data-analyst · genspark-ai — Claude Code skill: what it does, how to install
data-analyst transforms raw tables into structured Excel workbooks featuring dynamic formulas, charts, and plain-language takeaways.
Apache-2.0 ★ 12,746 updated 2026-10-29
npx skills add genspark-ai/genoffice --skill data-analyst -a claude-codeWhat data-analyst does
This workflow instructs the coding assistant to operate like a business data analyst. It starts by reviewing pasted tables or file attachments, auditing row counts, field definitions, missing entries, duplicated records, and conflicting measurement units. If columns look ambiguous, the assistant pauses to clarify before running calculations.
Next, it generates an Excel workbook using environment spreadsheet tools. Sheet 1 isolates cleaned records alongside notes detailing excluded entries. Sheet 2 handles rollups: grouped aggregates, period-over-period shifts, year-over-year figures, and Top-N rankings, strictly using spreadsheet formulas rather than hardcoded totals. Numeric columns are right-aligned, headers receive bold styling, and line or bar charts visualize key metrics.
Closing replies summarize 3 to 5 clear takeaways pairing specific numbers with observations and suggested actions. When records lack enough evidence for a solid deduction, the skill mandates reporting "insufficient data" instead of inventing explanations.
What it helps with
- clean dirty tabular inputs with inconsistent units and blank cells
- generate Excel summaries using real formulas instead of typed totals
- plot line and bar charts for composition and trend metrics
- draft actionable business observations supported by exact figures
Example prompts for the agent
- Analyse this table and give me the key conclusions
- Turn this data into an analysis workbook with charts
- Review the attached sales export and prepare an Excel summary sheet
How to install data-analyst
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill data-analyst -a claude-code2Manually: put the files in place
~/.claude/skills/data-analyst/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/data-analyst/
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill data-analyst -a codex2Manually: put the files in place
.agents/skills/data-analyst/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill data-analyst -a cursor2Manually: put the files in place
.cursor/skills/data-analyst/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install genspark-ai/genoffice skills/recommended/data-analyst2Manually: put the files in place
.github/skills/data-analyst/SKILL.md1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill data-analyst -a gemini-cli2Platform CLI
gemini skills install https://github.com/genspark-ai/genoffice --path skills/recommended/data-analystManually: put the files in place
.devin/skills/data-analyst/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about data-analyst
How to install data-analyst in Claude Code?
Run npx skills add genspark-ai/genoffice --skill data-analyst -a claude-code in your terminal. This registers the configuration at ~/.claude/skills/data-analyst/SKILL.md.
What does data-analyst do?
It orchestrates a complete analytical pipeline, turning raw datasets into clean Excel workbooks with formulaic summaries, visual charts, and straightforward conclusions.
How does data-analyst prevent false inferences?
The workflow explicitly instructs the assistant to respond with "insufficient data" whenever existing records cannot mathematically back up an assumption.
Source text
SKILL.md · Apache-2.0
--- name: data-analyst description: Take raw data through cleaning, formulas and charts to plain-language conclusions, delivered as an Excel workbook category: data scenarios: Data cleaning | Chart visualisation | Business review quickPrompts: Analyse this table and give me the key conclusions | Turn this data into an analysis workbook with charts metadata: version: 1.0.0 --- You are a data analyst. The goal is for a non-technical user to come away with insights they can understand, not just a table. ## Workflow 1. Look at the data first: read the attachment or pasted data once through, confirm what each field means, the row count, and obvious dirty data (blanks / duplicates / inconsistent units). Ask about anything ambiguous before going on. 2. Build the workbook as an Excel workbook with the spreadsheet tools available here. - Sheet 1 holds the cleaned detail (units and date formats unified, with a note of what was excluded); - Sheet 2 holds the summary: grouped statistics, period-on-period and year-on-year comparisons and Top-N, all with formulas, never typed results; - Key metrics get charts (line for trends, bar / pie for composition); headers bold, number columns right-aligned. 3. Once the workbook is done, give 3-5 conclusions in the reply, each = observation + figure + likely explanation or recommendation. Do not restate the table. 4. Where the data cannot support a conclusion, say "insufficient data" rather than over-inferring.
© genspark-ai · Apache-2.0 · genspark-ai/genoffice
Similar skills
All skills for Data and databases →data-analyst by other authors comes first.