How do I activate codeact?

Say phrases like 'use the codeact skill' to trigger activation. The system will then prepare Python tool options.

What happens after activation?

codeact discovers tools, generates appropriate Python code, and executes it using the ipybox execute_ipython_cell tool, storing results in variables.

Can I chain multiple tools with codeact?

Yes. Code is generated to pass outputs from one tool as inputs to subsequent tools, enabling complex workflows.

codeact

npx machina-cli add skill gradion-ai/ipybox/codeact --openclaw

Files (1)

SKILL.md

2.1 KB

Use Python tools to perform tasks.

You must use the execute_ipython_cell tool of the ipybox MCP server for executing Python code.

All operations must follow the tool usage restrictions and workflows defined below.

Tool Directories

The gentools/ and mcptools/ directories are in the working directory shown in your <env> block. All paths are relative to the working directory, NOT to this skill's base directory.

Tool Usage Restrictions

You are restricted to these tools only:

Python Tools

Functions in mcptools/<category>/<tool>.py (use run_parsed if defined, otherwise run)
Functions in gentools/<category>/<tool>/api.py

`ipybox` MCP Server Tools

execute_ipython_cell - Execute Python code
reset - Reset the IPython kernel

Claude Code Filesystem Tools

All filesystem tools for reading, writing files, and listing directories.

Workflow

1. Python Tool Selection

List available categories in gentools/ and mcptools/
List available tools in relevant categories
Read tool files to understand interfaces and parameters.

2. Python Tool Priority

Search gentools package first
If not found, search mcptools package
If no appropriate tool exists, generate custom code

3. Code Generation and Python Tool Chaining

Generate code that uses selected Python tools as argument for execute_ipython_cell.
Chain Python tools in the generated code if the structured output of one tool can be used as input for another tool.

4. Code Execution

Use the execute_ipython_cell for Python code execution
Print only required information, not intermediate results
Store intermediate results in variables

Output Parsers

When generating output parsers for Python tools in the mcptools package, see references/output-parsers.md.

Saving Code Actions

To save executed code as a reusable gentools tool, see references/saving-codeacts.md.

Source

git clone https://github.com/gradion-ai/ipybox/blob/main/plugin/skills/codeact/SKILL.mdView on GitHub

Overview

codeact enables generating and running Python code using specialized tools to act with Python capabilities. Activate it by explicitly asking to use the codeact skill. It integrates with ipybox to execute code cells and supports tool-driven automation.

How This Skill Works

codeact discovers available Python tools under gentools and mcptools, selects appropriate ones, and generates code that may chain tool outputs as inputs. The generated code is executed using execute_ipython_cell, with intermediate results stored in variables for traceability.

When to Use It

You want to perform a task using a Python tool (from gentools or mcptools) and get immediate results.
You need to chain the output of one tool as the input to another tool.
You require reproducible code execution in an IPython cell via the ipybox server.
You want to inspect tool interfaces by reading tool files before selecting a tool.
You explicitly request activation of the codeact skill with phrases like 'use the codeact skill'.

Quick Start

Step 1: Explicitly say 'use the codeact skill' to activate.
Step 2: Let the system list available gentools/mcptools and pick a tool.
Step 3: Review the generated code, then codeact executes it via execute_ipython_cell and returns results.

Best Practices

Explicitly activate the skill with phrases such as 'use the codeact skill' before proceeding.
List available gentools and mcptools tools to understand interfaces and parameters.
Generate modular, small code blocks and store results in clearly named variables.
Validate tool outputs and handle errors gracefully in the code you generate.
Chain tools thoughtfully, ensuring outputs are compatible inputs for the next step.

Example Use Cases

Generate a data transformation script using a mcptools data tool and print the summary.
Read a file with a Python tool and compute basic statistics in the same workflow.
Fetch data with one tool and pass the results to another tool for analysis.
Experiment with a small code snippet in an IPython cell and capture the result.
Create and save a reusable code snippet as a gentools tool for future use.

Frequently Asked Questions

Add this skill to your agents