data-analyst
/data-analyst
Cleans, analyzes and visualizes data from CSV, Excel or JSON files and explains the findings in plain language. Use when the user shares a spreadsheet or dataset, asks for trends, charts, summaries, or wants to know what the numbers say.
- Author
- dev-shubh-madara ↗
- Repository
- madara-skillhub ↗
- Licence
- MIT
- Last repository change
- 09.11.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 09.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Cleans, analyzes and visualizes data from CSV, Excel or JSON files and explains the findings in plain language. Use when the user shares a spreadsheet or dataset, asks for trends, charts, summaries, or wants to know what the numbers say.
Original author description
Cleans, analyzes and visualizes data from CSV, Excel or JSON files and explains the findings in plain language. Use when the user shares a spreadsheet or dataset, asks for trends, charts, summaries, or wants to know what the numbers say.
How it works
- Before you start
- Workflow
- Quality bar
- Avoid
- Reference
- Self-check before replying
SKILL.md preview
--- name: data-analyst description: "Cleans, analyzes and visualizes data from CSV, Excel or JSON files and explains the findings in plain language. Use when the user shares a spreadsheet or dataset, asks for trends, charts, summaries, or wants to know what the numbers say." --- # Data analyst ## Before you start Ask what decision the data should help with. Look at the file before assuming anything: columns, types, row count, missing values. ## Workflow 1. **Inspect.** Shape, column types, missing values, duplicates, odd values. Report what you find in a few lines. 2. **Clean.** Fix types and dates, handle missing values in a stated way, remove exact duplicates. Keep the raw file untouched and write the cleaned copy next to it. List every change made. 3. **Question first.** Turn the user's goal into two or three specific questions, then compute the answers in code. Do not estimate numbers by eye or in prose. 4. **Analyze.** Summary statistics, group comparisons, trends over time, and outliers, as the questions need. 5. **Chart.** One chart per message: pick the chart that fits the data (line for time, bar for categories, scatter for relationships). Label axes with units and give each chart a title that states the finding. 6. **Explain.** Lead with the main result, then the supporting numbers, then limits: small samples, missing data, correlation not proving cause. 7. **Hand over** the cleaned data and the script, so the work can be repeated. ## Quality bar - Every number in the summary comes from code that ran. - Totals are cross-checked against the raw data. - Assumptions are written down. - The summary can be understood by someone who never opens the file. ## Avoid - Dropping rows silently. - Charts with truncated axes that exaggerate a small change. - Claiming causes the data cannot show. - Overwriting the user's original file. ## Reference Read `references/analysis-recipes.md` when inspecting, cleaning, choosing a chart, or writing the summary. It has the checklists, templates and worked examples for this skill. ## Self-check before replying Run through these before you send the answer. Fix anything that fails. - Did every number in my summary come from code that ran on this file? - Do totals after cleaning match the raw data, or is the gap explained? - Did I state each assumption (date format, how missing values were handled)? - Does any chart exaggerate with a truncated axis? - Am I claiming a cause the data cannot show? - If a fact could have changed since your training (versions, prices, rules, who holds a role), look it up or say it is unverified.
Files in this package (2)
- SKILL.md 3 KB
- references/analysis-recipes.md 2 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · dev-shubh-madara/madara-skillhub | 100 | MIT |
| jeremylongshore/tons-of-skills-marketplace | 100 | MIT |
| borghei/Claude-Skills | 100 | MIT |
| agentic-swe/agentic-swe | 100 | MIT |
| pranav8494/team-of-agents | 100 | MIT |
| charlieviettq/awesome-agent-skill | 100 | MIT |
| cline/skills | 100 | Apache-2.0 |
| Kuan-AI-com/agent-skills | 90 | MIT |
| ntygod/zhiwei | 86 | MIT |
Database snapshot: 13.11.2026 · package version 3f3ba016bc8f (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100excel-data-analyst
Analyze Excel, CSV, and business tables to support reliable decisions. Use when cleaning data, checking formulas or reconciliations, finding anomalies, building pivots or charts, and preparing reproducible management reports. - 98data-analysis
Analyze spreadsheet data, generate insights, and create visualizations. Use when a user asks to analyze data, explore a dataset, find trends, generate statistics, create charts from CSV or Excel data, summarize data, or answer questions about tabular data. - 98data-analysis
Loads CSV, Excel, and JSON data files, performs statistical analysis, and generates charts and reports. Use when the user asks to analyze a dataset, compute statistics, create visualizations, find trends, or produce a data report. - 100spreadsheet-ops
Spreadsheet processing and analysis for CSV/Excel; trigger when users ask to merge/clean tabular data, run statistics, add/edit Excel formulas, apply formatting, generate charts, or force workbook recalculation. - 100csv-data-analysis
This skill should be used when users need to analyze CSV or Excel files, understand data patterns, generate statistical summaries, or create data visualizations. Trigger keywords include "analyze CSV", "analyze Excel", "data analysis", "CSV analysis", "Excel analysis", "data… - 95data-analysis
Use this skill when analyzing structured datasets: load, clean, explore, visualize, and report on data from CSV, JSON, Excel, or SQL sources. Produces statistical summaries, correlation matrices, time series analysis, regression models, hypothesis tests, and publication-quality visualizations.