G GnOuGo
gnougo-community/smartguide-brainstorming GnOuGo master mascot

smartguide-brainstorming

Official LAB Public

A GnOuGo Labs that turns business ideas into observable SmartGuide DSL knowledge.

smartguidebrainstormingknowledge-base
gnougo-community/smartguide-brainstorming/brainstorm-smartguide.gnougo-flow.yaml GnOuGo workflow mascot./brainstorm-smartguide.gnougo-flow.yaml
v0.1.0
version: 1
name: brainstorm-smartguide
skill:
  description: Turns a business idea and a method document into structured workshop options.
  tags: [brainstorming, documents, structured-output]
  inputs:
    idea: { type: string, required: true }
    methods_file: { type: string, required: false }
  outputs:
    workshop: { type: object }

workflows:
  main:
    inputs:
      idea: { type: string, required: true }
      methods_file:
        type: string
        required: false
        default: data/brainstorming-methods.md
      model:
        type: string
        required: false
        default: gpt-4o-mini
    steps:
      - id: discover_document_tools
        type: mcp.list
        input:
          servers: [GnOuGo.Document.Mcp]
          include: [tools]

      - id: read_methods
        type: mcp.call
        input:
          server: GnOuGo.Document.Mcp
          kind: tool
          method: document_read
          request:
            filePath: "${data.inputs.methods_file}"
            format: markdown

      - id: generate_options
        type: llm.call
        input:
          model: "${data.inputs.model}"
          temperature: 0.4
          prompt: |
            Design three complementary brainstorming exercises for this idea:
            ${data.inputs.idea}

            Use this method library as grounded context:
            ${json(data.steps.read_methods.response)}
          structured_output:
            schema_inline:
              type: object
              properties:
                title: { type: string }
                exercises:
                  type: array
                  items:
                    type: object
                    properties:
                      name: { type: string }
                      duration_minutes: { type: number }
                      instructions: { type: string }
                    required: [name, duration_minutes, instructions]
                    additionalProperties: false
              required: [title, exercises]
              additionalProperties: false
            strict: true

      - id: choose_format
        type: human.input
        input:
          mode: choice
          prompt: Choose the preferred workshop format.
          context: "${json(data.steps.generate_options.json)}"
          choices: [remote, in-person, hybrid]

    outputs:
      workshop: "${data.steps.generate_options.json}"
      selected_format: "${data.steps.choose_format.response}"
      document_tools: "${len(data.steps.discover_document_tools.tools)}"

Semantic view

Workflow graph

Semantically valid

Generated from the validated YAML with GnOuGo.Flow.Mermaid. Emit steps are hidden to keep the execution graph focused.

main

Entrypoint
flowchart TD n0_start(("Start")) n1_end(("End")) n2_inputs[/"Inputs: idea, methods_file, model"/] n3_discover_document_tools[("discover_document_tools - mcp.list")] n4_read_methods[("read_methods - mcp.call")] n5_generate_options>"generate_options - llm.call"] n6_choose_format[/"choose_format - human.input"\] n7_outputs[/"Outputs: document_tools, selected_format, workshop"/] n0_start --> n2_inputs n3_discover_document_tools --> n4_read_methods n4_read_methods --> n5_generate_options n5_generate_options --> n6_choose_format n2_inputs --> n3_discover_document_tools n6_choose_format --> n7_outputs n7_outputs --> n1_end