How do I install the Create Md From Browsermcp Snapshot skill?

Run npx skillmds@latest add derailed-dash/create-md-from-browsermcp-snapshot 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 Create Md From Browsermcp Snapshot 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 Create Md From Browsermcp Snapshot?

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 Create Md From Browsermcp Snapshot free to use?

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

Who published Create Md From Browsermcp Snapshot?

derailed-dash (@derailed-dash) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Create Md From Browsermcp Snapshot by derailed-dash

Name: Create Md From Browsermcp Snapshot
Author: derailed-dash

Create Md From Browsermcp Snapshot

Extracts and converts BrowserMCP accessibility tree snapshots into clean, high-fidelity Markdown documents with correct structures (headings, lists, tables, blockquotes, formatting, and links). Use when the user asks to create a markdown document from a webpage; especially if they ask to do it with BrowserMCP.

derailed-dash 2c2d961 2 files · 13.6 KB Updated Sep 17, 2026

File contents

Create Markdown from BrowserMCP Snapshot

This skill converts a raw accessibility tree snapshot captured by BrowserMCP (via the browser_snapshot tool) into a beautifully formatted, high-fidelity Markdown document.

Prerequisites & BrowserMCP Check

[!IMPORTANT] This skill strictly requires the BrowserMCP server to be installed and available in the environment.

Before attempting to navigate a site or capture a snapshot:

Verify Tool Availability: Check whether the browsermcp server and its browser_snapshot tool are present in your active MCP tools list.
If BrowserMCP is NOT Found:
- Stop execution immediately and notify the user.
- Guide the user to install BrowserMCP and configure the browsermcp server entry in their MCP configuration (e.g. in ~/.gemini/config/mcp_config.json or Antigravity MCP settings).
- Request that the user re-run the task once BrowserMCP is enabled and available.

When to Use

Use this skill when:

You have captured a webpage's accessibility tree YAML using the BrowserMCP browser_snapshot tool.
You need to generate a structured, high-fidelity Markdown (.md) representation of the page content.
You want to extract clean lists, tables, headers, blockquotes, and link destinations from the captured page layout.

Note: This skill complements browser navigation using the BrowserMCP tool. It is NOT intended to be used with other browser navigation tools, such as Playwright or the Antigravity built-in browser agent. Be sure to be explicit about what tools to use and what to avoid.

How it Works

The skill runs a Python parser that reads the captured accessibility tree YAML snapshot, builds a parent-child node hierarchy, and recursively converts the tags and properties into Markdown text.

Folder Structure

create-md-from-browsermcp-snapshot/
├── SKILL.md
└── scripts/
    └── parse_snapshot.py

Execution Procedure

Verify BrowserMCP: Confirm browsermcp is installed as detailed in Prerequisites & BrowserMCP Check. If absent, guide the user to install it.
Capture Snapshot: Navigate to the target URL using browser_navigate and run browser_snapshot to output the accessibility tree YAML.
Execute Parser: Run the Python script parse_snapshot.py passing the absolute path of the captured snapshot text file as an argument and specifying the output Markdown path:

python3 ./create-md-from-browsermcp-snapshot/scripts/parse_snapshot.py --input <snapshot_path> --output <markdown_path> [--start-heading <heading_title>] [--end-marker <footer_text>]

---name: create-md-from-browsermcp-snapshotdescription: Extracts and converts BrowserMCP accessibility tree snapshots into clean, high-fidelity Markdown documents with correct structures (headings, lists, tables, blockquotes, formatting, and links). Use when the user asks to create a markdown document from a webpage; especially if they ask to do it with BrowserMCP.---# Create Markdown from BrowserMCP SnapshotThis skill converts a raw accessibility tree snapshot captured by BrowserMCP (via the `browser_snapshot` tool) into a beautifully formatted, high-fidelity Markdown document.## Prerequisites & BrowserMCP Check> [!IMPORTANT]> This skill strictly requires the **BrowserMCP** server to be installed and available in the environment.Before attempting to navigate a site or capture a snapshot:1. **Verify Tool Availability**: Check whether the `browsermcp` server and its `browser_snapshot` tool are present in your active MCP tools list.2. **If BrowserMCP is NOT Found**: - Stop execution immediately and notify the user. - Guide the user to install BrowserMCP and configure the `browsermcp` server entry in their MCP configuration (e.g. in `~/.gemini/config/mcp_config.json` or Antigravity MCP settings). - Request that the user re-run the task once BrowserMCP is enabled and available.## When to UseUse this skill when:- You have captured a webpage's accessibility tree YAML using the BrowserMCP `browser_snapshot` tool.- You need to generate a structured, high-fidelity Markdown (`.md`) representation of the page content.- You want to extract clean lists, tables, headers, blockquotes, and link destinations from the captured page layout.Note: This skill complements browser navigation using the BrowserMCP tool. It is NOT intended to be used with other browser navigation tools, such as Playwright or the Antigravity built-in browser agent. Be sure to be explicit about what tools to use and what to avoid.## How it WorksThe skill runs a Python parser that reads the captured accessibility tree YAML snapshot, builds a parent-child node hierarchy, and recursively converts the tags and properties into Markdown text.### Folder Structure```create-md-from-browsermcp-snapshot/├── SKILL.md└── scripts/ └── parse_snapshot.py```### Execution Procedure1. **Verify BrowserMCP**: Confirm `browsermcp` is installed as detailed in [Prerequisites & BrowserMCP Check](#prerequisites--browsermcp-check). If absent, guide the user to install it.2. **Capture Snapshot**: Navigate to the target URL using `browser_navigate` and run `browser_snapshot` to output the accessibility tree YAML.3. **Execute Parser**: Run the Python script `parse_snapshot.py` passing the absolute path of the captured snapshot text file as an argument and specifying the output Markdown path:```bashpython3 ./create-md-from-browsermcp-snapshot/scripts/parse_snapshot.py --input <snapshot_path> --output <markdown_path> [--start-heading <heading_title>] [--end-marker <footer_text>]```

Frequently asked questions