Conversational — Testing skill for Claude Code
Spec a conversational UI — voice assistant, chatbot, AI chat (LLM), or live-agent chat.
How to install Conversational
Installs to ~/.claude/skills/sungjin9288-design-ai-conversational/SKILL.md
mkdir -p ~/.claude/skills/sungjin9288-design-ai-conversational && curl -fsSL https://raw.githubusercontent.com/sungjin9288/design-ai/HEAD/commands/conversational.md -o ~/.claude/skills/sungjin9288-design-ai-conversational/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Conversational does
description: Spec a conversational UI — voice assistant, chatbot, AI chat (LLM), or live-agent chat. Modality, persona, intents, flows, error recovery, accessibility; Korean conventions (Bixby / Clova / KakaoTalk channel) included.
You will produce a conversational UI spec for the surface described in `$ARGUMENTS`.
Input
Parse `$ARGUMENTS`. Expect:
- Surface (e.g., "customer support chatbot", "voice search feature", "AI onboarding chat", "Bixby Capsule for ride hailing", "KakaoTalk
Alternatives in Testing
- RocketSimApp — RocketSim — 30+ tools for Xcode's iOS Simulator 791 ★
- Spy — by spylang - Enforces strict coding conventions with comprehensive testing guidelines, multiple code compilati 678 ★
- Test After Change Diagnostics.V1 — If any program code changes, run unit-tests and follow up on the test-result (fix code if there is an error) 272 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Game UI
Spec game UI — HUD, menus, inventory, store, settings — across genres + platforms. Korean conventions (확률 표시,
Spatial
Spec a spatial / AR / VR / MR experience. Platform, anchoring, locomotion, UI elements, comfort, accessibility
Tpl
by KarpelesLab - Details Go project conventions with comprehensive error handling recommendations, table-drive
Lecture Mastery Tester
Interactive, conversational mastery test for a specific lecture. Tests whether the student has truly learned t
Grounded RAG
Data-agnostic, professionally oriented chatbot prototype demonstrated on the Spanish GeSIDA HIV guidelines. Im
Persona Acid Test
You are running the Persona Acid Test. This is not a general critique. You will review the design three times,
Related Agents
GPT Chat
Conducts a conversation with a GPT model (Codex) as a separate conversational partner—the thread persists betw
Omd Kr Writer
Korean blog / long-form writer with 6 voice presets (toss-tech-design, karrot-neighborly, brunch-maker-popular
Code Reviewer Voice
Rewrites code review comment bodies in plain, conversational voice. Preserves every citation, file path, line