Creates a standardized directory structure and configuration for new MDA (BPMN) process projects.

Install

mkdir -p .claude/skills/mda-init && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12065" && unzip -o skill.zip -d .claude/skills/mda-init && rm skill.zip

Installs to .claude/skills/mda-init

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Scaffold a new MDA process repository. Use when creating a new BPMN process project from scratch.
97 chars✓ has a “when” trigger
Beginner

Key capabilities

  • Scaffold a new MDA process repository
  • Create standard directory structures
  • Generate default configuration files
  • Prompt for necessary process metadata
  • List the created directory tree

How it works

The skill executes a Python CLI command to initialize a new MDA process repository, creating the necessary files and directories, and then displays the generated structure and configuration.

Inputs & outputs

You give it
A process name as an argument
You get back
A new MDA process repository with directory structure and `mda.config.yaml`

When to use mda-init

  • Create a new BPMN project from scratch
  • Initialize standard MDA folder structures
  • Generate default mda.config.yaml files

About this skill

MDA Init -- Scaffold a New Process Repository

This command creates a new MDA process repository with the standard directory structure, default configuration, and template files needed to begin modeling a BPMN process.

Context

Current working directory: !pwd Existing MDA config: !test -f mda.config.yaml && echo "mda.config.yaml found" || echo "No mda.config.yaml in current directory"

Steps

  1. Run the scaffolding command for the process named $ARGUMENTS:
python cli/mda.py init $ARGUMENTS
  1. If the command asks for additional information (domain prefix, namespace, etc.), prompt the user for those values before re-running.

  2. After successful scaffolding, list the created directory structure to confirm everything was set up:

ls -R $ARGUMENTS/
  1. Show the user:
    • The created directory tree
    • The generated mda.config.yaml contents
    • Suggested next steps (add BPMN file, add corpus documents, run ingest)

When not to use it

  • When an `mda.config.yaml` file already exists in the current directory
  • When the user does not want to create a new BPMN process project
  • When the `cli/mda.py` script is not available

Limitations

  • Requires the `cli/mda.py` script to be present
  • Prompts for additional information if the scaffolding command requires it
  • Assumes the user wants a standard directory structure

How it compares

This skill automates the initial setup of a BPMN process project with a predefined structure and configuration, simplifying repository creation compared to manual setup.

Compared to similar skills

mda-init side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
mda-init (this skill)04moReviewBeginner
linear-todo-sync110moReviewBeginner
mixseek-team-config06moReviewIntermediate
jarvis-packetize02moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

linear-todo-sync

qdhenry

This skill fetches open tasks assigned to the user from the Linear API and generates a markdown todo list file in the project root. This skill should be used when the user asks about their work items, wants to see what they need to work on, or requests to load/sync their Linear tasks. Requires Python 3.7+, requests, mdutils, and python-dotenv packages. Requires LINEAR_API_KEY in .env file.

13

mixseek-team-config

drillan

MixSeekのチーム設定ファイル(team.toml)を生成します。「チームを作成」「エージェント設定を生成」「Web検索チームを作って」「分析チームを設定」といった依頼で使用してください。Leader AgentとMember Agentの構成を定義します。

00

jarvis-packetize

A-C-I-SOFTWARE-AND-DEVELOPMENT

Turn a plain-English request into a bounded JARVIS work packet (intent, risk, owner gates, allowed files, verification, rollback) without executing anything.

00

loop-engineering

Mark393295827

Turn a repeatable task into a bounded, evidence-driven agent loop. Use when Codex needs to decide whether a task merits a Goal, Loop, Automation, or AutoResearch pattern; define a loop contract; check trigger/state/tools/codebase readiness; choose single-agent versus maker-checker versus manager-wor

00

tsg-pipeline

jcentner

Use when: changing TSG Builder pipeline behavior, stage prompts, TSG markers, required headings, review warnings, retries, or Research/Write/Review contracts.

00

video-downloader

ComposioHQ

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

101255

Search skills

Search the agent skills registry