Convert To Markdown
Pull clean markdown from any URL with ezycopy—fast HTTP by default or headless Chrome when the page is JS-rendered or authenticated.
Overview
Convert-to-markdown is an agent skill most often used in Idea (also Validate scope, Build docs) that extracts clean markdown from URLs via the ezycopy CLI.
Install
npx skills add https://github.com/gupsammy/claudest --skill convert-to-markdownWhat is this skill?
- Three-phase flow: choose extraction mode, run ezycopy, retry with --browser on empty or short output
- Default fast HTTP fetch; --browser for JS SPAs, Twitter/X, paywalls, and cookie-auth pages
- Flags: clipboard (-c), output path (-o), --no-images, timeout (-t), default 30s
- In browser mode run foreground without stderr redirected into stdout (2>&1 breaks capture)
- Triggered by convert/extract/scrape URL phrasing and argument-hint URL
- Default timeout: 30s (-t)
- Phases: mode selection → execute ezycopy → handle failure with --browser
Adoption & trust: 1 installs on skills.sh; 253 GitHub stars; 0/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You have a URL full of ads and layout noise and need dependable markdown for research or docs without writing a one-off scraper.
Who is it for?
Solo builders capturing competitor pages, articles, or JS-heavy sites into markdown for specs, notes, or content repurposing.
Skip if: Bulk crawling entire domains, bypassing paywalls without legitimate access, or pages where you already have an official API export.
When should I use this skill?
User asks to convert this page to markdown, extract/scrape a webpage, save an article from a URL, or provides a link for clean content.
What do I get? / Deliverables
You get clipboard or file-ready markdown from the chosen URL, with a clear fallback to headless Chrome when HTTP-only extraction fails.
- Markdown on clipboard (-c) or saved file/directory (-o)
- Clean text with optional images stripped (--no-images)
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Competitive and reference research starts with grabbing readable source material from the web before you scope or document your own product. Research subphase is where you capture external articles, docs, and pages as structured markdown inputs for later specs and content.
Where it fits
Save a competitor landing page as markdown before you draft positioning.
Extract feature lists from rival docs pages into your research folder.
Pull a long-form article that defines the problem space into notes for a prototype brief.
Archive an external API tutorial as markdown inside your repo docs.
Capture a reference post cleanly before rewriting it for your newsletter.
How it compares
Use structured ezycopy extraction instead of asking the model to hallucinate page content from memory.
Common Questions / FAQ
Who is convert-to-markdown for?
Indie builders and agents who need faithful web text as markdown for research, documentation, or content workflows.
When should I use convert-to-markdown?
In Idea research when saving competitor or reference URLs; during Validate when grounding scope in external writeups; in Build docs when archiving third-party guides—whenever the user says convert this page to markdown or provides a URL to extract.
Is convert-to-markdown safe to install?
It runs Bash (ezycopy, curl) and may launch headless Chrome with network access; review the Security Audits panel on this Prism page before granting tools on sensitive machines.
SKILL.md
READMESKILL.md - Convert To Markdown
# Web-to-Markdown via EzyCopy Extract clean markdown from any URL using the `ezycopy` CLI. ## Phase 1: Determine Extraction Mode Default mode uses fast HTTP fetch. Add `--browser` when the page relies on client-side JavaScript to render its content or when authentication cookies are required — the default fetcher only sees the raw HTML response, not the JS-rendered DOM. Common `--browser` cases: Twitter/X, single-page applications, paywalled content. ### Flags - `-c` — copy output to clipboard - `-o <path>` — save to file or directory - `--browser` — use headless Chrome for JS-rendered or authenticated pages - `--no-images` — strip image links - `-t <duration>` — timeout (default: 30s) ## Phase 2: Execute Run `ezycopy <URL> [flags]` with the chosen mode. In `--browser` mode: run as a foreground process and do not redirect stderr with `2>&1`. Chrome outputs diagnostic messages to stderr that should flow naturally rather than polluting stdout capture. ## Phase 3: Handle Failure If the output is empty or suspiciously short and `--browser` was not used, retry with `--browser` — the site likely requires JS rendering. If `ezycopy` is not found, ask the user before installing: ``` curl -sSL https://raw.githubusercontent.com/gupsammy/EzyCopy/main/install.sh | sh ``` ## Phase 4: Deliver Present the extracted markdown to the user. If the user requested a file save, use `-o`. If they requested clipboard, use `-c`. When no explicit destination was given, display the content directly.