Bpmn Workflow logo

Bpmn Workflow

Organization
WellApp-ai
bpmn-workflow

Generate and maintain BPMN 2.0 diagrams linked to Gherkin scenarios

Overview

PublisherWellApp-ai
RepositoryWell
Skill namebpmn-workflow
Stars
342
Forks
48
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 WellApp-ai on GitHub. Read the source before you install it.

Installation

Install the Bpmn Workflow 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/WellApp-ai/Well.git /tmp/Well
mkdir -p .claude/skills
cp -r /tmp/Well/cursor-rules/skills/bpmn-workflow .claude/skills/bpmn-workflow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bpmn Workflow 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 Bpmn Workflow 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 Bpmn Workflow 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.

BPMN Workflow Skill

Generate BPMN 2.0 process diagrams from feature specifications, link them to Gherkin scenarios, and compose a system-wide workflow diagram.

When to Use

  • After completing Ask mode (feature exploration) to visualize the flow
  • When documenting system processes for stakeholders
  • Before Plan mode to ensure all scenarios are captured
  • When updating existing features with new scenarios

Prerequisites

  • Feature has been explored in Ask mode with wireframes
  • User flows have been identified
  • API endpoints (if any) have been specified

Instructions

Phase 1: Gather Feature Context

Step 1.1: Check for existing .feature files

Glob docs/bpmn/features/**/*.feature

If found, parse existing scenarios:

CallMcpTool:
  server: "bpmn-mcp"
  toolName: "read-feature"
  arguments: { "featurePath": "docs/bpmn/features/{feature-id}/{feature-id}.feature" }

Step 1.2: If no .feature file exists, generate scenarios from:

  • Ask mode wireframes (each screen = potential scenario)
  • User flow descriptions
  • API endpoints defined (CRUD operations = scenarios)
  • Edge cases identified (error states, empty states)

Phase 2: Generate Gherkin (if needed)

If generating new scenarios, structure them as:

gherkin
Feature: [Feature Name]
  As a [user type]
  I want to [action]
  So that [benefit]

  Scenario: [Happy path name]
    Given [precondition]
    When [action]
    Then [expected result]

  Scenario: [Error case name]
    Given [precondition]
    When [invalid action]
    Then [error handling]

Scenario naming conventions:

  • Happy path: Successful [action], [Action] completes
  • Validation: [Action] with invalid [field]
  • Error: [Action] when [error condition]
  • Edge: [Action] with [edge case]

Phase 3: Generate BPMN

Call the generate-bpmn MCP tool:

CallMcpTool:
  server: "bpmn-mcp"
  toolName: "generate-bpmn"
  arguments: {
    "featureId": "{feature-id}",
    "featureName": "{Feature Name}",
    "scenarios": [
      {
        "id": "{scenario-id}",
        "name": "{Scenario Name}",
        "steps": [
          { "keyword": "Given", "text": "{step text}" },
          { "keyword": "When", "text": "{step text}" },
          { "keyword": "Then", "text": "{step text}" }
        ]
      }
    ],
    "outputPath": "docs/bpmn/features/{feature-id}/{feature-id}.bpmn"
  }

Phase 4: Create Manifest Link

Link BPMN elements to Gherkin scenarios:

CallMcpTool:
  server: "bpmn-mcp"
  toolName: "link-gherkin"
  arguments: {
    "featureId": "{feature-id}",
    "featureName": "{Feature Name}",
    "bpmnFile": "docs/bpmn/features/{feature-id}/{feature-id}.bpmn",
    "featureFile": "docs/bpmn/features/{feature-id}/{feature-id}.feature"
  }

This creates docs/bpmn/features/{feature-id}/manifest.json with traceability links.

Phase 5: Compose System Diagram

Update the master system diagram:

CallMcpTool:
  server: "bpmn-mcp"
  toolName: "compose-system"
  arguments: {
    "systemName": "Well Platform",
    "featuresDir": "docs/bpmn/features",
    "outputPath": "docs/bpmn/system.bpmn"
  }

Output Format

After completing all phases, present:

markdown
## BPMN Workflow Generated

### Files Created/Updated

| File | Status | Description |
|------|--------|-------------|
| `docs/bpmn/features/{id}/{id}.feature` | Created/Updated | [N] scenarios |
| `docs/bpmn/features/{id}/{id}.bpmn` | Created | Process diagram |
| `docs/bpmn/features/{id}/manifest.json` | Created | [N] links |
| `docs/bpmn/system.bpmn` | Updated | Added {Feature Name} pool |

### Scenarios Mapped

| Scenario | BPMN Element | Steps |
|----------|--------------|-------|
| [Name] | Task_{id} | [N] |

### System Diagram

[ASCII representation of system pools]

┌─────────────────┐     ┌─────────────────┐
│  Auth           │────▶│  Workspaces     │
│  • Login        │     │  • Create       │
│  • Register     │     │  • Switch       │
└─────────────────┘     └─────────────────┘

BPMN Element Mapping

Gherkin ConceptBPMN Element
ScenarioUserTask
Given stepsDocumentation (preconditions)
When stepsDocumentation (action)
Then stepsDocumentation (expected)
FeatureProcess
BackgroundSubprocess (shared)

Storage Structure

docs/bpmn/
├── README.md                    # Documentation
├── system.bpmn                  # Master system diagram
└── features/
    └── {feature-id}/
        ├── {feature-id}.bpmn    # Feature process diagram
        ├── {feature-id}.feature # Gherkin scenarios
        └── manifest.json        # BPMN ↔ Gherkin links

Related Skills

  • problem-framing - Defines the problem before BPMN generation
  • competitor-scan - Research how competitors document workflows
  • design-context - Ensures BPMN aligns with existing patterns

Troubleshooting

No MCP server available:

  • Ensure bpmn-mcp is configured in .cursor/mcp.json
  • Check that @wellapp/bpmn package is built

Invalid BPMN generated:

  • Validate with validate-bpmn tool
  • Check scenario IDs are unique
  • Ensure step keywords are valid (Given/When/Then/And/But)

Manifest links broken:

  • Re-run link-gherkin after updating scenarios
  • Ensure scenario IDs match between .feature and manifest

Frequently asked questions

What does the Bpmn Workflow AI skill do?

Generate and maintain BPMN 2.0 diagrams linked to Gherkin scenarios

Why use Bpmn Workflow on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/WellApp-ai/Well/tree/main/cursor-rules/skills/bpmn-workflow. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Bpmn Workflow?

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 Bpmn Workflow?

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

Is the Bpmn Workflow AI skill free?

Yes. It is published on GitHub by WellApp-ai 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 👇