webpage-screenshotter — Claude Code skill: what it does, install
webpage-screenshotter captures full-page website screenshots with Playwright and returns the image as Base64. Useful when an agent needs a visual copy of a URL.
no license 167 installs ★ 2 updated 2025-11-23
npx skills add rkreddyp/investrecipes --skill webpage-screenshotter -a claude-codeWhat webpage-screenshotter does
The skill opens a URL in Chromium through Playwright and writes a full-page capture to screenshot.png. Its main flow waits for domcontentloaded, reloads the page, then encodes the PNG as Base64. It can also write to a custom path or process several URLs in one run.
The default setup uses a 1920x1080 viewport, a 0.5 device scale factor, and a 120000 millisecond timeout. Pages that need more time can use load or networkidle, with an optional visible-element wait. A navigation timeout is caught before the flow continues.
The Python implementation imports playwright, so that package must be available in the runtime before the example can run. That dependency is the main setup point to check in a local environment.
What it helps with
- capture a complete webpage image
- write a screenshot to a chosen path
- turn PNG data into Base64
- collect screenshots from multiple URLs
Example prompts for the agent
- Capture a full-page screenshot of
https://example.comand return it as Base64. - Save a screenshot of
https://example.comtohomepage.pngafter all page resources load. - Process this list of URLs and return a Base64 result for each page.
How to install webpage-screenshotter
1Skills CLI (Vercel)
npx skills add rkreddyp/investrecipes --skill webpage-screenshotter -a claude-code2Manually: put the files in place
~/.claude/skills/webpage-screenshotter/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/webpage-screenshotter/
1Skills CLI (Vercel)
npx skills add rkreddyp/investrecipes --skill webpage-screenshotter -a codex2Manually: put the files in place
.agents/skills/webpage-screenshotter/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rkreddyp/investrecipes --skill webpage-screenshotter -a cursor2Manually: put the files in place
.cursor/skills/webpage-screenshotter/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rkreddyp/investrecipes .claude/skills/webpage-screenshotter2Manually: put the files in place
.github/skills/webpage-screenshotter/SKILL.md1Skills CLI (Vercel)
npx skills add rkreddyp/investrecipes --skill webpage-screenshotter -a gemini-cli2Platform CLI
gemini skills install https://github.com/rkreddyp/investrecipes --path .claude/skills/webpage-screenshotterManually: put the files in place
.devin/skills/webpage-screenshotter/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add rkreddyp/investrecipes --skill webpage-screenshotter -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about webpage-screenshotter
How do I install webpage-screenshotter in Claude Code?
Run npx skills add rkreddyp/investrecipes --skill webpage-screenshotter -a claude-code, then check ~/.claude/skills/webpage-screenshotter/SKILL.md.
What does webpage-screenshotter do?
It loads a URL with Chromium and Playwright, captures the complete page, writes a PNG, and returns the image data as Base64. Custom output paths, batches, and alternative page-wait modes are supported.
What is required to run the Python example?
The runtime needs the playwright package, which the Python implementation imports.