Dify Workflow CLI
Create, edit, and validate Dify workflow DSL YAML from the command line
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 15, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 7b03557
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.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 3/5
- Triggers reliably 5/5
- Output vs. baseline 9/10
- Docs & honesty 5/5
What Dify Workflow CLI does
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.
How to install Dify Workflow CLI
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
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Dify Workflow CLI
-
/dify-workflowCreate, edit, and validate Dify workflow DSL YAML from the command line
It also activates on plain-language prompts like these:
-
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
Frequently asked questions
- Is the Dify Workflow CLI skill free?
- Yes. The skill itself is free from Akabane71/dify-workflow-cli. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Dify Workflow CLI work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Works with setup. 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.
- What is the Dify Workflow CLI SkillProof Score?
- 8.8/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
- How do I install Dify Workflow CLI?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Dify Workflow CLI with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.