data-analysis

Name: data-analysis
Author: MagicCube

489stars57forks

How to install data-analysis?

magiccube/agentara/data-analysis

$npx -y skills add MagicCube/agentara --skill data-analysis

Installs into the current project.

Summary

Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate statistics, create summaries, pivot tables, SQL queries, or any form of structured data exploration. Supports multi-sheet Excel workbooks, aggregation, filtering, joi

Files · 1

View on GitHub

SKILL.md

1	# Data Analysis Skill
2
3	## Overview
4
5	This skill analyzes user-uploaded Excel/CSV files using DuckDB — an in-process analytical SQL engine. It supports schema inspection, SQL-based querying, statistical summaries, and result export, all through a single Python script.
6
7	## Core Capabilities
8
9	- Inspect Excel/CSV file structure (sheets, columns, types, row counts)
10	- Execute arbitrary SQL queries against uploaded data
11	- Generate statistical summaries (mean, median, stddev, percentiles, nulls)
12	- Support multi-sheet Excel workbooks (each sheet becomes a table)
13	- Export query results to CSV, JSON, or Markdown
14	- Handle large files efficiently with DuckDB's columnar engine
15
16	## Workflow
17
18	### Step 1: Understand Requirements
19
20	When a user uploads data files and requests analysis, identify:
21
22	- File location: Path(s) to uploaded Excel/CSV files under `/mnt/user-data/uploads/`
23	- Analysis goal: What insights the user wants (summary, filtering, aggregation, comparison, etc.)
24	- Output format: How results should be presented (table, CSV export, JSON, etc.)
25	- You don't need to check the folder under `/mnt/user-data`
26
27	### Step 2: Inspect File Structure
28
29	First, inspect the uploaded file to understand its schema:
30
31	```bash
32	python /mnt/skills/public/data-analysis/scripts/analyze.py \
33	--files /mnt/user-data/uploads/data.xlsx \
34	--action inspect
35	```
36
37	This returns:
38	- Sheet names (for Excel) or filename (for CSV)
39	- Column names, data types, and non-null counts
40	- Row count per sheet/file
41	- Sample data (first 5 rows)
42
43	### Step 3: Perform Analysis
44
45	Based on the schema, construct SQL queries to answer the user's questions.
46
47	#### Run SQL Query
48
49	```bash
50	python /mnt/skills/public/data-analysis/scripts/analyze.py \
51	--files /mnt/user-data/uploads/data.xlsx \
52	--action query \
53	--sql "SELECT category, COUNT(*) as count, AVG(amount) as avg_amount FROM Sheet1 GROUP BY category ORDER BY count DESC"
54	```
55
56	#### Generate Statistical Summary
57
58	```bash
59	python /mnt/skills/public/data-analysis/scripts/analyze.py \
60	--files /mnt/user-data/uploads/data.xlsx \
61	--action summary \
62	--table Sheet1
63	```
64
