Drupal Config logo

Drupal Config

Community
edutrul
drupal-config

Drupal configuration management with Drush — import/export config, preview config changes before applying (e.g., seeing what would change without importing), config splits, and environment syncing.

Overview

Publisheredutrul
Repositorydrupal-ai
Skill namedrupal-config
Stars
73
Forks
14
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Drupal Config 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/edutrul/drupal-ai/tree/main/.claude/skills/drupal-config
  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/edutrul/drupal-ai.git /tmp/drupal-ai
mkdir -p .claude/skills
cp -r /tmp/drupal-ai/.claude/skills/drupal-config .claude/skills/drupal-config
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Drupal Config 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 Drupal Config 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 Drupal Config 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.

Drupal Configuration Management

Safety: Avoid Accidental Remote Imports

Remote drush may default to --yes and auto-confirm cim. Always use safe patterns:

bash
# SAFE — preview only
ssh user@remote "drush cim --no --diff"
ssh user@remote "drush config:get config.name"
ssh user@remote "drush config:status"

# DANGEROUS — may auto-import
ssh user@remote "drush cim --diff"

Import / Export

bash
ddev drush cex               # Export active config → YAML files
ddev drush cim               # Import YAML files → active config
ddev drush cim --no --diff   # Preview only (no import)
ddev drush config:status     # Show pending changes (read-only)

Config Splits

Complete vs Partial — CRITICAL distinction

TypeBehaviorUse for
CompleteConfig exists ONLY in that environmentModules on/off (devel, stage_file_proxy)
PartialBase config everywhere, different VALUESAPI keys, SMTP, search server URLs

Complete split: config is removed from config/sync/ and lives only in config/{split}/. Partial split: config stays in config/sync/, overrides live in config/{split}/config_split.patch.*.yml.

Split Commands

bash
ddev drush config-split:status            # List splits and active state
ddev drush csex {split-name}              # Export specific split
ddev drush csim {split-name}              # Import specific split
ddev drush config-split:activate {name}
ddev drush config-split:deactivate {name}

Updating a Split Definition

Changes must be in active config (DB), not just YAML files:

bash
# Edit YAML, then import to activate
ddev drush config:import --partial
# OR set via PHP eval
ddev drush php:eval "\$c = \Drupal::configFactory()->getEditable('config_split.config_split.local'); \$c->set('partial_list', ['config.name']); \$c->save();"
ddev drush cex

Troubleshooting

Config deleted from config/sync/ on export

Root cause: Config is in complete_list instead of partial_list.

bash
# Diagnose
grep -A10 "complete_list:" config/sync/config_split.config_split.local.yml
grep -A10 "partial_list:" config/sync/config_split.config_split.local.yml

Fix: move the item from complete_list to partial_list in the split YAML, then import and re-export.

Config won't import

bash
ddev drush config:import --skip-config=system.site   # Skip specific locked config
ddev drush config:import --skip-modules=config_split  # Ignore splits

Split not activating

bash
ddev drush config-split:status
ddev drush config-split:activate {split-name}
ddev drush cex

Intent → Command Mapping

User IntentCommand
Preview config changesdrush cim --no --diff
Import configdrush cim
Export configdrush cex

Related Commands

Read-only: config:get, config:status Export: cex / config:export Import: cim --no --diff (preview), cim (apply) Splits: config-split:status, csex, csim, config-split:activate

Deep Dive

  • full-guide.md — Extended reference on Config Split 2.0, patch files, export/import internals

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 Drupal Config AI skill do?

Drupal configuration management with Drush — import/export config, preview config changes before applying (e.g., seeing what would change without importing), config splits, and environment syncing.

Why use Drupal Config on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/edutrul/drupal-ai/tree/main/.claude/skills/drupal-config. 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 Drupal Config?

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 Drupal Config?

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

Is the Drupal Config AI skill free?

Yes. It is published on GitHub by edutrul 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 👇