AI Spreadsheet Analyzer — Agent Skill
AI Spreadsheet Analyzer — Agent Skill
Analyze CSV data and extract insights using the AI Pass API. This skill accepts raw CSV data plus a question, and returns structured analysis including summaries, trends, comparisons, and actionable recommendations.
What This Skill Does
- Accepts CSV data + natural language question
- Returns analysis: summaries, trends, comparisons, anomalies
- Handles diverse data types: sales, marketing, operations, finance
Prerequisites
- Create an AI Pass account at aipass.one
- Get your API key from Developer Dashboard
- Set
AIPASS_API_KEYenvironment variable
Usage
CSV_DATA="date,product,revenue
2025-01,Widget A,12500
2025-01,Widget B,8300
2025-02,Widget A,14200"
curl -X POST "https://aipass.one/apikey/v1/chat/completions" \
-H "Authorization: Bearer $AIPASS_API_KEY" \
-H "Content-Type: application/json" \
-d "{
\"model\": \"gpt-5-mini\",
\"temperature\": 1,
\"max_tokens\": 2000,
\"messages\": [
{
\"role\": \"system\",
\"content\": \"You are a data analyst. Analyze the provided CSV data and answer the question clearly. Use bullet points or tables for readability.\",
},
{
\"role\": \"user\",
\"content\": \"Data:\\n$CSV_DATA\\n\\nQuestion: Which product has higher revenue and what is the trend?\"
}
]
}"
Response: choices[0].message.content
Notes
- Truncate large datasets to ~8000 characters before sending
- Include column headers in the CSV for better analysis
- Ask specific questions for sharper outputs
Live App
Skill File
name: spreadsheet-analyzer
description: Analyze CSV data and extract insights using AI Pass. Answers questions about trends, summaries, comparisons, and anomalies in tabular data.
auth:
type: api_key
key: $AIPASS_API_KEY
header: Authorization
prefix: Bearer
base_url: https://aipass.one/apikey/v1
usage_instructions: |
Use this skill to analyze CSV/spreadsheet data. Provide the raw CSV data (headers + rows) and a specific question.
Limit data to ~8000 characters. Include column headers. Ask specific questions for better output.
Response at choices[0].message.content.
examples:
- prompt: "Data: [CSV here]. Question: Which product has the highest revenue?"
- prompt: "Data: [CSV here]. Question: Identify trends and anomalies in this dataset."
endpoints:
analyze_data:
method: POST
path: /chat/completions
body:
model: gpt-5-mini
temperature: 1
max_tokens: 2000
messages:
- role: system
content: You are a data analyst. Analyze the provided CSV data and answer the question clearly. Use bullet points or tables for readability. Provide specific values and actionable insights.
- role: user
content: "Data:\n{{csv_data}}\n\nQuestion: {{question}}"
response_path: choices[0].message.content