Skip to content
agentusehub
Sign in+ Submit
Research & KnowledgeAny

Scrape weekly Substack rankings and write a report

Claude in Chrome runs weekly to scrape Substack ranking data into a dataset, and Cowork analyzes it and writes a weekly report.

Read the experience
Time saved
Not reported
Setup time
Not reported
Running cost
Not reported
Cost range
Not reported

Use case overview

Claude in Chrome runs weekly to scrape Substack ranking data into a dataset, and Cowork analyzes it and writes a weekly report.

Read the original report ↗

Reported experience

  1. What they did

    Frank Andrade prompts Claude in Chrome to scrape the first 250 rows of Reletter's Substack charts (rank, newsletter, date, free/paid) into a CSV, then converts that prompt into a task that runs every Tuesday. A Cowork task at 5:10 PM reads the saved folder and builds a spreadsheet of the biggest rank gains, losses and new entrants, for paid and free separately.

  2. How it went

    Each week the scrape takes a couple of minutes, and Cowork drops the analysis spreadsheet into his folder. The source gives no accuracy checks or other figures.

  3. Worth knowing

    Scheduled tasks only run while the computer is awake and the Claude desktop app is open, and each run draws on your daily usage allowance.

Example prompts

Try with Claude in Chrome
Go to [ranking page URL, such as a Substack leaderboard for my category] and scrape the top [50] entries with rank, name, and any visible stats into a spreadsheet, adding a column for today's date. Append to the existing file at [file location] if it exists. Stop when the data is saved and tell me how many rows were added, so I can run the same job weekly.

Related use cases

Research & Knowledge

Analyze 170k LLM logs overnight

A user left a Gemini agent running overnight to analyze 170k LLM logs with the llm CLI and a free model, and it finished the job despite limits.

Gemini