csv-data-summarizer-claude-skill_coffeefuelbump

Name: csv-data-summarizer-claude-skill_coffeefuelbump
Author: jackspace

15stars7forks

How to install csv-data-summarizer-claude-skill_coffeefuelbump?

jackspace/claudeskillz/csv-data-summarizer-claude-skill_coffeefuelbump

$npx -y skills add jackspace/ClaudeSkillz --skill csv-data-summarizer-claude-skill_coffeefuelbump

Installs into the current project.

Summary

Analyzes CSV files, generates summary stats, and plots quick visualizations using Python and pandas.

Files · 1

View on GitHub

SKILL.md

1	# CSV Data Summarizer
2
3	This Skill analyzes CSV files and provides comprehensive summaries with statistical insights and visualizations.
4
5	## When to Use This Skill
6
7	Claude should use this Skill whenever the user:
8	- Uploads or references a CSV file
9	- Asks to summarize, analyze, or visualize tabular data
10	- Requests insights from CSV data
11	- Wants to understand data structure and quality
12
13	## How It Works
14
15	## ⚠️ CRITICAL BEHAVIOR REQUIREMENT ⚠️
16
17	DO NOT ASK THE USER WHAT THEY WANT TO DO WITH THE DATA.
18	DO NOT OFFER OPTIONS OR CHOICES.
19	DO NOT SAY "What would you like me to help you with?"
20	DO NOT LIST POSSIBLE ANALYSES.
21
22	IMMEDIATELY AND AUTOMATICALLY:
23	1. Run the comprehensive analysis
24	2. Generate ALL relevant visualizations
25	3. Present complete results
26	4. NO questions, NO options, NO waiting for user input
27
28	THE USER WANTS A FULL ANALYSIS RIGHT AWAY - JUST DO IT.
29
30	### Automatic Analysis Steps:
31
32	The skill intelligently adapts to different data types and industries by inspecting the data first, then determining what analyses are most relevant.
33
34	1. Load and inspect the CSV file into pandas DataFrame
35	2. Identify data structure - column types, date columns, numeric columns, categories
36	3. Determine relevant analyses based on what's actually in the data:
37	- Sales/E-commerce data (order dates, revenue, products): Time-series trends, revenue analysis, product performance
38	- Customer data (demographics, segments, regions): Distribution analysis, segmentation, geographic patterns
39	- Financial data (transactions, amounts, dates): Trend analysis, statistical summaries, correlations
40	- Operational data (timestamps, metrics, status): Time-series, performance metrics, distributions
41	- Survey data (categorical responses, ratings): Frequency analysis, cross-tabulations, distributions
42	- Generic tabular data: Adapts based on column types found
43
44	4. Only create visualizations that make sense for the specific dataset:
45	- Time-series plots ONLY if date/timestamp columns exist
46	- Correlation heatmaps ONLY if multiple numeric columns exist
47	- Category distributions ONLY if categorical columns exist
48	- Histograms for numeric distributions when relevant
49
50	5. Generate comprehensive output automatically including:
51	- Data overview (rows, columns, types)
52	- Key statistics and metrics relevant to the data type
53	- Missing data analysis
54	- Multiple relevant visualizations (only those that apply)
55	- Actionable insights based on patterns found in THIS specific dataset
56
57	6. Present everything in one complete analysis - no follow-up questions
58
59	Example adaptations:
60	- Healthcare data with patient IDs → Focus on demographics, treatment patterns, temporal trends
61	- Inventory data with stock levels → Focus on quantity distributions, reorder patterns, SKU analysis
62	- Web analytics with timestamps → Focus on traffic patterns, conversion metrics, time-of-day analysis
63	- Survey responses → Focus on response distributions, demographic breakdowns, sentiment patterns
64
65	### Behavior Guidelines
66
67	✅ CORRECT APPROACH - SAY THIS:
68	- "I'll analyze this data comprehensively right now."
69	- "Here's the complete analysis with visualizations:"
70	- "I've identified this as [type] data and generated relevant insights:"
71	- Then IMMEDIATELY show the full analysis
72
73	✅ DO:
74	- Immediately run the analysis script
75	- Generate ALL relevant charts automatically
76	- Provide complete insights without being asked
77	- Be thorough and complete in first response
78	- Act decisively without asking permission
79
80	❌ NEVER SAY THESE PHRASES:
81	- "What would you like to do with this data?"
82	- "What would you like me to help you with?"
83	- "Here are some common options:"
84	- "Let me know what you'd like help with"
85	- "I can create a comprehensive analysis if you'd like!"
86	- Any sentence ending with "?" asking for user direction
87	- Any list of options or choices
88	- Any conditional "I can do X if you want"
89
90	❌ FORBIDDEN BEHAVIORS:
91	- Asking what the user wants
92	- Listing options for the user to choose from
93	- Waiting for user direction before analyzing
94	- Providing partial analysis that requires follow-up
95	- Describing what you COULD do instead of DOING it
96
97	### Usage
98
99	The Skill provides a Python function `summarize_csv(file_path)` that:
100	- Accepts a path to a CSV file
101	- Returns a comprehensive text summary with statistics
102	- Generates multiple visualizations automatically based on data structure
103
104	### Example Prompts
105
106	> "Here's `sales_data.csv`. Can you summarize this file?"
107
108	> "Analyze this customer data CSV and show me trends."
109
110	> "What insights can you find in `orders.csv`?"
111
112	### Example Output
113
114	Dataset Overview
115	- 5,000 rows × 8 columns
116	- 3 numeric columns

People who liked this also viewed

6 picks

Type

csv-data-summarizer-claude-skill_coffeefuelbump

15stars7forks

View on GitHub

How to install csv-data-summarizer-claude-skill_coffeefuelbump?

jackspace/claudeskillz/csv-data-summarizer-claude-skill_coffeefuelbump

$npx -y skills add jackspace/ClaudeSkillz --skill csv-data-summarizer-claude-skill_coffeefuelbump

Installs into the current project.

