Search

PythonReactSEOPDF
OpenClaw

knods

Build and modify Knods visual AI workflows using the OpenClaw Gateway polling protocol. Use when Knods sends polling payloads with fields like messageId/message/history and responses must be streamed back as delta chunks with optional [KNODS_ACTION] JSON blocks in assistant text. Includes a packaged bridge runtime and installer for persistent polling.

alesys0 source installs☆ 0 Repository stars

Installation

Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.

SkillHub CLI

skillhub install alesys/knods

Inspect the source and compatibility requirements, then follow its installation steps.

Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.

View source ↗Guides

Skill instructions

Knods

Overview

Handle Knods chat turns that request new flows or edits on a visual canvas. Parse Knods polling payload messages, generate assistant text, and include [KNODS_ACTION]...[/KNODS_ACTION] blocks when the canvas should change.

Workflow

  1. Parse incoming payload fields.
  • Treat message as the primary request.
  • Use history for continuity.
  • On first turn in a conversation, expect prepended context in message describing node types and action rules.
  • Use messageId to map all response chunks to the correct message.
  1. Choose whether to emit a canvas action block.
  • Use addNode for single-node additions.
  • Use addFlow for multi-node workflows or any request requiring edges.
  • If the user only asks a question, respond with normal text and no action block.
  1. Build strict action JSON.
  • Wrap each action exactly as:
    • [KNODS_ACTION]{"action":"addNode",...}[/KNODS_ACTION]
    • [KNODS_ACTION]{"action":"addFlow",...}[/KNODS_ACTION]
  • For addFlow, ensure every edge source and target references an existing node id.
  • Always end flows with an Output node.
  • Never connect two generator nodes directly; route through Output or through appropriate input/output structure.
  • Use stable node IDs (for example input_1, image_1, output_1) so follow-up edits are easy.
  • Avoid unknown keys in action JSON.
  1. Stream response back to Knods.
  • Send assistant text as delta chunks to /respond for the same messageId.
  • Send {"messageId":"...","done":true} when complete.
  • Keep first chunk quick to avoid timeout perception.

Output Rules

  • Return normal assistant text; do not wrap the full reply in a custom envelope.
  • Include [KNODS_ACTION]...[/KNODS_ACTION] inline only when a canvas mutation is intended.
  • Do not mention internal polling URLs/tokens in user-facing text.
  • Keep action JSON valid and compact.

Flow Design Heuristics

  • Build the smallest flow that satisfies the request.
  • Prefer node types listed in the fir...

Source information

Source
github
Repository
openclaw/skills
Path
skills/alesys/knods
Version
—
Commit
f4dcc79d2a26123f3dc79e8a22557d5359cd4105
Classification source
rules
Status
active
Visibility
public

These signals come from indexed source analysis and may lag behind changes. Check the current source files.

Extracted content

SKILL.md
# Knods

## Overview

Handle Knods chat turns that request new flows or edits on a visual canvas. Parse Knods polling payload messages, generate assistant text, and include `[KNODS_ACTION]...[/KNODS_ACTION]` blocks when the canvas should change.

## Workflow

1. Parse incoming payload fields.
- Treat `message` as the primary request.
- Use `history` for continuity.
- On first turn in a conversation, expect prepended context in `message` describing node types and action rules.
- Use `messageId` to map all response chunks to the correct message.

2. Choose whether to emit a canvas action block.
- Use `addNode` for single-node additions.
- Use `addFlow` for multi-node workflows or any request requiring edges.
- If the user only asks a question, respond with normal text and no action block.

3. Build strict action JSON.
- Wrap each action exactly as:
  - `[KNODS_ACTION]{"action":"addNode",...}[/KNODS_ACTION]`
  - `[KNODS_ACTION]{"action":"addFlow",...}[/KNODS_ACTION]`
- For `addFlow`, ensure every edge `source` and `target` references an existing node id.
- Always end flows with an `Output` node.
- Never connect two generator nodes directly; route through `Output` or through appropriate input/output structure.
- Use stable node IDs (for example `input_1`, `image_1`, `output_1`) so follow-up edits are easy.
- Avoid unknown keys in action JSON.

4. Stream response back to Knods.
- Send assistant text as delta chunks to `/respond` for the same `messageId`.
- Send `{"messageId":"...","done":true}` when complete.
- Keep first chunk quick to avoid timeout perception.

## Output Rules

- Return normal assistant text; do not wrap the full reply in a custom envelope.
- Include `[KNODS_ACTION]...[/KNODS_ACTION]` inline only when a canvas mutation is intended.
- Do not mention internal polling URLs/tokens in user-facing text.
- Keep action JSON valid and compact.

## Flow Design Heuristics

- Build the smallest flow that satisfies the request.
- Prefer node types listed in the fir...

Related skills

OpenClaw

geo-optimization

capt-marbles

Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discove...

OpenClaw

139mail

chang-tong

139邮箱邮件收发 Skill - 支持 IMAP/SMTP 协议,兼容139/QQ/163/Gmail等主流邮箱 功能: 1. 发送邮件(SMTP) 2. 接收邮件(IMAP) 3. 查看收件箱列表 4. 查看未读邮件 当用户提到 "发邮件"、"收邮件"、"查看邮件"、"邮箱"...