Workflow Launchers logo

Workflow Launchers

Organization
adobe
workflow-launchers

Configure and deploy Workflow Launchers that automatically start workflows in response to JCR content changes on AEM as a Cloud Service

Overview

Publisheradobe
Repositoryskills
Skill nameworkflow-launchers
Stars
298
Forks
92
Bundled files
7
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.

  • 7 bundled files

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

  • Open source

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

Installation

Install the Workflow Launchers 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/adobe/skills/tree/main/plugins/aem/cloud-service/skills/aem-workflow/workflow-launchers
  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/adobe/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/aem/cloud-service/skills/aem-workflow/workflow-launchers .claude/skills/workflow-launchers
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Workflow Launchers 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 Workflow Launchers 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 Workflow Launchers 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.

Workflow Launchers Skill — AEM as a Cloud Service

Purpose

This skill teaches you how to configure and deploy Workflow Launchers that automatically start workflows in response to JCR content changes on AEM as a Cloud Service.

When to Use This Skill

  • A workflow must start automatically when an asset is uploaded to DAM
  • A review workflow should trigger whenever an author modifies content under a specific path
  • You need to replicate or replace an OOTB launcher behavior without editing /libs
  • You want to enable, disable, or restrict a launcher to specific run modes

Core Concept: What Is a Workflow Launcher?

A Workflow Launcher (cq:WorkflowLauncher) is a JCR node that registers a JCR event listener. When a node event occurs at a path matching the launcher's glob pattern, node type, and conditions, the Granite Workflow Engine enqueues a workflow start.

The listener is managed by WorkflowLauncherListener (an OSGi service). It reads all active launcher configurations at startup and re-evaluates them when configurations change.

Architecture at a Glance

JCR Event (NODE_ADDED / NODE_MODIFIED / NODE_REMOVED)
    ↓
WorkflowLauncherListener (OSGi EventListener)
    ↓ matches: glob, nodetype, event type, conditions
Workflow Engine: enqueue WorkflowData
    ↓
Workflow Instance created at /var/workflow/instances/

Launcher Configuration Properties

PropertyTypeDescription
eventTypeLong1 = NODE_ADDED, 2 = NODE_MODIFIED, 4 = NODE_REMOVED, 8 = PROPERTY_ADDED, 16 = PROPERTY_CHANGED, 32 = PROPERTY_REMOVED
globStringGlob pattern matched against the event node path (e.g., /content/dam(/.*)?)
nodetypeStringJCR node type the event node must be (e.g., dam:AssetContent)
conditionsString[]Additional JCR property conditions on the event node
workflowStringRuntime path of the workflow model /var/workflow/models/<id>
enabledBooleanWhether the launcher is active
descriptionStringHuman-readable description
excludeListString[]Workflow model IDs to exclude
runModesString[]Restrict to specific run modes (e.g., author)

Deploying a Custom Launcher on Cloud Service

On Cloud Service, /libs is immutable. Store launcher configurations at:

/conf/global/settings/workflow/launcher/config/<launcher-name>

Maven project location:

ui.content/src/main/content/jcr_root/conf/global/settings/workflow/launcher/config/
    my-custom-launcher/
        .content.xml

Filter in filter.xml:

xml
<filter root="/conf/global/settings/workflow/launcher/config/my-custom-launcher"/>

Node structure (.content.xml):

xml
<?xml version="1.0" encoding="UTF-8"?>
<jcr:root
    xmlns:jcr="http://www.jcp.org/jcr/1.0"
    xmlns:cq="http://www.day.com/jcr/cq/1.0"
    jcr:primaryType="cq:WorkflowLauncher"
    eventType="{Long}1"
    glob="/content/dam(/.*)?/jcr:content/renditions/original"
    nodetype="nt:file"
    workflow="/var/workflow/models/dam/update_asset"
    enabled="{Boolean}true"
    description="Start DAM update workflow on new original rendition upload"
    runModes="[author]"/>

Overlaying an OOTB Launcher

To disable or modify an OOTB launcher (e.g., dam_update_asset_create):

  1. Copy the node from /libs/settings/workflow/launcher/config/dam_update_asset_create to /conf/global/settings/workflow/launcher/config/dam_update_asset_create
  2. Modify the property (e.g., set enabled="{Boolean}false" to disable it)
  3. Deploy as a content package via Cloud Manager

Common OOTB Launchers (Cloud Service)

LauncherTriggerWorkflow
dam_update_asset_createNODE_ADDED on dam:AssetContent under /content/damDAM Update Asset
dam_update_asset_modifyNODE_MODIFIED on asset propertiesDAM Update Asset
dam_xmp_writebackNODE_MODIFIED on renditionDAM Writeback
update_page_version_*Node events on cq:Page jcr:contentPage Version Create

Event Type Combinations

To listen for both ADD and MODIFY, combine event types:

xml
eventType="{Long}3"  <!-- 1 (ADD) + 2 (MODIFY) = 3 -->

Where-Clause Conditions

The conditions array lets you add JCR property conditions on the triggering node:

xml
conditions="[property=cq:type,value=publicationevent,type=STRING]"

Condition format: property=<name>,value=<value>,type=<JCR_TYPE> (type is optional, defaults to STRING).

Disabling a Launcher for a Run Mode

Use runModes to restrict:

xml
runModes="[author]"   <!-- only fires on Author -->
runModes="[publish]"  <!-- only fires on Publish -->

Omit runModes to fire on all run modes.

Debugging Launchers

  • Tools → Workflow → Launchers UI — lists all active launchers, you can enable/disable interactively
  • Check /conf/global/settings/workflow/launcher/config/ in CRXDE Lite for your deployed configs
  • Check OSGi console → WorkflowLauncherListener service properties
  • After deployment, verify via: curl -u admin:admin http://localhost:4502/etc/workflow/launcher.json

References in This Skill

ReferenceWhat It Covers
references/workflow-launchers/launcher-config-reference.mdFull property spec and XML templates
references/workflow-launchers/condition-patterns.mdCommon condition patterns, glob syntax, event type codes
references/workflow-foundation/architecture-overview.mdGranite Workflow Engine overview
references/workflow-foundation/cloud-service-guardrails.mdCloud Service constraints for config paths
references/workflow-foundation/jcr-paths-reference.mdWhere launchers live in the JCR

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 Workflow Launchers AI skill do?

Configure and deploy Workflow Launchers that automatically start workflows in response to JCR content changes on AEM as a Cloud Service

Why use Workflow Launchers on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/adobe/skills/tree/main/plugins/aem/cloud-service/skills/aem-workflow/workflow-launchers. 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 Workflow Launchers?

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 Workflow Launchers?

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

Is the Workflow Launchers AI skill free?

Yes. It is published on GitHub by adobe 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 👇