Knowledge Router logo

Knowledge Router

Organization
runxhq
knowledge-router

Route one question or source event through a supplied knowledge catalog to validated source, owner, escalation, and follow-up skill references. Use for evidence discovery and ownership routing, not broad business-action fanout or answering the question itself.

Overview

Publisherrunxhq
Repositoryrunx
Skill nameknowledge-router
Stars
105
Forks
109
Bundled files
6
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by runxhq on GitHub. Read the source before you install it.

Installation

Install the Knowledge Router AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/runxhq/runx/tree/main/skills/knowledge-router
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/runxhq/runx.git /tmp/runx
mkdir -p .claude/skills
cp -r /tmp/runx/skills/knowledge-router .claude/skills/knowledge-router
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Knowledge Router in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Knowledge Router on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Knowledge Router is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Knowledge Router

Produce a validated retrieval and ownership route from a bounded source catalog. This skill decides where evidence should come from and who owns the answer; it does not answer the question or perform the follow-up operation.

knowledge-router resolves references inside an explicit knowledge catalog. Its deterministic validator rejects invented sources, owners, and skills.

Source catalog

Supply:

json
{
  "sources": [
    {"id": "auth-docs", "kind": "docs", "summary": "API authentication and key scopes"}
  ],
  "owners": [
    {"id": "security-team", "domains": ["authentication"]}
  ],
  "skills": [
    {"id": "research", "purpose": "Resolve a bounded source-backed question"}
  ]
}

Every selected reference must exist in the corresponding catalog collection. The route may return no follow-up skill when more context or manual review is the honest outcome.

Procedure

  1. Match the question or event to supplied source summaries and owner domains.
  2. Propose the smallest source set needed to resolve the question.
  3. Select an owner only when the catalog supports the ownership relationship.
  4. Select a follow-up skill only when its declared purpose matches the next job.
  5. Use manual_review for consequential legal, billing, security, privacy, or destructive decisions—not merely because the topic belongs to those teams.
  6. Validate every source, owner, and skill reference deterministically.
  7. Return needs_more_context when no supported route exists.

Output

  • route: domain, rationale, and validated source references.
  • source_matches: validated source references and matching signals.
  • owner_recommendation: validated owner reference, rationale, and escalation posture, or null.
  • next_skill: validated skill reference and rationale, or null.
  • verdict: routed, needs_more_context, manual_review, or the deterministic validator's refused result for an invented reference.
  • validation: catalog digest inputs, invalid-reference findings, and result.

Inputs

  • question (required): question, event, or thread summary to route.
  • available_sources (required): explicit sources, owners, and skills collections.
  • constraints (optional): allowed sources, sensitivity, excluded systems, or preferred owners. Constraints are not authority.

Agent task contracts

knowledge-router-propose

Route the question through only the supplied knowledge catalog. Return route_proposal with verdict, route, source_matches, owner_recommendation, and next_skill. Every selected source_id, owner_id, and skill must exactly match a supplied id. Choose the smallest useful source set. Use needs_more_context with no selected ids when the catalog cannot support a route. Use manual_review for consequential legal, billing, security, privacy, or destructive decisions, not merely because the topic belongs to those domains. Do not answer the question or perform the follow-up skill.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Knowledge Router AI skill do?

Route one question or source event through a supplied knowledge catalog to validated source, owner, escalation, and follow-up skill references. Use for evidence discovery and ownership routing, not broad business-action fanout or answering the question itself.

Why use Knowledge Router on TypingMind?

Because you install it once and use it with any model. Knowledge Router is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Knowledge Router in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/runxhq/runx/tree/main/skills/knowledge-router. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Knowledge Router?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Knowledge Router?

As many as you like. As long as a model supports skills, you can use Knowledge Router with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Knowledge Router AI skill free?

Yes. It is published on GitHub by runxhq under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