brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Generate and execute code for acting with Python tools. Activate when user explicitly requests to "use the codeact skill" or similar phrases.
Claude Code
$ npx -y skills add gradion-ai/ipybox --skill codeact --agent claude-code
Codex
$ npx skills add gradion-ai/ipybox --skill codeact -a codex -y
Cursor
$ npx skills add gradion-ai/ipybox --skill codeact -a cursor -y
Gemini CLI
$ npx skills add gradion-ai/ipybox --skill codeact -a gemini-cli -y
GitHub Copilot
$ npx skills add gradion-ai/ipybox --skill codeact -a github-copilot -y
OpenCode
$ npx skills add gradion-ai/ipybox --skill codeact -a opencode -y
Windsurf
$ npx skills add gradion-ai/ipybox --skill codeact -a windsurf -y
name: codeact description: Generate and execute code for acting with Python tools. Activate when user explicitly requests to "use the codeact skill" or similar phrases.
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:
1. List available categories in `gentools/` and `mcptools/` 2. List available tools in relevant categories 3. Read tool files to understand interfaces and parameters.
1. Search `gentools` package first 2. If not found, search `mcptools` package 3. If no appropriate tool exists, generate custom code
When generating output parsers for Python tools in the `mcptools` package, see [references/output-parsers.md](references/output-parsers.md).
To save executed code as a reusable gentools tool, see [references/saving-codeacts.md](references/saving-codeacts.md).
mcp-name: io.github.gradion-ai/ipybox ipybox is a unified execution environment for Python code, shell commands, and programmatic MCP tool calls.
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.