FlowSync
Open App
中文
ProContent5 nodes
Score 73

Email Newsletter Automation

Pull from RSS feeds and article URLs → extract main content → curate top stories → generate newsletter-ready HTML with summaries and links. Export as Markdown for any ESP.

Run this template Fork & customise

What does this workflow do?

Drop your feeds — the pipeline runs 5 automated steps: Requests (feeds→json) → Trafilatura (URLs→text) → LLM Reasoning (text→json) → LLM Reasoning (json→html) → MarkItDown (html→md) — and delivers md. Every node is visible, auditable, and replaceable.

System flow

1. Requests — HTTP fetch layer with retry, throttle and header control 2. Trafilatura — Boilerplate-free main-content extraction from any web page 3. LLM Reasoning — Large-language-model step that extracts, classifies, validates or writes structured output 4. LLM Reasoning — Large-language-model step that extracts, classifies, validates or writes structured output 5. MarkItDown — Converts mixed document formats into clean Markdown

Pipeline breakdown

Requests feeds Trafilatura URLs LLM Reasoning text LLM Reasoning json MarkItDown html
  1. Requests requests — HTTP fetch layer with retry, throttle and header control feeds → json
  2. Trafilatura trafilatura — Boilerplate-free main-content extraction from any web page URLs → text
  3. LLM Reasoning llm — Large-language-model step that extracts, classifies, validates or writes structured output text → json
  4. LLM Reasoning llm — Large-language-model step that extracts, classifies, validates or writes structured output json → html
  5. MarkItDown markitdown — Converts mixed document formats into clean Markdown html → md

Workflow Reputation Score

Based on executions, success rate, update frequency, component quality, and user rating.

73Overall
★★★★★ 4.4
▶Executions
30
✓Success rate
100
↻Update frequency
70
⚙Component quality
90
★User rating
88

Based on executions, success rate, update frequency, component quality, and user rating.

Components used

Requestsrequests

HTTP fetch layer with retry, throttle and header control

psf/requests ↗
Trafilaturatrafilatura

Boilerplate-free main-content extraction from any web page

adbar/trafilatura ↗
LLM Reasoningllm

Large-language-model step that extracts, classifies, validates or writes structured output

FlowSync proprietary
MarkItDownmarkitdown

Converts mixed document formats into clean Markdown

microsoft/markitdown ↗

How is this different from n8n or Zapier?

Unlike generic workflow builders, FlowSync workflows ship pre-configured with AI skills baked into every node — OCR, LLM reasoning, transcription, super-resolution — not just webhook triggers. Each node is white-box auditable: you see input, output, and config. Deployment is instant — no self-hosting, no API-key per node.

Use cases

  • Weekly industry digest
  • Product update newsletter
  • Roundup from internal sources
  • Multi-author curation

Author & Source

This workflow is maintained by the FlowSync team. All components are open-source or commercially licensed. Source code for each component is linked in the Components section above.

Pricing: Free tier available · PRO tier · Official

Data handling

Data is processed in-memory during pipeline execution only. No files are stored permanently unless you choose to save outputs to your account.

FlowSync Workflow Marketplace · 73 reputation score · 30% execution · 100% success · 5-node white-box pipeline · maintained by FlowSync Official

Ready to run?

Pull from RSS feeds and article URLs → extract main content → curate top stories → generate newsletter-ready HTML with summaries and links. Export as Markdown for any ESP.

Run Email Newsletter Automation → Browse all workflows →