Workflow folder structure conventions for Output SDK. Use when creating new workflows, organizing workflow files, or understanding the standard project layout.
Provides Output SDK workflow folder structure conventions. Use when creating new workflows or reorganizing existing ones to ensure proper file placement and project layout compliance.
/plugin marketplace add growthxai/output-claude-plugins/plugin install growthxai-outputai-plugins-outputai@growthxai/output-claude-pluginsThis skill is limited to using the following tools:
This skill documents the standard folder structure for Output SDK workflows. Following these conventions ensures consistency across the codebase and enables proper tooling support.
src/workflows/{category}/{workflow-name}/
├── workflow.ts # Main workflow definition (default export)
├── steps.ts # Step function definitions (all I/O operations)
├── types.ts # Zod schemas and TypeScript types
├── utils.ts # Helper functions (optional)
├── prompts/ # LLM prompt files (optional)
│ └── {promptName}@v1.prompt
└── scenarios/ # Test input scenarios (optional)
└── {scenario_name}.json
workflow() function definitionRelated Skill: output-dev-workflow-function
step() function definitionsRelated Skill: output-dev-step-function
z from @output.ai/core (never from zod)Related Skill: output-dev-types-file
.prompt files for LLM operations{promptName}@v1.promptRelated Skill: output-dev-prompt-file
{scenario_name}.jsonRelated Skill: output-dev-scenario-file
Workflows are organized into category folders:
src/workflows/
├── content_utils/ # Content processing workflows
├── data_processing/ # Data transformation workflows
├── integrations/ # External service integrations
└── {custom_category}/ # Project-specific categories
snake_case for workflow folder namesimage_infographic_nano, resume_parsercamelCase for .ts files (except workflow.ts, steps.ts, types.ts)camelCase@v{n} for .prompt filessnake_case for .json scenario filesname property in workflow() should be camelCasecontentUtilsImageInfographicNanosrc/workflows/content_utils/image_infographic_nano/
├── workflow.ts # workflow({ name: 'contentUtilsImageInfographicNano', ... })
├── steps.ts # generateImageIdeas, generateImages, validateReferenceImages
├── types.ts # WorkflowInputSchema, WorkflowOutput, step schemas
├── utils.ts # normalizeReferenceImageUrls, buildS3Url, etc.
├── prompts/
│ └── generateImageIdeas@v1.prompt
└── scenarios/
├── test_input_complex.json
└── test_input_solar_panels.json
HTTP clients are shared across workflows and live in a central location:
src/clients/
├── gemini_client.ts # Google Gemini API client
├── jina_client.ts # Jina AI client
└── perplexity_client.ts # Perplexity API client
Import pattern in workflows:
import { GeminiImageService } from '#clients/gemini_client.js';
Related Skill: output-dev-http-client-create
When reviewing workflow structure, verify:
workflow.ts exists with default exportsteps.ts exists with all step definitionstypes.ts exists with Zod schemas.ts imports use .js extensionprompts/ folder exists if LLM operations are usedscenarios/ folder exists with at least one test inputsnake_case conventioncamelCase conventionoutput-dev-workflow-function - Writing workflow.ts filesoutput-dev-step-function - Writing step functionsoutput-dev-types-file - Creating Zod schemasoutput-dev-prompt-file - Creating prompt filesoutput-dev-scenario-file - Creating test scenariosoutput-dev-http-client-create - Creating shared HTTP clientsThis 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.