Dify Workflow CLI

Create, edit, and validate Dify workflow DSL YAML from the command line

par Akabane71 · Akabane71/dify-workflow-cli

Fonctionne avec configuration ★ 8.8/10

Dify Workflow CLI — Create, edit, and validate Dify workflow DSL YAML from the command line

Ce que fait

Wraps a Python CLI (dify-workflow) that creates, edits, validates, auto-layouts, and exports Dify AI workflow DSL files across all 5 app modes and 22 node types. Triggers when the user wants to build a Dify workflow/chatflow/agent, wire nodes and edges, or debug why a Dify import shows disconnected nodes or checklist errors.

Rapport de test

Ran the real CLI end to end (create, validate, checklist, layout, mermaid export) and it produced a schema-valid Dify DSL on the first try; a hand-written baseline DSL failed the same validator with 3 missing-field errors. Caveat: the Python package (pyproject.toml, dify_workflow/) lives at the repo root, not inside skills/dify-workflow/, so the documented cp -r single-folder copy leaves `dify-workflow` uninstalled — you must clone the whole repo and `pip install -e .` from the root, then separately copy the skill folder.

Testé le: 2026-07-15 · Claude Code 2.x (agent harness)

Installation

git clone https://github.com/Akabane71/dify-workflow-cli
mkdir -p ~/.claude/skills
cp -r dify-workflow-cli/skills/dify-workflow ~/.claude/skills/dify-workflow

Commandes et exemples de prompts

/dify-workflowCreate, edit, and validate Dify workflow DSL YAML from the command line

Les skills se déclenchent sur des demandes en langage courant — aucune commande à retenir. Après installation, des prompts comme ceux-ci l'activent (en anglais) :

Create a Dify chatflow with an LLM node and a knowledge retrieval node
Validate this Dify workflow YAML, the import shows disconnected nodes
Add a question classifier node to my Dify workflow and wire the branches

Rapport complet →