Router logo

Router

Organization
lubusIN
router

Route to the appropriate Frappe skill based on task type. Use as the entry point when working on Frappe projects to determine which specialized skill to apply.

Overview

PublisherlubusIN
Repositoryfrappe-skills
Skill namerouter
Stars
62
Forks
23
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the 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.
  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/lubusIN/frappe-skills.git /tmp/frappe-skills
mkdir -p .claude/skills
cp -r /tmp/frappe-skills/router .claude/skills/router
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 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 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 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.

Frappe Router

Route to the appropriate Frappe skill based on your task.

When to use

  • First step when starting any Frappe-related work
  • To determine which specialized skill applies to your task

Procedure

0) Identify task type

TaskSkill
Understand project structure, versions, appsproject-triage
Scaffold new app, hooks, architecture, background jobsapp-development
Create/modify DocTypes, fields, controllersdoctype-development
Build REST/RPC APIs, webhooks, integrationsapi-development
Customize Desk UI, form scripts, list views, JS APIdesk-customization
Build Vue 3 frontends with Frappe UI, portalsfrontend-development
UI/UX patterns from CRM/Helpdesk/HRMSui-patterns
Create print formats, email templates, Jinja, PDFsprinting-templates
Build reports (Builder, Query, Script)reports
Create public web forms for data collectionweb-forms
Write or run teststesting
Set up dev environment with Docker/FMfrappe-manager
Build CRM/Helpdesk/enterprise systemsenterprise-patterns

1) Run triage first (recommended)

Before deep work, run project-triage to understand:

  • Project type (bench/FM/standalone)
  • Frappe version
  • Installed apps
  • Available tooling

2) Combine skills as needed

Complex tasks may require multiple skills:

  • New app = app-development + doctype-development + api-development + testing
  • Feature with UI = doctype-development + desk-customization + api-development
  • Custom frontend = frontend-development + api-development
  • Document workflow = doctype-development + printing-templates + reports
  • Enterprise app = enterprise-patterns + doctype-development

Quick decision tree

Is this about understanding the project?
  → project-triage

Is this about creating a new app or app architecture?
  → app-development

Is this about data models or DocTypes?
  → doctype-development

Is this about APIs or external access?
  → api-development

Is this about Desk UI, form scripts, or client-side JS?
  → desk-customization

Is this about a Vue 3 frontend or portal?
  → frontend-development

Is this about UI/UX patterns or app design?
  → ui-patterns

Is this about print formats, PDFs, or Jinja templates?
  → printing-templates

Is this about reports or data analysis views?
  → reports

Is this about public web forms?
  → web-forms

Is this about testing?
  → testing

Is this about local dev environment?
  → frappe-manager

Is this a complex enterprise system?
  → enterprise-patterns

Guardrails

  • Always run triage first before making code changes to unknown projects
  • Check Frappe version before recommending features (API availability varies significantly between v13, v14, v15, v16)
  • Don't assume ERPNext - many projects use Frappe Framework without ERPNext
  • Verify site context - commands like bench migrate affect specific sites

Common Mistakes

MistakeWhy It FailsFix
Skipping project triageApplying wrong patterns for versionAlways run triage first
Using ERPNext-specific code in Frappe-only projectsModule not found errorsCheck installed apps first
Wrong skill for taskIncomplete implementationMatch task type to skill carefully
Ignoring version differencesDeprecated/missing APIsCheck version compatibility in skill references
Working on wrong siteChanges don't appearAlways specify --site flag
Using vanilla JS/jQuery for frontendsEcosystem mismatchUse Frappe UI (Vue 3) via frontend-development
Custom app shell for CRUD appsInconsistent UXFollow CRM/Helpdesk patterns via enterprise-patterns

Frequently asked questions

What does the Router AI skill do?

Route to the appropriate Frappe skill based on task type. Use as the entry point when working on Frappe projects to determine which specialized skill to apply.

Why use Router on TypingMind?

Because you install it once and use it with any model. 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 Router in TypingMind?

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

Which AI models can use 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 Router?

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

Is the Router AI skill free?

Yes. It is published on GitHub by lubusIN under the MIT 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 👇