Skip to main content
skill CX Codex

web-to-markdown · softaworks — Claude Code skill: what it does, how to install

web-to-markdown converts JavaScript-heavy web pages into clean Markdown via a local browser CLI. Helpful for archiving articles and docs without layout junk.

MIT 796 installs ★ 2,707 updated 2026-03-05

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add softaworks/agent-toolkit --skill web-to-markdown -a claude-code
Open on GitHub

What web-to-markdown does

The skill turns dynamic pages into Markdown using the local web2md utility. It drives an installed Chromium browser through puppeteer-core, strips extraneous layout elements using Readability, and transforms the body with Turndown while cleaning up links.

A strict gate protects activation. The agent halts and refuses to run unless your prompt includes use the skill web-to-markdown or use a skill web-to-markdown.

Execution fails if web2md is absent from your PATH when checked by command -v web2md. For gated content or verification screens, passing --interactive launches a visible browser window with --user-data-dir so you can solve checks manually before parsing starts.

What it helps with

  • extract readable article text from JavaScript-rendered sites
  • pass manual login checks or captchas before saving content
  • strip banners and navbars from web pages into clean Markdown
  • batch save several pages into auto-named Markdown files

Example prompts for the agent

  • use the skill web-to-markdown: convert the page to ./page.md
  • use the skill web-to-markdown: print page contents to stdout
  • use the skill web-to-markdown: run interactive mode with profile ./tmp/web2md-profile and save to ./out/

How to install web-to-markdown

1Skills CLI (Vercel)

npx skills add softaworks/agent-toolkit --skill web-to-markdown -a claude-code

2Manually: put the files in place

~/.claude/skills/web-to-markdown/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/web-to-markdown/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about web-to-markdown

How do I install web-to-markdown in Claude Code?

Run npx skills add softaworks/agent-toolkit --skill web-to-markdown -a claude-code in your terminal.

What does the web-to-markdown skill do?

It controls a local Chromium browser using web2md, extracts text via Readability, and outputs Markdown with Turndown.

Why does the skill ignore generic conversion prompts?

It enforces a mandatory activation trigger. The assistant will refuse the task unless the request contains the exact phrase use the skill web-to-markdown.

Source text

SKILL.md · MIT
---
name: web-to-markdown
description: "Use ONLY when the user explicitly says: 'use the skill web-to-markdown ...' (or 'use a skill web-to-markdown ...'). Converts webpage URLs to clean Markdown by calling the local web2md CLI (Puppeteer + Readability), suitable for JS-rendered pages."
metadata:
  version: 0.1.0
---

# web-to-markdown

Convert web pages to clean Markdown by driving a locally installed browser (via `web2md`).

## Hard trigger gate (must enforce)

This skill MUST NOT be used unless the user explicitly wrote **exactly** a phrase like:
- `use the skill web-to-markdown ...`
- `use a skill web-to-markdown ...`

If the user did not explicitly request this skill by name, stop and ask them to re-issue the request including: `use the skill web-to-markdown`.

## What this skill does

- Handles JS-rendered pages (Puppeteer → user Chrome).
- Works best with Chromium-family browsers (Chrome/Chromium/Brave/Edge) via `puppeteer-core`.
- Extracts main content (Readability).
- Converts to Markdown (Turndown) with cleaned links and optional YAML frontmatter.

## Non-goals

- Do not use Playwright or other browser automation stacks; the mechanism is `web2md`.

## Inputs you should collect (ask only if missing)

- `url` (or a list of URLs)
- Output preference:
  - Print to stdout (`--print`), OR
  - Save to a file (`--out ./file.md`), OR
  - Save to a directory (`--out ./some-dir/` to auto-name by page title)
- Optional rendering controls for tricky pages:
  - `--chrome-path <path>` (if Chrome auto-detection fails)
  - `--interactive` (show Chrome and pause so the user can complete human checks/login, then press Enter)
  - `--wait-until load|domcontentloaded|networkidle0|networkidle2`
  - `--wait-for '<css selector>'`
  - `--wait-ms <milliseconds>`
  - `--headful` (debug)
  - `--no-sandbox` (sometimes required in containers/CI)
  - `--user-data-dir <dir>` (login/session; use a dedicated profile directory)

