Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    dify dsl creator

    0

    Generate, validate, and repair import-ready Dify DSL YAML for workflows and chatflows.

    $10

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    dify dsl creator

    dify dsl creator

    Example session with this skill installed

    Build a Dify workflow: accept user question, query knowledge base, then call LLM to answer, add a condition branch for empty search result.

    • Read your context and instructions
    • Compiled the dify dsl creator

    app:
    description: 问题分类路由工作流示例
    icon: 🤖
    icon_background: '#FFEAD5'
    mode: workflow
    name: 问题分类路由示例
    use_icon_as_answer_icon: false
    dependencies: []
    kind: app
    version: 0.3.0
    workflow:
    conversation_variables: []
    environment_variables: []
    features:
    file_upload:
    allowed_file_extensions:
    - .JPG
    - .JPEG
    - .PNG
    - .GIF
    - .WEBP
    - .SVG
    allowed_file_types:
    - image
    allowed_file_upload_methods:
    - local_file
    - remote_url
    enabled: false
    fileUploadConfig:
    audio_file_size_limit: 50
    batch_count_limit: 5
    file_size_limit: 15
    image_file_size_limit: 10
    video_file_size_limit: 100
    workflow_file_upload_limit: 10
    number_limits: 3
    opening_statement: ''
    retriever_resource:
    enabled: false
    sensitive_word_avoidance:
    enabled: false
    speech_to_text:
    enabled: false
    suggested_questions: []
    suggested_questions_after_answer:
    enabled: false
    text_to_speech:
    enabled: false
    language: ''
    voice: ''
    graph:
    edges:
    - data:
    isInIteration: false
    sourceType: start
    targetType: question-classifier
    id: edge-start-classifier
    source: '1730000000201'
    sourceHandle: source
    target: '1730000000202'
    targetHandle: target
    type: custom
    zIndex: 0
    - data:
    isInIteration: false
    sourceType: question-classifier
    targetType: llm
    id: edge-classifier-product
    source: '1730000000202'
    sourceHandle: '1'
    target: '1730000000203'
    targetHandle: target
    type: custom
    zIndex: 0
    - data:
    isInIteration: false
    sourceType: question-classifier
    targetType: llm
    id: edge-classifier-support
    source: '1730000000202'
    sourceHandle: '2'
    target: '1730000000204'
    targetHandle: target
    type: custom
    zIndex: 0
    - data:
    isInIteration: false
    sourceType: llm
    targetType: variable-aggregator
    id: edge-product-aggregator
    source: '1730000000203'
    sourceHandle: source
    target: '1730000000205'
    targetHandle: target
    type: custom
    zIndex: 0
    - data:
    isInIteration: false
    sourceType: llm
    targetType: variable-aggregator
    id: edge-support-aggregator
    source: '1730000000204'
    sourceHandle: source
    target: '1730000000205'
    targetHandle: target
    type: custom
    zIndex: 0
    - data:
    isInIteration: false
    sourceType: variable-aggregator
    targetType: end
    id: edge-aggregator-end
    source: '1730000000205'
    sourceHandle: source
    target: '1730000000206'
    targetHandle: target
    type: custom
    zIndex: 0
    nodes:
    - data:
    desc: ''
    selected: false
    title: 开始
    type: start
    variables:
    - label: 用户问题
    max_length: 200
    options: []
    required: true
    type: text-input
    variable: query
    height: 90
    id: '1730000000201'
    position:
    x: 80
    y: 282
    positionAbsolute:
    x: 80
    y: 282
    selected: false
    sourcePosition: right
    targetPosition: left
    type: custom
    width: 244
    - data:
    classes:
    - id: '1'
    name: 产品咨询
    - id: '2'
    name: 售后服务
    desc: ''
    instruction: 请根据用户问题判断它属于产品咨询还是售后服务。
    model:
    completion_params:
    temperature: 0
    mode: chat
    name: gpt-4o-mini
    provider: openai
    query_variable_selector:
    - '1730000000201'
    - query
    selected: false
    title: 问题分类
    type: question-classifier
    height: 98
    id: '1730000000202'
    position:
    x: 430
    y: 282
    positionAbsolute:
    x: 430
    y: 282
    selected: false
    sourcePosition: right
    targetPosition: left
    type: custom
    width: 244
    - data:
    context:
    enabled: false
    variable_selector: []
    desc: ''
    model:
    completion_params:
    temperature: 0.5
    mode: chat
    name: gpt-4o-mini
    provider: openai
    prompt_template:
    - role: system
    text: 你是产品顾问,请回答产品功能、价格和适用场景相关问题。
    - role: user
    text: '{{#1730000000201.query#}}'
    selected: false
    title: 产品咨询回复
    type: llm
    variables: []
    vision:
    enabled: false
    height: 98
    id: '1730000000203'
    position:
    x: 780
    y: 162
    positionAbsolute:
    x: 780
    y: 162
    selected: false
    sourcePosition: right
    targetPosition: left
    type: custom
    width: 244
    - data:
    context:
    enabled: false
    variable_selector: []
    desc: ''
    model:
    completion_params:
    temperature: 0.5
    mode: chat
    name: gpt-4o-mini
    provider: openai
    prompt_template:
    - role: system
    text: 你是售后支持人员,请回答退换货、故障排查和投诉相关问题。
    - role: user
    text: '{{#1730000000201.query#}}'
    selected: false
    title: 售后回复
    type: llm
    variables: []
    vision:
    enabled: false
    height: 98
    id: '1730000000204'
    position:
    x: 780
    y: 402
    positionAbsolute:
    x: 780
    y: 402
    selected: false
    sourcePosition: right
    targetPosition: left
    type: custom
    width: 244
    - data:
    desc: ''
    output_type: string
    selected: false
    title: 变量聚合
    type: variable-aggregator
    variables:
    - - '1730000000203'
    - text
    - - '1730000000204'
    - text
    height: 98
    id: '1730000000205'
    position:
    x: 1130
    y: 282
    positionAbsolute:
    x: 1130
    y: 282
    selected: false
    sourcePosition: right
    targetPosition: left
    type: custom
    width: 244
    - data:
    desc: ''
    outputs:
    - value_selector:
    - '1730000000205'
    - output
    variable: result
    selected: false
    title: 结束
    type: end
    height: 107
    id: '1730000000206'
    position:
    x: 1480
    y: 282
    positionAbsolute:
    x: 1480
    y: 282
    selected: false
    sourcePosition: right
    targetPosition: left
    type: custom
    width: 244
    viewport:
    x: 0
    y: 0
    zoom: 0.7

