Doctype Development logo

Doctype Development

Organization
lubusIN
doctype-development

Create and modify Frappe DocTypes including schema design, controllers, child tables, and customization. Use when building data models, adding fields, or implementing document lifecycle logic.

Overview

PublisherlubusIN
Repositoryfrappe-skills
Skill namedoctype-development
Stars
62
Forks
23
Bundled files
8
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.

  • 8 bundled files

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

  • Open source

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

Installation

Install the Doctype Development 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/doctype-development .claude/skills/doctype-development
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Doctype Development 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 Doctype Development 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 Doctype Development 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 DocType Development

Build and modify DocTypes—the core data model abstraction in Frappe Framework.

When to use

  • Creating new DocTypes (standard, single, child table, submittable, tree)
  • Adding or modifying fields on existing DocTypes
  • Implementing controller logic (validate, before_save, on_submit, etc.)
  • Setting up naming series and auto-naming
  • Configuring permissions and workflows
  • Building child tables and parent-child relationships

Inputs required

  • Target app and module path
  • DocType name and type (standard/single/child/submittable/tree)
  • Field definitions (name, type, options)
  • Permission requirements by role
  • Whether workflow is needed

Procedure

0) Verify environment

bash
# Ensure developer mode is enabled
bench --site <site> console
>>> frappe.conf.developer_mode  # Must be True

1) Choose DocType type

TypeUse CaseKey Setting
StandardMultiple recordsDefault
SingleConfig/settings (one record)issingle: 1
Child TableRows in parent tableistable: 1
SubmittableDraft→Submit→Cancel workflowis_submittable: 1
TreeHierarchical datais_tree: 1
VirtualExternal data sourceis_virtual: 1

2) Create DocType

Option A: Via UI (recommended for new DocTypes)

  1. Navigate to DocType List → New
  2. Define fields, permissions, settings
  3. Save (exports to app in developer mode)

Option B: Via code

python
# Create DocType JSON in: 
# <app>/<module>/doctype/<doctype_name>/<doctype_name>.json

3) Define fields

Common field patterns:

json
{
  "fieldname": "customer",
  "fieldtype": "Link",
  "label": "Customer",
  "options": "Customer",
  "reqd": 1
}

See references/field-types.md for all field types.

4) Implement controller

Create <doctype_name>.py alongside the JSON:

python
import frappe
from frappe.model.document import Document

class MyDocType(Document):
    def validate(self):
        # Lightweight validation
        if not self.customer:
            frappe.throw("Customer is required")
    
    def before_save(self):
        # Pre-save normalization
        self.full_name = f"{self.first_name} {self.last_name}"
    
    def after_insert(self):
        # Post-create side effects
        frappe.publish_realtime("new_doc", {"name": self.name})

5) Set up naming

json
{
  "autoname": "naming_series:",
  "fields": [
    {
      "fieldname": "naming_series",
      "fieldtype": "Select",
      "options": "PRJ-.YYYY.-\nPRJ-.YYYY.-.###"
    }
  ]
}

Options: field:fieldname, naming_series:, hash, format:PREFIX-{####}

6) Configure permissions

Set in DocType → Permissions tab:

  • Role + Read/Write/Create/Delete/Submit/Cancel
  • User permissions for row-level filtering

7) Add workflow (if needed)

Create Workflow DocType linking to your DocType with states and transitions.

Verification

  • DocType appears in list and can create new records
  • All fields save correctly
  • Controller hooks fire (check logs)
  • Permissions enforced for each role
  • Naming series generates correctly
  • Run: bench --site <site> migrate succeeds

Failure modes / debugging

  • DocType not found: Check module path and app installation
  • Controller not loading: Verify class name matches DocType name (PascalCase)
  • Fields not saving: Check fieldtype and options compatibility
  • Permission denied: Verify role permissions and User Permissions

Escalation

References

Guardrails

  • Check developer_mode before schema changes: DocType modifications only export to files when developer_mode = 1 in site config
  • Verify naming series uniqueness: Ensure naming series prefixes don't conflict with existing DocTypes
  • Test child tables separately: Child tables have their own lifecycle; test them in isolation before parent integration
  • Always run migrate after changes: Schema changes require bench --site <site> migrate to apply
  • Validate fieldname conventions: Use snake_case, max 140 chars, no reserved SQL keywords

Common Mistakes

MistakeWhy It FailsFix
Missing reqd on mandatory fieldsUsers can save incomplete dataSet reqd: 1 on fields that must have values
Wrong fieldtype for dataData truncation or validation errorsMatch fieldtype to data (e.g., Currency for money, not Float)
Not running bench migrateSchema changes not applied to databaseAlways run bench --site <site> migrate after DocType changes
Circular Link dependenciesDocType creation failsUse Dynamic Link or restructure relationships
Controller class name mismatchController methods not calledClass name must be PascalCase of DocType name (e.g., SalesOrder for "Sales Order")
Missing in_list_view on key fieldsFields not visible in listSet in_list_view: 1 on important fields

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 Doctype Development AI skill do?

Create and modify Frappe DocTypes including schema design, controllers, child tables, and customization. Use when building data models, adding fields, or implementing document lifecycle logic.

Why use Doctype Development on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lubusIN/frappe-skills/tree/main/doctype-development. 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 Doctype Development?

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 Doctype Development?

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

Is the Doctype Development 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 👇