knods
Build and modify Knods visual AI workflows using either the OpenClaw Gateway polling protocol or the Knods headless flows API. Use for Knods polling payloads with fields like messageId/message/history, or for direct flow discovery/execution tasks like listing flows, reading input schemas, starting runs, polling status, cancelling runs, and retrieving outputs programmatically.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/alesys/knodsWhat This Skill Does
The Knods skill enables OpenClaw AI agents to interface directly with Knods visual AI canvases. By utilizing the OpenClaw Gateway polling protocol, the agent can translate natural language requests into complex visual workflows. The skill parses incoming payloads containing message history and context, allowing the agent to generate both conversational responses and machine-executable [KNODS_ACTION] blocks. These blocks allow the agent to instantiate, configure, and connect nodes on a visual canvas, turning an abstract idea into a functional, multi-step pipeline.
Installation
To integrate this skill, use the ClawHub installer. Ensure you have the OpenClaw environment initialized and run the following command in your terminal:
clawhub install openclaw/skills/skills/alesys/knods
This will provision the necessary bridge runtime and set up the persistent polling service required for real-time communication between your agent and the Knods visual canvas interface.
Use Cases
- Rapid Prototyping: Build complex AI chains (e.g., text-to-image to video-upscale) instantly by describing them to the agent.
- Workflow Automation: Create reusable visual workflows for content generation, research, or data processing without manual drag-and-drop.
- Dynamic Editing: Instruct the agent to modify existing nodes, update parameters, or restructure flow logic mid-conversation using simple follow-up prompts.
- Educational Visualization: Use the canvas to map out how different AI models interact, helping users visualize complex prompt engineering pipelines.
Example Prompts
- "Create a flow with a ChatGPT node connected to a FluxImage node to generate an illustration based on my prompt."
- "Add a text input to the current flow, route it through a Claude node for summarization, and send the result to the Output node."
- "Modify the existing workflow: change the image model to Gemini and ensure the final output is formatted as a JSON dictionary."
Tips & Limitations
- Keep nodes lean: Always build the smallest flow possible to satisfy the requirement to maintain performance and readability.
- Stability: Utilize stable ID naming conventions (e.g., node_1, node_2) to ensure the agent can reliably track and modify nodes in subsequent turns.
- Context is King: On the first interaction, ensure your agent provides node type availability so the flow generation adheres strictly to supported operations.
- Latency: The polling system works best with 1-2 second intervals; keep your action JSON compact to ensure the gateway processes responses without timing out.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-alesys-knods": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: external-api