2 analysis skills that match your domain
  176. **Week 4+ — Go advanced**
  177. - Chain 4–5 skills end-to-end on a full project
  178. - Add company-specific references to the skills you use most
  179. - Build team context documents for shared onboarding
  180. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.