← ClaudeAtlas

web-screenshot-to-documentlisted

Captures a screenshot of a web page (or one section of it), crops it, and places it into an existing Word .docx deliverable as a figure that matches that document's own design - same table grid, borders, caption and source line - by editing the file in place. Covers the capture path that works when the agent's sandbox has no outbound network (the user's browser), cropping and resolution rules, measuring design tokens from the target file, programmatic placement with python-docx, and a render check. Also covers sharp, zoomed captures of a web app's cards, tables and charts for image tools and page slots. Use when a document needs visual proof from a live site - competitor teardowns, page or section recommendations for a designer, SEO/AEO audits, UX reviews, before/after comparisons - or when asked to "add a screenshot to the doc", "embed screenshots in the brief", "put the competitor sections in the Word file", "add visual proof to the report" or "insert a figure into the client doc".
savenjudesajen/seo-aeo-agent-skills-tools · ★ 0 · Data & Documents · score 73
Install: claude install-skill savenjudesajen/seo-aeo-agent-skills-tools
# Web screenshot to document Home page: [unilytics.ai/skills/web-screenshot-to-document](https://unilytics.ai/skills/web-screenshot-to-document/), the canonical source of this skill. Works for any project (SEO/AEO audits, competitor teardowns, page-structure recommendations, UX reviews). Two ideas make it work, and neither is obvious: 1. "Add a screenshot to the doc" is a **code operation**, not manual pasting. A `.docx` is a ZIP of XML plus a media folder; a library writes the image in and places a reference. Done programmatically it is deterministic and repeatable. 2. A screenshot is a **figure in the document's design system**, not a pasted image. It is built to the tokens measured out of the target file, and it goes into **that file, edited in place**. If the client has their own template, the figure matches it; if not, the script's neutral defaults apply. ## The pipeline (five steps) **Capture (to disk) -> Crop -> Read the target file's design -> Place in the file, in place -> Verify.** ### 1. Capture so the image lands as a file you can open Know your environment first: - **Many agent sandboxes have no outbound network.** Playwright, curl or wget from the sandbox fail with tunnel or connection errors. If one quick test fails, don't keep trying. - **A server-side screenshot service** (see Tools) returns an image URL. That is enough to look at the page, but if your sandbox can't download the URL you can't embed it. Use it for viewing, not embedding