html2md
by saikatkumardey
Web & Frontend DevelopmentBrief
Convert HTML pages to clean, agent-friendly markdown using Readability + Turndown.
Description
What This Skill Does
Converts HTML pages to clean markdown using Mozilla Readability for content extraction and Turndown for conversion. Strips navigation, ads, footers, cookie banners, and other noise. Supports URL fetching, local files, stdin, token budgeting, and JSON output.
Readability-based extraction removes nav and ad noise that raw HTML fetchers leave in, so token usage stays low and content arrives clean for LLM consumption.
When to Use It
- Extracting article content from news sites for LLM summarization
- Converting documentation pages to markdown for offline reference
- Feeding cleaned web content to sub-agents in research pipelines
- Token-budgeted page extraction to fit LLM context windows
- Batch scraping blog posts in cron-based agent workflows
Example Workflow
User asks: Summarize the key points from https://paulgraham.com/greatwork.html, keeping it under 2000 tokens
- 1
Run html2md --max-tokens 2000 https://paulgraham.com/greatwork.html
- 2
Readability isolates the main article body, discarding nav, footers, and sidebars
- 3
Turndown converts the cleaned HTML to markdown
- 4
Post-processing removes remaining noise and truncates at the 2000-token budget
- 5
Agent receives clean markdown and generates the summary
Clean markdown of the article body truncated to 2000 tokens, ready for summarization
Installation
clawhub install saikatkumardey/html2mdRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.