## Workflow

1) Confirm the user explicitly invoked the skill (`use the skill web-to-markdown`).
2) Validate URL(s) start with `http://` or `https://`.
3) Ensure `web2md` is installed:
   - Run: `command -v web2md`
   - If missing, instruct the user to install it (assume the project exists at `~/workspace/softaworks/projects/web2md`):
     - `cd ~/workspace/softaworks/projects/web2md && npm install && npm run build && npm link`
     - Or: `cd ~/workspace/softaworks/projects/web2md && npm install && npm run build && npm install -g .`
4) Convert:
   - Single URL → file:
     - `web2md '<url>' --out ./page.md`
   - Single URL → auto-named file in directory:
     - `mkdir -p ./out && web2md '<url>' --out ./out/`
   - Human verification / login walls (interactive):
     - `mkdir -p ./out && web2md '<url>' --interactive --user-data-dir ./tmp/web2md-profile --out ./out/`
     - Then: complete the check in the browser window and press Enter in the terminal to continue.
   - Print to stdout:
     - `web2md '<url>' --print`
   - Multiple URLs (batch):
     - Create output dir (e.g. `./out/`) then run one `web2md` command per URL using `--out ./out/`
5) Validate output:
   - If writing files, verify they exist and are non-empty (e.g. `ls -la <path>` and `wc -c <path>`).
6) Return:
   - The saved file path(s), or the Markdown (stdout mode).

## Defaults (recommended)

- For most pages: `--wait-until networkidle2`
- For heavy apps: start with `--wait-until domcontentloaded --wait-ms 2000`, then add `--wait-for 'main'` (or another stable selector) if needed.

© softaworks · MIT · softaworks/agent-toolkit

Similar skills

All skills for Browser and scraping →

web-to-markdown by other authors comes first.

web-to-markdown rookie-ricardo The web-to-markdown skill extracts web pages as cleaned Markdown, choosing a fetch route by site. Use it when an agent needs to read an article or YouTube content from a link. CX Codex +1 249installs baoyu-url-to-markdown JimLiu baoyu-url-to-markdown fetches webpages via Chrome CDP and converts their content into Markdown. Runs when an agent needs to archive articles, social threads, or video transcripts. CX Codex +1 31,000installs Web to Markdown jackwener Web to Markdown is a Claude Code skill that saves web pages into clean Markdown files using an active browser tab. Runs when asked to clip, export, or archive online material. CX Codex +1 ★ 239repo stars Universal Screenshot MCP sethbang Universal Screenshot MCP — an MCP server providing web page captures via Puppeteer and desktop screenshots across macOS, Linux, and Windows. CX Codex +1 ★ 37repo stars anti-detect-browser antibrow anti-detect-browser is a Claude Code skill that launches Chromium with a genuine device fingerprint through Playwright API. Each profile persists across runs for testing, scraping, and multi-account work. CX Codex +1 168,800installs dev-browser SawyerHood dev-browser is a skill for controlling a real Chrome with short Puppeteer scripts. Named pages persist between runs, so browser automation can continue from the same state. CX Codex +1 2,600installs puppeteer-automation Mindrally puppeteer-automation — a skill that gives your agent working patterns for Puppeteer: navigation, clicks, screenshots, PDFs and network interception in headless Chrome. CX Codex +1 1,900installs

From the same set79

The whole set →
feedback-mastery feedback-mastery guides developers and leads through difficult workplace conversations using the SBI and Preparation-Delivery-Follow-up frameworks. Helps turn friction into factual feedback. CX Codex +1 4,000installs gemini Runs Gemini CLI for code reviews, architecture analysis and processing context over 200k tokens. Activated on user request, defaults to Gemini 3 Pro. CX Codex +1 4,000installs lesson-learned lesson-learned analyzes recent git changes and extracts engineering takeaways directly from your code. Helpful when you want to reflect on architectural choices or review what a feature branch teaches. CX Codex +1 3,000installs gepetto gepetto turns a Markdown spec into an implementation plan, using research, user interviews, and reviews from Gemini and Codex. Use it before building a feature that needs careful planning. CX Codex +1 1,600installs communication-excellence-coach communication-excellence-coach reviews communication drafts, calibrates tone for different audiences, and runs roleplay practice for difficult conversations. CX Codex ★ 2,707repo stars sync-branch Syncs a feature branch with the latest main via rebase. Runs on /sync-branch and updates the PR with force-push. CX Codex +1 ★ 2,707repo stars compose-email compose-email — a command for drafting professional emails using the What-Why-How framework. Provide context and get a ready-to-send draft with clear structure, matching tone, and concrete next steps. CX Codex +1 ★ 2,707repo stars viral-tweet viral-tweet converts rough draft thoughts into high-engagement posts tailored to the recommendation system of X. CX Codex +1 ★ 2,707repo stars

Project sponsors

Companies that keep this analytics open