From codeact-sandbox
Generates and executes Python code to perform tasks, using gentools and mcptools packages with ipybox MCP server. Useful for automating actions with Python tools.
How this skill is triggered — by the user, by Claude, or both
Slash command
/codeact-sandbox:codeactThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use Python tools to perform tasks.
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.
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.
You are restricted to these tools only:
mcptools/<category>/<tool>.py (use run_parsed if defined, otherwise run)gentools/<category>/<tool>/api.pyipybox MCP Server Toolsexecute_ipython_cell - Execute Python codereset - Reset the IPython kernelgentools/ and mcptools/gentools package firstmcptools packageexecute_ipython_cell.execute_ipython_cell for Python code executionWhen generating output parsers for Python tools in the mcptools package, see references/output-parsers.md.
To save executed code as a reusable gentools tool, see references/saving-codeacts.md.
npx claudepluginhub gradion-ai/ipybox --plugin codeact-defaultInvokes MCP tools via tool-executor for semantic code search, refactoring, AI research, image generation, and library docs when basic tools fall short.
Discovers Claude Code tool environment including native tools and MCP servers via scans, amplifies prompts with capabilities, and suggests non-binding tool compositions for 'what tools to use' or 'best approach' queries.
Design patterns for building autonomous coding agents, including agent loops, tool-calling APIs, permission systems, and human-in-the-loop workflows.