65	This returns for each numeric column: count, mean, std, min, 25%, 50%, 75%, max, null_count.
66	For string columns: count, unique, top value, frequency, null_count.
67
68	#### Export Results
69
70	```bash
71	python /mnt/skills/public/data-analysis/scripts/analyze.py \
72	--files /mnt/user-data/uploads/data.xlsx \
73	--action query \
74	--sql "SELECT * FROM Sheet1 WHERE amount > 1000" \
75	--output-file /mnt/user-data/outputs/filtered-results.csv
76	```
77
78	Supported output formats (auto-detected from extension):
79	- `.csv` — Comma-separated values
80	- `.json` — JSON array of records
81	- `.md` — Markdown table
82
83	### Parameters
84
85	\| Parameter \| Required \| Description \|
86	\|-----------\|----------\|-------------\|
87	\| `--files` \| Yes \| Space-separated paths to Excel/CSV files \|
88	\| `--action` \| Yes \| One of: `inspect`, `query`, `summary` \|
89	\| `--sql` \| For `query` \| SQL query to execute \|
90	\| `--table` \| For `summary` \| Table/sheet name to summarize \|
91	\| `--output-file` \| No \| Path to export results (CSV/JSON/MD) \|
92
93	> [!NOTE]
94	> Do NOT read the Python file, just call it with the parameters.
95
96	## Table Naming Rules
97
98	- Excel files: Each sheet becomes a table named after the sheet (e.g., `Sheet1`, `Sales`, `Revenue`)
99	- CSV files: Table name is the filename without extension (e.g., `data.csv` → `data`)
100	- Multiple files: All tables from all files are available in the same query context, enabling cross-file joins
101	- Special characters: Sheet/file names with spaces or special characters are auto-sanitized (spaces → underscores). Use double quotes for names that start with numbers or contain special characters, e.g., `"2024_Sales"`
102
103	## Analysis Patterns
104
105	### Basic Exploration
106	```sql
107	-- Row count
108	SELECT COUNT(*) FROM Sheet1
109
110	-- Distinct values in a column
111	SELECT DISTINCT category FROM Sheet1
112
113	-- Value distribution
114	SELECT category, COUNT(*) as cnt FROM Sheet1 GROUP BY category ORDER BY cnt DESC
115
116	-- Date range
117	SELECT MIN(date_col), MAX(date_col) FROM Sheet1
118	```
119
120	### Aggregation & Grouping
121	```sql
122	-- Revenue by category and month
123	SELECT category, DATE_TRUNC('month', order_date) as month,
124	SUM(revenue) as total_revenue
125	FROM Sales
126	GROUP BY category, month
127	ORDER BY month, total_revenue DESC
128
129	-- Top 10 customers by spend
130	SELECT customer_name, SUM(amount) as total_spend
131	FROM Orders GROUP BY customer_name
132	ORDER BY total_spend DESC LIMIT 10
133	```
134
135	### Cross-file Joins
136	```sql
137	-- Join sales with customer info from different files
138	SELECT s.order_id, s.amount, c.customer_name, c.region
139	FROM sales s
140	JOIN customers c ON s.customer_id = c.id
141	W

