Menu
Solve the user's task by writing Python; the harness runs it in an isolated sandbox and returns stdout.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Analyze data (e.g. an uploaded CSV/Excel) with pandas and produce a chart or report file, returned to the user as an attachment.
Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform. Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like multimodal inputs, tools, media generation, caching, batch prediction, and Live API.
Manages datasets, tables, and jobs in BigQuery, and integrates with BigQuery ML and Gemini for advanced data analytics and AI-driven insights. Use when you need to interact with BigQuery, run SQL queries, manage BigQuery resources, or leverage BigQuery's built-in ML capabilities. Also use when performing data analysis, ingesting data into BigQuery, or developing AI applications on BigQuery.
Echo the user input back verbatim
Compute the prime factorization of an integer by executing Python in the sandbox
Reverse the user input string
Based on SOC occupation classification
| name | python-runner |
| description | Solve the user's task by writing Python; the harness runs it in an isolated sandbox and returns stdout. |
When the user asks for a computation or transformation:
run_code tool with that script as code.Constraints (the sandbox enforces these structurally):
print() its text result — stdout is returned.open("data.csv")). Never hardcode or reconstruct
a file's contents from memory — if a file you need isn't in the working directory, ask the user
to attach it rather than inventing the data.