Coding

Record a browser task once and get an n8n workflow

  • Level Intermediate
  • Setup1–3 hrs (estimated)
  • Evidence Some evidence
  • CostNot stated in source
  • No-codeNo
n8nClaudeSource-linked

What they did

An open-source Chrome extension records you doing a task once, a vision model turns it into a plan with variables and a trigger, and a builder outputs n8n nodes. Steps without an API become marked manual steps.

How it went

v0.2, early: linear workflows only; loaded unpacked. MIT

Worth knowing

  • v0.2, early: linear workflows only; loaded unpacked. MIT.

Prompt

Cleaned version rewritten from the source — not a direct quote.

Watch me do this task once: [copy the invoice amount from the latest email from X into my Invoices sheet]. Turn it into a repeatable workflow: list the steps, which values change each run, and a trigger (new email). Mark anything without an API as a manual step.

Recommended

Try it in Grok Bot

  1. Copy the prompt (button below).
  2. Open Grok Bot chat and paste it. Replace any [bracketed] placeholders.
  3. Connect the listed tools (Email) as connectors when Grok Bot asks.
  4. If the task repeats, ask: "Make this a daily routine."

Alternatives: the same prompt works in n8n, Claude, ChatGPT Agent, OpenClaw.

Set it up

Tools: Email · Stack: n8n + ShowOnce (Claude, Gemini or Ollama)

  1. Read the original source for full context.
  2. Connect the tools your agent needs.
  3. Paste the prompt and replace [bracketed] placeholders.
  4. Run once manually and check the output before scheduling it.

Generic suggested steps, not from the source.

Evidence

v0.2, early: linear workflows only; loaded unpacked. MIT

Source: Web · Verified by us: not yet · Report broken or outdated

Related use cases

MoneyWeb · 2026-02

Check a hospital bill against what Medicare would pay

A writer gave Claude the coded hospital claim (UB-04) for his late brother-in-law's $195,628 ER bill and asked it to build a spreadsheet of Medicare rates per code. Claude flagged bundled items billed separately, a bypass charge for a procedure that never happened, and a ventilation charge Medicare does not allow.

  • Level Intermediate
  • Setup1–3 hrs*
  • Evidence Strong evidence
ClaudeSource-linked
CodingX · 2026-10

Hermes Agent Nearly Doubled Speech-to-Text Accuracy on Hard Words: 99 to 183 of 240

A user turned his 15K saved Wispr Flow dictations into a test set for the local Whisper model behind his Hermes Agent. The agent turned his Wispr dictionary into a hint list, diffed raw vs corrected text to find words Whisper keeps mishearing, made find-and-fix rules, and tested every rule against the full history. With no fine-tuning, dictionary words went from 99/240 to 183/240 on Wispr clips and 19/45 to 43/45 on sentences he read aloud. It now archives the data nightly and looks for new fixes weekly.

  • Level Advanced
  • Setup1–3 hrs*
  • Evidence Strong evidence
Hermes AgentSource-linked