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Manually writing Dify DSL YAML is error-prone, leading to "Invalid DSL" errors and broken variable references during import. This skill automates the generation, repair, and validation of import-ready YAML for Dify workflow and advanced-chat (Chatflow) applications.

    What it does

    • Generate DSL produces structured YAML for workflows and chatflows using verified node contracts.
    • Validate Structure runs deterministic checks for node IDs, variable selectors, and edge connectivity.
    • Repair YAML identifies and fixes broken references, missing required fields, or invalid node schemas in existing files.
    • Canvas Layout applies readable x/y coordinate spacing to prevent overlapping nodes on the Dify canvas.
    • Version Adaptation handles differences between standard Dify and specific distributions like Qinglian Dify.

    How it works

    1. Target Definition confirms the app mode, Dify version, and required node inventory.
    2. Skeleton Initialization loads a verified base template for the specific version (e.g., 0.3.0 or 0.3.1).
    3. Graph Construction populates nodes and edges while enforcing variable reference rules.
    4. Validation executes scripts/validate_dify_dsl.py to ensure the output is importable.

    Frameworks & tools

    The skill generates Dify-compatible YAML DSL and utilizes a Python-based validation script for structural integrity checks. It includes specific profiles for standard Dify and Qinglian Dify distributions.

    Why this beats prompting it yourself

    Generic LLMs often hallucinate Dify variable syntax, mixing up structured selectors with template tags. This skill uses strict node contracts and a local validation script to ensure every generated file actually imports without errors.

    Use cases

    • Workflow Scaffolding quickly builds complex RAG or HTTP request chains from scratch.
    • DSL Troubleshooting fixes "Variable not found" or "Circular dependency" errors in exported files.
    • Mass Migration adapts standard Dify exports for compatibility with private cloud distributions.

    Known limitations

    Does not support iteration or custom plugin nodes without a user-provided template. Requires a local Python environment to run the optional validation script.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.

    Cannot verify if specific model IDs or API keys exist in your Dify instance. Requires user-provided templates for custom marketplace plugins and iteration nodes.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    Software
    Python 3.10+Git

    Ensure Python 3.10+ installed. Install dependencies via pip install -r requirements.txt

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access

    Read/Write files: load DSL reference and save generated yaml. Terminal: run python validation script. Network access: fetch latest Dify DSL spec reference.

    Listed5 days ago
    Updated1 day ago

    What's inside

    Frequently Asked Questions

    The skill automates the creation and repair of Dify YAML files, specifically solving the "Invalid DSL" error often encountered when manually editing or prompting generic LLMs for workflow exports.

    It supports standard Dify (versions 0.3.x and above) and specialized distributions like Qinglian Dify, covering both Workflow and Advanced-Chat (Chatflow) application modes.

    Yes, the skill includes a "Repair YAML" feature designed to identify and fix broken variable references, missing mandatory fields, and circular dependencies in your existing exports.

    You will receive the core AI skill optimized for DSL generation, verified base templates for different Dify versions, and a Python-based validation script for local structural integrity checks.

    The skill handles most native Dify nodes; however, custom plugins or "iteration" nodes require a user-provided template to ensure the specific schema is followed correctly.

    The skill includes a Canvas Layout feature that automatically assigns x/y coordinates to nodes, ensuring that your imported workflow is organized and readable rather than stacked in a single pile.

    A: Yes, we maintain alignment with official Dify workflow schema.

    New in Prompt & Skill Engineering