People who liked this also viewed

6 picks

Type

data-analysis

489stars57forks

View on GitHub

How to install data-analysis?

magiccube/agentara/data-analysis

$npx -y skills add MagicCube/agentara --skill data-analysis

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Data Analysis Skill
2
3	## Overview
4
5	This skill analyzes user-uploaded Excel/CSV files using DuckDB — an in-process analytical SQL engine. It supports schema inspection, SQL-based querying, statistical summaries, and result export, all through a single Python script.
6
7	## Core Capabilities
8
9	- Inspect Excel/CSV file structure (sheets, columns, types, row counts)
10	- Execute arbitrary SQL queries against uploaded data
11	- Generate statistical summaries (mean, median, stddev, percentiles, nulls)
12	- Support multi-sheet Excel workbooks (each sheet becomes a table)
13	- Export query results to CSV, JSON, or Markdown
14	- Handle large files efficiently with DuckDB's columnar engine
15
16	## Workflow
17
18	### Step 1: Understand Requirements
19
20	When a user uploads data files and requests analysis, identify:
21
22	- File location: Path(s) to uploaded Excel/CSV files under `/mnt/user-data/uploads/`
23	- Analysis goal: What insights the user wants (summary, filtering, aggregation, comparison, etc.)
24	- Output format: How results should be presented (table, CSV export, JSON, etc.)
25	- You don't need to check the folder under `/mnt/user-data`
26
27	### Step 2: Inspect File Structure
28
29	First, inspect the uploaded file to understand its schema:
30
31	```bash
32	python /mnt/skills/public/data-analysis/scripts/analyze.py \
33	--files /mnt/user-data/uploads/data.xlsx \
34	--action inspect
35	```
36
37	This returns:
38	- Sheet names (for Excel) or filename (for CSV)
39	- Column names, data types, and non-null counts
40	- Row count per sheet/file
41	- Sample data (first 5 rows)
42
43	### Step 3: Perform Analysis
44
45	Based on the schema, construct SQL queries to answer the user's questions.
46
47	#### Run SQL Query
48
49	```bash
50	python /mnt/skills/public/data-analysis/scripts/analyze.py \
51	--files /mnt/user-data/uploads/data.xlsx \
52	--action query \
53	--sql "SELECT category, COUNT(*) as count, AVG(amount) as avg_amount FROM Sheet1 GROUP BY category ORDER BY count DESC"
54	```
55
56	#### Generate Statistical Summary
57
58	```bash
59	python /mnt/skills/public/data-analysis/scripts/analyze.py \
60	--files /mnt/user-data/uploads/data.xlsx \
61	--action summary \
62	--table Sheet1
63	```
64
65	This returns for each numeric column: count, mean, std, min, 25%, 50%, 75%, max, null_count.
66	For string columns: count, unique, top value, frequency, null_count.
67
68	#### Export Results
69
70	```bash
71	python /mnt/skills/public/data-analysis/scripts/analyze.py \
72	--files /mnt/user-data/uploads/data.xlsx \
73	--action query \
74	--sql "SELECT * FROM Sheet1 WHERE amount > 1000" \
75	--output-file /mnt/user-data/outputs/filtered-results.csv
76	```
77
78	Supported output formats (auto-detected from extension):
79	- `.csv` — Comma-separated values
80	- `.json` — JSON array of records
81	- `.md` — Markdown table
82
83	### Parameters
84
85	\| Parameter \| Required \| Description \|
86	\|-----------\|----------\|-------------\|
87	\| `--files` \| Yes \| Space-separated paths to Excel/CSV files \|
88	\| `--action` \| Yes \| One of: `inspect`, `query`, `summary` \|
89	\| `--sql` \| For `query` \| SQL query to execute \|
90	\| `--table` \| For `summary` \| Table/sheet name to summarize \|
91	\| `--output-file` \| No \| Path to export results (CSV/JSON/MD) \|
92
93	> [!NOTE]
94	> Do NOT read the Python file, just call it with the parameters.
95
96	## Table Naming Rules
97
98	- Excel files: Each sheet becomes a table named after the sheet (e.g., `Sheet1`, `Sales`, `Revenue`)
99	- CSV files: Table name is the filename without extension (e.g., `data.csv` → `data`)
100	- Multiple files: All tables from all files are available in the same query context, enabling cross-file joins
101	- Special characters: Sheet/file names with spaces or special characters are auto-sanitized (spaces → underscores). Use double quotes for names that start with numbers or contain special characters, e.g., `"2024_Sales"`
102
103	## Analysis Patterns
104
105	### Basic Exploration
106	```sql
107	-- Row count
108	SELECT COUNT(*) FROM Sheet1
109
110	-- Distinct values in a column
111	SELECT DISTINCT category FROM Sheet1
112
113	-- Value distribution
114	SELECT category, COUNT(*) as cnt FROM Sheet1 GROUP BY category ORDER BY cnt DESC
115
116	-- Date range
117	SELECT MIN(date_col), MAX(date_col) FROM Sheet1
118	```
119
120	### Aggregation & Grouping
121	```sql
122	-- Revenue by category and month
123	SELECT category, DATE_TRUNC('month', order_date) as month,
124	SUM(revenue) as total_revenue
125	FROM Sales
126	GROUP BY category, month
127	ORDER BY month, total_revenue DESC
128
129	-- Top 10 customers by spend
130	SELECT customer_name, SUM(amount) as total_spend
131	FROM Orders GROUP BY customer_name
132	ORDER BY total_spend DESC LIMIT 10
133	```
134
135	### Cross-file Joins
136	```sql
137	-- Join sales with customer info from different files
138	SELECT s.order_id, s.amount, c.customer_name, c.region
139	FROM sales s
140	JOIN customers c ON s.customer_id = c.id
141	W

People who liked this also viewed

6 picks

Type