Data Analysis Agent Skill

by HezaoHezao

Analyze Excel/CSV files with DuckDB SQL via bash.

997 tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

117

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/HezaoHezao/poirot --skill data-analysis

What it tells the agent to use

found in the instruction text

Bash runs shell commands — read the instruction before connecting

The instruction itself

14 sections, as written by the author

Data Analysis

Overview

Analyzes user-provided Excel (.xlsx/.xls) or CSV files using DuckDB — an

in-process analytical SQL engine. Supports schema inspection, SQL querying,

statistical summaries, and result export.

> Poirot note: The original deer-flow skill uses a bundled

> scripts/analyze.py helper. Poirot doesn't bundle that script, so this

> version uses bash with python3 + duckdb directly. Install duckdb first:

> pip install duckdb.

When to Use

User uploads Excel/CSV files and wants analysis
User wants statistics, summaries, pivot tables, or SQL queries on data
User wants to filter, join, or aggregate structured data

Prerequisites

# Install duckdb if not present
pip install duckdb openpyxl

Workflow

Step 1: Inspect File Structure

python3 -c "
import duckdb
con = duckdb.connect()
# For CSV
result = con.execute(\"DESCRIBE SELECT * FROM read_csv_auto('data.csv')\").fetchall()
for col in result:
    print(f'{col[0]:30s} {col[1]}')

# For Excel (each sheet = a table)
result = con.execute(\"SELECT * FROM st_read('data.xlsx', layer='Sheet1') LIMIT 0\").fetchall()

# Row count
count = con.execute(\"SELECT COUNT(*) FROM read_csv_auto('data.csv')\").fetchone()[0]
print(f'Rows: {count}')
"

Step 2: Statistical Summary

python3 -c "
import duckdb
con = duckdb.connect()
# Describe statistics
print(con.execute(\"SUMMARIZE SELECT * FROM read_csv_auto('data.csv')\").df().to_string())
"

Step 3: SQL Queries

python3 -c "
import duckdb
con = duckdb.connect()

# Aggregation
result = con.execute('''
    SELECT category, COUNT(*) as count, AVG(price) as avg_price
    FROM read_csv_auto('data.csv')
    GROUP BY category
    ORDER BY count DESC
''').fetchall()
for row in result:
    print(row)

# Join two files
result = con.execute('''
    SELECT a.id, a.name, b.amount
    FROM read_csv_auto('orders.csv') a
    JOIN read_csv_auto('payments.csv') b ON a.id = b.order_id
''').fetchall()
"

Step 4: Export Results

python3 -c "
import duckdb
con = duckdb.connect()
# Export to CSV
con.execute(\"COPY (SELECT * FROM read_csv_auto('data.csv') WHERE amount > 100) TO 'filtered.csv' (HEADER, DELIMITER ',')\")
# Export to JSON
con.execute(\"COPY (SELECT * FROM read_csv_auto('data.csv')) TO 'output.json' (FORMAT JSON)\")
"

Common Patterns

Pivot table

SELECT
    product,
    SUM(CASE WHEN month = 'Jan' THEN amount ELSE 0 END) AS jan,
    SUM(CASE WHEN month = 'Feb' THEN amount ELSE 0 END) AS feb,
    SUM(CASE WHEN month = 'Mar' THEN amount ELSE 0 END) AS mar
FROM read_csv_auto('sales.csv')
GROUP BY product

Percentiles

SELECT
    percentile_cont(0.5) WITHIN GROUP (ORDER BY price) AS median,
    percentile_cont(0.95) WITHIN GROUP (ORDER BY price) AS p95
FROM read_csv_auto('data.csv')

Multi-sheet Excel

python3 -c "
import duckdb
con = duckdb.connect()
# List sheets
sheets = con.execute(\"SELECT table_name FROM st_geometry_tables()\").fetchall()
# Query specific sheet
result = con.execute(\"SELECT * FROM st_read('data.xlsx', layer='Sheet2') LIMIT 10\").fetchall()
"

Pitfalls

DuckDB not installed: pip install duckdb openpyxl first
Large files: DuckDB handles large files well, but SUMMARIZE on very

large datasets may be slow. Sample first: SELECT * FROM ... TABLESAMPLE 10%

Encoding: CSV with non-UTF-8 encoding may fail. Specify encoding in

read_csv_auto options.

Date parsing: DuckDB auto-detects dates, but ambiguous formats may need

explicit strptime parsing.

Excel formulas: st_read reads cell values, not formula results. Use

openpyxl directly if you need computed values.

Other skills for the same job

different authors, same section of the catalogue

XLSX

by anthropics

vendor ×15

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.

Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.

MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment.

Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.

7k tokens

How to use it

Copy the folder

Take hezaohezao/data-analysis from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference pip. Without those the skill loads but fails at the first command.