How do I install the Substack Notes Scraper skill?

Run npx skillmds@latest add aravinds-wick/substack-notes-scraper in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Substack Notes Scraper safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Substack Notes Scraper?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Substack Notes Scraper free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Substack Notes Scraper?

AravindS-Wick (@aravinds-wick) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Substack Notes Scraper by aravinds-wick

Name: Substack Notes Scraper
Author: AravindS-Wick

Substack Notes Scraper

Scrape Substack Notes metrics for a specific author and time period. Uses agent-browser to load the page, scrolls to fetch all posts, extracts metrics (likes, comments, restacks), and formats them as a structured spreadsheet (.xlsx). Use when the user runs /substack-notes-scraper, asks to scrape/analyze Substack notes, or wants a metrics report on Substack posts.

File contents

Substack Notes Scraper (`substack-notes-scraper`)

Scrapes author notes from Substack and compiles dates, text, likes, comments, restacks, and links into a structured spreadsheet.

Prerequisites

Requires agent-browser and a spreadsheet writing utility (like Python's openpyxl or pandas).

Parameters

Parameter	Required	Description
`url`	Yes	The Substack notes page URL (e.g. `https://substack.com/@username/notes`)
`period`	No	Date range to filter (e.g., "last 30 days", "April 2026")

Step-by-Step Instructions

1. Load Notes Page

Run agent-browser to open the Substack notes page:

agent-browser open "{url}"

2. Scroll and Fetch Content

Use agent-browser to scroll the page downwards recursively to load older notes.
Stop scrolling once the posts' dates go beyond the target period or no new elements load.
Extract the following data points for each note:
- Date/Timestamp
- Note Text (first 100 characters for identification)
- Likes Count
- Comments Count
- Restacks Count
- Direct URL Link

3. Generate Metrics Spreadsheet

Filter out restacks from other authors to avoid noise.
Write the parsed entries into a structured Excel file (substack_notes_metrics.xlsx).
Format the sheet with frozen headers, bold text, and column width auto-fitting.

4. Output Summary

Provide a brief overview of the top 3 best-performing notes by engagement (likes + restacks) and the link to download the generated .xlsx file.

---name: substack-notes-scraperdescription: Scrape Substack Notes metrics for a specific author and time period. Uses agent-browser to load the page, scrolls to fetch all posts, extracts metrics (likes, comments, restacks), and formats them as a structured spreadsheet (.xlsx). Use when the user runs /substack-notes-scraper, asks to scrape/analyze Substack notes, or wants a metrics report on Substack posts.---# Substack Notes Scraper (`substack-notes-scraper`)Scrapes author notes from Substack and compiles dates, text, likes, comments, restacks, and links into a structured spreadsheet.## Prerequisites- Requires `agent-browser` and a spreadsheet writing utility (like Python's `openpyxl` or `pandas`).## Parameters| Parameter | Required | Description ||---|---|---|| `url` | Yes | The Substack notes page URL (e.g. `https://substack.com/@username/notes`) || `period` | No | Date range to filter (e.g., "last 30 days", "April 2026") |## Step-by-Step Instructions### 1. Load Notes PageRun `agent-browser` to open the Substack notes page:```bashagent-browser open "{url}"```### 2. Scroll and Fetch Content- Use `agent-browser` to scroll the page downwards recursively to load older notes.- Stop scrolling once the posts' dates go beyond the target `period` or no new elements load.- Extract the following data points for each note: - **Date/Timestamp** - **Note Text** (first 100 characters for identification) - **Likes Count** - **Comments Count** - **Restacks Count** - **Direct URL Link**### 3. Generate Metrics Spreadsheet- Filter out restacks from other authors to avoid noise.- Write the parsed entries into a structured Excel file (`substack_notes_metrics.xlsx`).- Format the sheet with frozen headers, bold text, and column width auto-fitting.### 4. Output SummaryProvide a brief overview of the top 3 best-performing notes by engagement (likes + restacks) and the link to download the generated `.xlsx` file.

Frequently asked questions