Slash Command

/design-conversation

Designs a complete human-AI conversation flow for a feature, producing a design document with flow diagram, initiative map, modality specs, repair protocol, disclosure plan, and 3 transcripts.

design

ai-ml

npx claudepluginhub owl-listener/ai-design-skills --plugin model-interaction-design

Details

Argument[feature or task description]

Prompt Preview

You are designing a human-AI conversation flow. Use only skills from the model-interaction-design plugin.
Follow this process:
## Step 1: Understand the Task
Using **conversation-patterns**, identify:
- What is the user trying to accomplish?
- What information does the AI need from the user?
- What information does the user need from the AI?
- What's the expected conversation length (2 turns or 20)?
## Step 2: Choose the Dialogue Structure
Using **conversation-patterns**, select the appropriate structure:
- Interview, co-creation, instruction-execution, exploration, or guided workflow
- Jus...

Command Content

Other plugins with /design-conversation

/design-prompt

Generates a complete system prompt package for an AI feature or product, including structured prompt, constraints, examples, rationale, context spec, and test cases.

prompt-architecture

/design-workflow

Designs a complete multi-agent workflow for a user goal or task, producing overview diagram, task decomposition, agent roles, handoffs, state management, interventions, recovery, and observability plan.

design-agent-orchestration

/design-chatbot

247

Designs complete chatbot UI spec covering persona, dialog flows, messages, quick replies, typing indicators, errors, and accessibility. Accepts type, platform, and persona args.

3 tools

naksha

/brainstorm

Explores user workflows using role templates to design agent systems by invoking the rcc:brainstorming-workflows skill.

rcc

/brainstorming

313

Explores requirements and design options before implementing features, components, functionality, or behavior changes.

opus

orchestrator-supaconductor

/brainstorm

Activates interactive Socratic brainstorming skill to refine ideas into detailed designs via guided session.

cipherpowers

Stats

Parent Repo Stars18

Parent Repo Forks3

Last CommitApr 25, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

You are designing a human-AI conversation flow. Use only skills from the model-interaction-design plugin. Follow this process: ## Step 1: Understand the Task Using **conversation-patterns**, identify: - What is the user trying to accomplish? - What information does the AI need from the user? - What information does the user need from the AI? - What's the expected conversation length (2 turns or 20)? ## Step 2: Choose the Dialogue Structure Using **conversation-patterns**, select the appropriate structure: - Interview, co-creation, instruction-execution, exploration, or guided workflow - Jus...

You are designing a human-AI conversation flow. Use only skills from the model-interaction-design plugin. Follow this process:

Step 1: Understand the Task

Using conversation-patterns, identify:

What is the user trying to accomplish?
What information does the AI need from the user?
What information does the user need from the AI?
What's the expected conversation length (2 turns or 20)?

Step 2: Choose the Dialogue Structure

Using conversation-patterns, select the appropriate structure:

Interview, co-creation, instruction-execution, exploration, or guided workflow
Justify why this structure fits the task

Step 3: Map Initiative

Using mixed-initiative-flow, define:

Who initiates the conversation?
Where does initiative shift from user to AI and back?
What triggers each handoff?
Create an initiative map showing control at each stage

Step 4: Design Modality

Using multimodal-orchestration, specify:

What modalities are used for input and output at each stage?
Where do cross-modal transitions happen?
What's the primary modality and what's supporting?

Step 5: Plan for Breakdown

Using conversation-patterns (repair sequences) and feedback-loops:

Design 3 repair sequences for likely misunderstandings
Define how the user corrects the AI mid-conversation
Specify grounding checkpoints

Step 6: Design Disclosure

Using progressive-disclosure:

What capabilities are revealed at conversation start?
What's revealed as the conversation progresses?
How does the AI teach the user what else it can do?

Output

Deliver a complete conversation design document:

Conversation flow diagram (text-based) showing all turns
Initiative map
Modality specification per stage
Repair protocol
Disclosure plan
3 example conversation transcripts (happy path, error recovery, edge case)