Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Write avatars to ./nomi/avatars and document nomi/ as persistent state for Nomi info across sessions
What This Skill Does
Connects to the Nomi AI companion platform via a bundled Python CLI. Supports one-on-one chats and group rooms with multiple Nomis. Stores profiles, room notes, and conversation summaries locally between sessions.
Manages identity injection, room context setup, and per-Nomi reply elicitation in the correct order so conversations stay coherent without manual API calls.
When to use it
- Interviewing a Nomi companion with structured follow-up questions
- Running group conversations across multiple Nomis in a shared room
- Persisting Nomi profiles and session notes between agent runs
- Conducting orientation drills with formatted, comparable Nomi responses
- Fetching Nomi avatars and profile details for reference
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Run a 3-question interview with my Nomi companion about their daily routine
- 1Run `nomi.py list` to find the target Nomi UUID
- 2Send identity and task intro as the first message to establish context
- 3Ask the primary question about daily routine
- 4Send two follow-up questions referencing the Nomi's actual answers
- 5Return the full transcript in Q: / A: format without paraphrasing
A complete interview transcript covering the initial question and two follow-ups
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.