Automated summary

Captures a web page using the sitecap CLI (npx) and then summarizes the capture: screenshot, accessibility tree, HTML, network, console, storage and performance data.

Strengths

A single command produces a complete, readable capture folder (meta.json, screenshot.png, accessibility.txt, console.json, performance.json, network.json).
Options adapt the capture: mobile viewport, selected data types, multi-page crawl, or a Chrome profile for authenticated pages.
The skill enforces an ordered read of the captured files and a concise report, then answers the user's question from that data.

When to use it

Reach for it when you need to inspect a deployed page's actual state: console errors, failed requests, accessibility structure or load metrics.

When not to use it

Skip it for large-scale visual comparison or automated regression testing, which it does not provide.

Security analysis

Caution

Quality score72/100

Nothing here is overtly malicious: there is no rm -rf, no curl|sh, no base64 payload, and no instruction to send data to an external endpoint. However, the skill does execute an unpinned third-party npm package, launches a browser, and can load the user's real Chrome profile and capture authenticated traffic into plaintext files. These are powerful but legitimate capabilities, so it warrants caution and version pinning rather than a risky rating.

Findings

•Runs `npx sitecap` with no pinned version, so arbitrary/latest code from the npm registry is downloaded and executed on each invocation (supply-chain risk, no integrity check).
•`--profile Default` reuses the user's real Chrome profile, potentially exposing cookies, saved credentials, and logged-in sessions to a third-party tool and to the capture output directory.
•Captures (network.json, storage, HTML) of possibly authenticated or internal pages are written to /tmp/sitecap-capture with no redaction guidance, so tokens/PII may land in files the agent then reads into context.
•No domain/URL allowlist is documented, and `--crawl` can be pointed at internal or localhost hosts (SSRF-style reach) from the agent's network position.
•Installs/launches a full headless browser via `--launch`, a heavyweight privileged action the user may not expect from a 'capture' command.

How this analysis is made

Examples

Quick page check

/capture https://example.com

Mobile viewport capture

/capture https://example.com -v 375x812

Authenticated dashboard capture

/capture https://myapp.com/dashboard --profile Default

/capture

Name: Capture Web Page
Author: Skills Guide Bot

Capture a web page using sitecap — screenshot, accessibility tree, HTML, network, console, storage, and performance data.

Usage

/capture <url> [options]

Instructions

When this skill is invoked, run sitecap to capture the specified URL:

npx sitecap <url> --launch -o /tmp/sitecap-capture

After capture completes, read and summarize the key files:

Read the meta.json to confirm what was captured
Read screenshot.png to see the page visually
Read accessibility.txt for the page structure
Read console.json for any errors
Read performance.json for load metrics
Read network.json for request summary (count, failed requests)

Report findings concisely. If the user asked a question about the page, answer it using the captured data.

Options

Pass additional flags after the URL:

--crawl --max-pages N — crawl the site
-t screenshot,accessibility — capture specific types only
-v 375x812 — mobile viewport
--profile Default — use Chrome profile for authenticated pages

Examples

/capture https://example.com
/capture https://example.com -v 375x812
/capture https://myapp.com/dashboard --profile Default

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/capture-web-page-mrwakbu8/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/capture-web-page-mrwakbu8' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/capture-web-page-mrwakbu8/download' --output '.skill-downloads/capture-web-page-mrwakbu8/SKILL.md.part' && mv '.skill-downloads/capture-web-page-mrwakbu8/SKILL.md.part' '.skill-downloads/capture-web-page-mrwakbu8/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/capture-web-page-mrwakbu8/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.