Guide for initializing and setting up new Keboola Python components using cookiecutter template. Use when starting a new component project from scratch.
/plugin marketplace add keboola/ai-kit/plugin install component-developer@keboola-claude-kitThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/initialization.mdThis skill helps you initialize and set up new Keboola Python components from scratch using the official cookiecutter template.
The fastest way to start a new component:
cookiecutter gh:keboola/cookiecutter-python-component
Then clean up and configure:
data/ directorydata/config.json with example parametersdata/ folder structure (not committed to git)For detailed step-by-step instructions, see:
The cookiecutter template creates:
src/ - Component Python codecomponent_config/ - Configuration schemas and descriptionstests/ - Test structure.github/workflows/ - CI/CD pipelinesDockerfile - Container definitionrequirements.txt - Python dependenciesdata/ - Local testing directory (with examples to remove)Once initialized, you'll typically want to:
@build-component skill)@build-component-ui skill)@test-component skill)After getting started:
@build-component skill@build-component-ui skill@test-component skill@debug-component skillThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.