data-analysis-skill — Claude Code skill: analysis, install
The data-analysis-skill skill reviews Excel and CSV data, runs parallel expert analysis, and builds interactive HTML reports with charts. It can export the report to PowerPoint when requested.
MIT 205 installs ★ 35 updated 2026-10-21
npx skills add podo/design-agent-skills --skill data-analysis-skill -a claude-codeWhat data-analysis-skill does
The skill handles Excel and CSV work such as business-metric reviews, ROI calculations, formula writing, and data visualization. For deeper questions, it assigns domain-expert roles to parallel subagents. Their findings are combined into one interactive HTML report with embedded charts.
A requested PowerPoint export converts the HTML report into slides. The runtime needs Python 3.8+ plus pandas, openpyxl, tabulate, and chardet; bundled scripts install missing packages through pip on first run. This skill is a poor fit for a single chart or a real-time streaming dashboard.
What it helps with
- analyze Excel and CSV files
- review business metrics and calculate ROI
- compare a dataset through several expert roles
- create an HTML report with charts
- turn an HTML report into PowerPoint slides
Example prompts for the agent
- Analyze this CSV, review its key metrics, and create an HTML report with charts.
- Run a parallel expert analysis of this dataset and combine the findings into one report.
- Export the finished HTML report to PowerPoint.
How to install data-analysis-skill
1Skills CLI (Vercel)
npx skills add podo/design-agent-skills --skill data-analysis-skill -a claude-code2Manually: put the files in place
~/.claude/skills/data-analysis-skill/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/data-analysis-skill/
1Skills CLI (Vercel)
npx skills add podo/design-agent-skills --skill data-analysis-skill -a codex2Manually: put the files in place
.agents/skills/data-analysis-skill/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add podo/design-agent-skills --skill data-analysis-skill -a cursor2Manually: put the files in place
.cursor/skills/data-analysis-skill/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install podo/design-agent-skills skills/data-analysis-skill2Manually: put the files in place
.github/skills/data-analysis-skill/SKILL.md1Skills CLI (Vercel)
npx skills add podo/design-agent-skills --skill data-analysis-skill -a gemini-cli2Platform CLI
gemini skills install https://github.com/podo/design-agent-skills --path skills/data-analysis-skillManually: put the files in place
.devin/skills/data-analysis-skill/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add podo/design-agent-skills --skill data-analysis-skill -a opencodeClaude.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-analysis-skill
How do I install data-analysis-skill in Claude Code?
Run npx skills add podo/design-agent-skills --skill data-analysis-skill -a claude-code, then check ~/.claude/skills/data-analysis-skill/SKILL.md.
What does data-analysis-skill do?
It works with Excel and CSV data, reviews metrics, calculates ROI, writes formulas, and creates visualizations. For deeper requests, it runs parallel expert subagents and combines their findings in an interactive HTML report.
What does data-analysis-skill require?
It needs Python 3.8+ with pandas, openpyxl, tabulate, and chardet. The bundled scripts can install missing packages with pip on the first run.
Source text
SKILL.md · MIT
--- name: data-analysis-skill description: | Multi-expert parallel analysis workflow that selects domain expert subagents to analyze datasets in parallel, synthesizes findings into interactive HTML reports with charts, and exports to PowerPoint on request. Requires Python packages: pandas, openpyxl, tabulate, chardet. triggers: - "data analysis skill" - "parallel data analysis" - "dongzhang84" - "data HTML report" - "data to PowerPoint" das: type: skill category: data-visualization upstream: "https://github.com/dongzhang84/data-analysis-skill" upstream_path: "SKILL.md" version: latest install: true --- # data-analysis-skill > Catalogue stub — full skill: [dongzhang84/data-analysis-skill](https://github.com/dongzhang84/data-analysis-skill) <!-- das:install:start — generated from stub.yaml by `npm run generate`; edit stub.yaml, not this block --> ## Decision tree 1. **Is the full skill already installed?** Upstream names this skill `data-analysis-pro`, so it installs next to this pointer (the pointer is not replaced). - Global: `f=~/.agents/skills/data-analysis-pro/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"` - Project: `f=.agents/skills/data-analysis-pro/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"` - `installed` → the skill is installed as `data-analysis-pro`, invoke it and proceed - `pointer` → go to step 2 2. **Detect scope, then install:** ```bash [ -e ~/.agents/skills/data-analysis-skill ] && echo "global" || echo "project" ``` **Global:** ```bash npx skills add dongzhang84/data-analysis-skill --skill data-analysis-pro -g -y ``` **Project:** ```bash npx skills add dongzhang84/data-analysis-skill --skill data-analysis-pro -y ``` > **Claude Code:** send a command as a chat message starting with `!` to run it without leaving the conversation. **Heads-up** - **Requires:** Python 3.8+ with pandas, openpyxl, tabulate and chardet (the bundled scripts auto-install missing packages with pip on first run) - **License:** MIT <!-- das:install:end --> ## Invoke after install - Skill name: `data-analysis-pro` - Trigger phrases: "data analysis skill", "parallel data analysis", "dongzhang84", "data HTML report", "data to PowerPoint" ## What it does End-to-end data analysis assistant for Excel/CSV analysis, business-metrics review, ROI calculation, formula writing, and data visualization. For deeper questions it runs a multi-expert analysis: it selects a panel of domain-expert roles, runs each as a parallel subagent so every expert analyses the dataset from a distinct angle, and synthesizes the results into a single interactive HTML report with embedded charts. PowerPoint export (HTML to PPTX) is available when the user asks for slides. Needs a Python environment with pandas, openpyxl, tabulate, and chardet; the bundled scripts install missing packages on first run. ## When NOT to use - Single-chart generation — use `d3js-skill`, `claud3` or `data-viz-agent` instead - Real-time streaming data dashboards - When Python dependencies cannot be installed in the environment
© podo · MIT · podo/design-agent-skills