interactor-agents
Create LLM-powered AI assistants with tools and data sources through Interactor. Use when building conversational AI, chatbots, tool-calling assistants, or agents that need to query databases and external APIs.
npx skills add majiayu000/claude-skill-registry --skill interactor-agents --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Build LLM-powered assistants that can have conversations, use tools, and access data sources.
How it works
- The skill guides how to create an Assistant, register Tools the assistant can call, and connect Data Sources for natural language queries.
- It provides a minimal example flow: Create an Assistant, Register Tools, Connect Data Sources, Create a Room, Send/Receive Messages, and Close Room.
- It includes curl-based commands to create an assistant, list or get assistants, update or delete, and to manage Rooms and Messages. It also describes how to configure and use tools (e.g., register a tool with a callback_url and parameters) and how tool invocations are communicated back via a callback.
- It documents real-time response options: Server-Sent Events (SSE), Webhooks, and Polling as a fallback, with code samples for streaming via SSE and browser fetch, plus an example webhook flow and a polling helper.
- It presents a Tools section with how to register a tool, including name, description, parameters, callback_url, and callback_secret, plus the structure of tool invocation requests.
When to use it
- Conversational AI: Building chat interfaces with AI assistants
- Tool-Calling Agents: Creating assistants that can invoke custom functions
- Data-Connected AI: Connecting AI to databases for natural language queries
- Customer Support Bots: Building support assistants with domain knowledge
- Internal Tools: Creating AI assistants for internal operations
What it can touch
- Tools are defined via API interactions (registering tools, callbacks) and webhook handling. The skill shows endpoints like https://core.interactor.com/api/v1/tools and payloads, including callback URLs and request bodies for tool execution, along with response examples.
Caveats
- Requires Interactor authentication configured (see interactor-auth skill).
- Requires understanding of prompts, tools, and context, plus a webhook endpoint for tool callbacks (optional for custom tools).
- The API surface may vary by Interactor version; some operations (DELETE endpoints, advanced pagination) may differ.
- Cursors for pagination expire after 24 hours; re-fetch from the beginning for long-running jobs.
- The real-time response methods (SSE, webhooks, polling) depend on deployment and version.
# Interactor AI Agents Skill Build LLM-powered assistants that can have conversations, use tools, and access your data sources. ## When to Use - **Conversational AI**: Building chat interfaces with AI assistants - **Tool-Calling Agents**: Creating assistants that can invoke custom functions - **Data-Connected AI**: Connecting AI to databases for natural language queries - **Customer Support Bots**: Building support assistants with domain knowledge - **Internal Tools**: Creating AI assistants for internal operations ## Prerequisites - Interactor authentication configured (see `interactor-auth` skill) - Understanding of LLM concepts (prompts, tools, context) - Webhook endpoint for tool callbacks (optional, for custom tools) - Database with network access from Interactor (optional, for data sources) - `jq` command-line tool (for bash examples) ## Overview The AI Agents system consists of: | Component | Description | |-----------|-------------| | **Assistants** | Configured AI agents with specific behaviors and capabilities | | **Rooms** | Chat sessions between users and assistants | | **Messages** | Individual messages in a conversation | | **Tools** | Custom functions that assistants
- When to Use
- Prerequisites
- Overview
- Quick Start
- Instructions
- Step 1: Create an Assistant
- Assistant Configuration Options
- List Assistants
- Get Assistant
- Update Assistant
- Delete Assistant
- Chat Rooms
- Create a Room
- List Rooms
Get your token first (see interactor-auth skill) export TOKEN="your_access_token_here" echo "Created assistant: $ASSISTANT_ID" echo "Created room: $ROOM_ID" curl -X POST https://core.interactor.com/api/v1/agents/rooms/$ROOM_ID/messages \ curl -X POST https://core.interactor.com/api/v1/agents/assistants \ curl https://core.interactor.com/api/v1/agents/assistants \ curl https://core.interactor.com/api/v1/agents/assistants/asst_abc \ curl -X PUT https://core.interactor.com/api/v1/agents/assistants/asst_abc \ curl -X DELETE https://core.interactor.com/api/v1/agents/assistants/asst_abc \
What does the interactor-agents skill do?
Create LLM-powered AI assistants with tools and data sources through Interactor. Use when building conversational AI, chatbots, tool-calling assistants, or agents that need to query databases and external APIs.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill interactor-agents --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.