Description / Intro This is a lightweight executor workflow designed to be used together with the main “Daily Github Action Executor Agent” template. It does not perform scheduling or decision logic on its own. Instead, it serves as an execution layer that receives structured inputs from the main workflow and triggers a GitHub Actions workflow via the GitHub API (workflow_dispatch). This template is intended to be published as a workflow tool and called by an Agent in another workflow.

Author：Zhiqiang Yang A scheduled weather notification workflow that sends a daily weather forecast email at a fixed time. It retrieves weather data for a specified city using the OpenWeather plugin, formats the forecast into a clear, human-readable email with an LLM, and automatically delivers it via Gmail. Suitable for daily planning, personal alerts, or location-based notification use cases.

In a corporate environment, we often need to process various types of spreadsheet data to extract information, insights, and trends. This is commonly applied across multiple fields, including sales, financial reporting, customer relations, and user research. This workflow allows you to easily upload a CSV file and automatically generate a polished data visualization report, helping you capture the specific information you care about from your data.

A daily scheduled workflow that checks whether required Docker images are missing from a target registry and triggers synchronization only when needed. On a Daily Trigger, it refreshes metadata, fetches the latest version, and validates whether any image variants are missing. If missing variants are found, an Agent parses the JSON, extracts namespace, name, and version, and calls the “Run Github Workflow” tool to trigger a GitHub Actions sync job. Finally, it updates the cron endpoint with the current version. Must be used with the companion “Github Action” tool template.

Author: Suliu Qin An automated workflow that scours the web for the latest AI news and product updates based on your keywords. It then intelligently summarizes the findings and generates a beautifully formatted, ready-to-share HTML daily digest. Stay ahead of the curve effortlessly.

This workflow acts as an intelligent ticket‑handling system. It receives ticket details via a webhook, extracts key information, classifies the ticket type (e.g. return, account issue, product question), retrieves relevant articles from a knowledge base and generates a response. It can also send notifications to team channels (e.g., Slack or Discord) and keep track of ticket status. The template is suitable for helpdesk automation and customer service triage.

This template demonstrates how to start a workflow from both a third‑party plugin event and a custom HTTP webhook. It listens to events from an external system via a plugin (e.g., GitHub events) and to arbitrary events via a webhook endpoint. Upon receiving an event, it processes the data, optionally summarises it with an LLM, and sends a formatted notification to Slack. The example shows how to build event‑driven integrations across multiple sources.

A multi-agent chatbot that automatically help you to conduct talent review with any file format you wish.

This workflow automatically turns long-form text into a visually consistent presentation deck. It first extracts and structures the input content into slide-level outlines, then generates a styled presentation cover and slide images in a unified visual theme.Each slide is rendered individually using an image-capable LLM, ensuring consistent branding, typography, and layout across the entire deck. The result is a ready-to-use presentation generated directly from raw text, without manual slide design.

This workflow is a daily briefing generator. A schedule trigger fires at a preset time each day, triggering a search for trending AI/technology news via the Tavily Search plugin. The results are summarised by an LLM into a concise brief and delivered to a Slack channel. It provides teams with up‑to‑date highlights without manual effort.

Fetches Bay Area AI events from Google Search on a schedule, extracts event details (title, date, location, URL) via LLM with computer use and jina_reader, then exports to JSON and ICS. Outputs `ics` and `json` for import into Google Calendar.

Turn any idea or document into a polished, Dify-branded HTML presentation — automatically.Upload a PDF, a Word doc, or just describe what you need. The workflow analyzes your input, asks a few smart questions to understand your intent, generates a structured outline for your approval, and then produces a complete interactive slide deck that follows Dify's visual identity: the signature blue palette, Instrument Serif typography, smooth animations, and full keyboard navigation — all in a single HTML file you can open in any browser.

DeepResearch uses loop variables and agent nodes to iteratively explore the web, identify knowledge gaps, and synthesize findings into a structured report. The workflow leverages tools like Tavily Search to collect relevant web results and Deepseek Reasoner to analyze and summarize them, delivering comprehensive answers to complex questions.

This instructional workflow demonstrates how to build a multi‑step pipeline in Dify. It accepts a body of text, extracts all standalone questions using a parameter‑extraction node, loops through each question, retrieves relevant knowledge from a dataset, and uses an agent to draft an answer with citations. Finally, the answers are formatted into a structured reply. The template is intended for educational purposes to help new users understand loops, iterations, knowledge retrieval and agent nodes.

This workflow automatically turns long-form text into a visually consistent presentation deck. It first extracts and structures the input content into slide-level outlines, then generates a styled presentation cover and slide images in a unified visual theme.Each slide is rendered individually using an image-capable LLM, ensuring consistent branding, typography, and layout across the entire deck. The result is a ready-to-use presentation generated directly from raw text, without manual slide design.

This workflow extracts structured information from images of a Chinese identity card. It processes the front (人像面) and back (国徽面) of the ID card separately, using vision‑enabled LLMs to extract fields such as Name, Gender, Ethnicity, Birth Date, Address, Issuing Authority, Validity Period and ID Number. The results are validated (e.g., checking dates and ID number format) and combined into a single JSON object. It is designed for onboarding, KYC or identity verification scenarios.

Author：Tianwei Wu A daily digest of the top-xranked Hugging Face research papers, written for non-researchers. Each paper is explained in plain English, highlighting its core idea, its real contribution, and who it is actually useful for. The goal is to help you quickly decide which of today’s most important papers are worth reading, without jargon, hype, or unnecessary detail.

This workflow automates the handling of inbound customer emails. Given a customer’s name, email subject and body, it classifies the query into predefined categories (e.g. product inquiry, refund request), retrieves relevant knowledge from your dataset, and uses an agent to compose a personalised reply that addresses the customer’s concerns. It streamlines customer support and ensures consistent responses.

Assesses Typeform partner applications with one Agent: google_search + assessment SOP → writes assessment.json, then Gmail (to partner with CC, or to operator for Proceed). Output is JSON only.

This workflow generates a multi-dimensional deconstruction poster for a novel. After you upload a novel file (TXT, PDF or EPUB), it extracts and cleans the text, verifies that it’s a novel, splits the content into manageable segments and uses a language model to summarise characters, events, timelines and key items. Those summaries are combined into a poster specification containing a title, character-relationship graph, a chronological timeline and additional dimensions. A Gemini image-generation tool then converts this specification into a hand-drawn style poster.

Through this template, you can learn how to use Human-in-the-Loop and experience our latest Symphony Runtime Agent capabilities. The Agent will assist you in researching a candidate's background by searching for relevant information across internet platforms such as Twitter, LinkedIn, GitHub, and Google Scholar. The process includes the following steps: 1. The Agent gathers information and drafts a background check PDF. 2. This PDF is then attached to a Gmail draft. 3. Throughout this process, you can review and supervise the progress via Human-in-the-Loop.