Summary

Analyzes CSV files, generates summary stats, and plots quick visualizations using Python and pandas.

Files · 1

View on GitHub

SKILL.md

1	# CSV Data Summarizer
2
3	This Skill analyzes CSV files and provides comprehensive summaries with statistical insights and visualizations.
4
5	## When to Use This Skill
6
7	Claude should use this Skill whenever the user:
8	- Uploads or references a CSV file
9	- Asks to summarize, analyze, or visualize tabular data
10	- Requests insights from CSV data
11	- Wants to understand data structure and quality
12
13	## How It Works
14
15	## ⚠️ CRITICAL BEHAVIOR REQUIREMENT ⚠️
16
17	DO NOT ASK THE USER WHAT THEY WANT TO DO WITH THE DATA.
18	DO NOT OFFER OPTIONS OR CHOICES.
19	DO NOT SAY "What would you like me to help you with?"
20	DO NOT LIST POSSIBLE ANALYSES.
21
22	IMMEDIATELY AND AUTOMATICALLY:
23	1. Run the comprehensive analysis
24	2. Generate ALL relevant visualizations
25	3. Present complete results
26	4. NO questions, NO options, NO waiting for user input
27
28	THE USER WANTS A FULL ANALYSIS RIGHT AWAY - JUST DO IT.
29
30	### Automatic Analysis Steps:
31
32	The skill intelligently adapts to different data types and industries by inspecting the data first, then determining what analyses are most relevant.
33
34	1. Load and inspect the CSV file into pandas DataFrame
35	2. Identify data structure - column types, date columns, numeric columns, categories
36	3. Determine relevant analyses based on what's actually in the data:
37	- Sales/E-commerce data (order dates, revenue, products): Time-series trends, revenue analysis, product performance
38	- Customer data (demographics, segments, regions): Distribution analysis, segmentation, geographic patterns
39	- Financial data (transactions, amounts, dates): Trend analysis, statistical summaries, correlations
40	- Operational data (timestamps, metrics, status): Time-series, performance metrics, distributions
41	- Survey data (categorical responses, ratings): Frequency analysis, cross-tabulations, distributions
42	- Generic tabular data: Adapts based on column types found
43
44	4. Only create visualizations that make sense for the specific dataset:
45	- Time-series plots ONLY if date/timestamp columns exist
46	- Correlation heatmaps ONLY if multiple numeric columns exist
47	- Category distributions ONLY if categorical columns exist
48	- Histograms for numeric distributions when relevant
49
50	5. Generate comprehensive output automatically including:
51	- Data overview (rows, columns, types)
52	- Key statistics and metrics relevant to the data type
53	- Missing data analysis
54	- Multiple relevant visualizations (only those that apply)
55	- Actionable insights based on patterns found in THIS specific dataset
56
57	6. Present everything in one complete analysis - no follow-up questions
58
59	Example adaptations:
60	- Healthcare data with patient IDs → Focus on demographics, treatment patterns, temporal trends
61	- Inventory data with stock levels → Focus on quantity distributions, reorder patterns, SKU analysis
62	- Web analytics with timestamps → Focus on traffic patterns, conversion metrics, time-of-day analysis
63	- Survey responses → Focus on response distributions, demographic breakdowns, sentiment patterns
64
65	### Behavior Guidelines
66
67	✅ CORRECT APPROACH - SAY THIS:
68	- "I'll analyze this data comprehensively right now."
69	- "Here's the complete analysis with visualizations:"
70	- "I've identified this as [type] data and generated relevant insights:"
71	- Then IMMEDIATELY show the full analysis
72
73	✅ DO:
74	- Immediately run the analysis script
75	- Generate ALL relevant charts automatically
76	- Provide complete insights without being asked
77	- Be thorough and complete in first response
78	- Act decisively without asking permission
79
80	❌ NEVER SAY THESE PHRASES:
81	- "What would you like to do with this data?"
82	- "What would you like me to help you with?"
83	- "Here are some common options:"
84	- "Let me know what you'd like help with"
85	- "I can create a comprehensive analysis if you'd like!"
86	- Any sentence ending with "?" asking for user direction
87	- Any list of options or choices
88	- Any conditional "I can do X if you want"
89
90	❌ FORBIDDEN BEHAVIORS:
91	- Asking what the user wants
92	- Listing options for the user to choose from
93	- Waiting for user direction before analyzing
94	- Providing partial analysis that requires follow-up
95	- Describing what you COULD do instead of DOING it
96
97	### Usage
98
99	The Skill provides a Python function `summarize_csv(file_path)` that:
100	- Accepts a path to a CSV file
101	- Returns a comprehensive text summary with statistics
102	- Generates multiple visualizations automatically based on data structure
103
104	### Example Prompts
105
106	> "Here's `sales_data.csv`. Can you summarize this file?"
107
108	> "Analyze this customer data CSV and show me trends."
109
110	> "What insights can you find in `orders.csv`?"
111
112	### Example Output
113
114	Dataset Overview
115	- 5,000 rows × 8 columns
116	- 3 numeric columns

People who liked this also viewed

6 picks

Type