phoebefu6

Phoebe Data Skills — Data skill for Claude Code

Data community

Data skills you can install, not just read.

How to install Phoebe Data Skills

This entry records only its repository, not the path inside it, so there is no exact command to give. Open phoebefu6/phoebe-data-skills and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Phoebe Data Skills does

Data skills you can install, not just read. Claude skills that run a full analysis on your own schema - 233,835 real rows, executed charts, flaws planted on purpose with an answer key, and a review pass that rewrites the code. by Phoebe Fu

Alternatives in Data

MCP Server Chart — 🤖 A visualization mcp & skills contains 25+ visual charts using @antvis 4k ★
Sprite Gen — Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame 763 ★
Query Token Info — Search tokens and fetch metadata, real-time market data, and K-Line candlestick charts by keyword or contract 483 ★

README

[![Open the live showcase](https://img.shields.io/badge/%E2%96%B6%20open%20the%20live%20showcase-1f6feb?style=for-the-badge)](https://phoebefu6.github.io/phoebe-data-skills/) [![Star this repo](https://img.shields.io/github/stars/phoebefu6/phoebe-data-skills?style=for-the-badge&label=star%20this%20repo&color=444444)](https://github.com/phoebefu6/phoebe-data-skills/stargazers)

▶︎ [Open the live showcase →](https://phoebefu6.github.io/phoebe-data-skills/)

Free and open. Every build links to its source.

Phoebe's Data Skills

**Data skills you can install, not just read.**

I'm [Phoebe Fu](https://github.com/phoebefu6). I build data and applied-AI skills that turn Claude into a working analyst - and I show the whole thing, end to end, on one complex industry case. Real code, real executed charts, real review. No toy datasets, no mockups.

🔗 See it in action

**[Open the showcase site →](https://phoebefu6.github.io/phoebe-data-skills/)** *(live once Pages is on)*

Watch `how-to-EDA` run a full exploratory analysis on Everrest, a fictional B2B2C retail platform - 233,835 rows, 12 chart types, six findings ranked by dollar impact. Every chart on the page came from a real run you can reproduce.

Why these are different

Most data tutorials show you `df.describe()` on the Titanic dataset. These skills work differently:

🧩 **Installable, not just readable.** Each skill is a Claude skill you install once. Hand Claude your own schema and business context; it runs the same steps on your data.

📊 **Real executed outputs only.** Every chart came from an actual run with a fixed seed. No mockups, no "illustrative" screenshots - re-run it and get identical results.

🎯 **A built-in answer key.** The sample data has problems planted on purpose - missing values, an outlier merchant, duplicate rows, hidden seasonality, a suspicious segment. Then the analysis is graded: did it catch everything we hid? (It caught all five,