---
title: "Weekly Substack ranking report"
canonical: "https://agenticfeats.com/c/weekly-substack-ranking-report-claude-in-chrome/"
agents: ["Claude Cowork", "Claude in Chrome"]
evidence_grade: "A"
outcome: "completed"
job_type: "Research"
industry: "Newsletters"
roles: ["Marketing"]
source_url: "https://artificialcorner.com/p/claude-automates"
source_date: "2026-03-04"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# Weekly Substack ranking report

Claude in Chrome scrapes the top 250 Substack newsletters from Reletter each week, then Claude Cowork turns the data into a gains and losses report.

Result: The author's weekly chart scraping and rank analysis now runs as two scheduled tasks every Tuesday, replacing manual copy-paste and taking a couple of minutes.

## How it was set up

Claude in Chrome runs the scrape, launched from Claude Cowork. Both use scheduled tasks created by converting a working prompt, set for Tuesday at 5 PM and 5:10 PM.

## Worth knowing

Tasks only run while the computer is awake and Claude Desktop is open. Each run uses the daily usage allowance.

## Prompt

```text
Based on the data in the folder [folder name], analyze the rankings: top 10 biggest rank gains, top 20 new entrants, top 10 biggest rank losses. Do this separately for [dataset A] and [dataset B].
```

## Evidence note

Author describes own workflow with screenshots and a video demo; no repo

## Sources

- Original: https://artificialcorner.com/p/claude-automates

## The receipt

- Agent: Claude Cowork, Claude in Chrome
- Evidence: Shown (grade A, artifact linked)
- Outcome: Completed
- Job type: Research
- Industry: Newsletters
- Roles: Marketing
- Source: Blog
- Published: 2026-03-04
- Added: 2026-10-13