← Back to Skills Marketplace
188
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install sjht-web-screenshot
Description
Capture screenshots of web pages running on local or remote servers using Puppeteer in headless Chromium. Use when user asks to screenshot web pages, capture...
Usage Guidance
This skill appears to do what it says: run a Node script that drives headless Chromium to capture screenshots and optionally perform SPA login. Before using it: 1) Verify and install dependencies (Node, puppeteer-core, and a Chromium binary at the expected path) since the registry metadata omitted them. 2) Do not point baseUrl to untrusted third-party sites — the script runs arbitrary JS in-page (including calling app internals) which could access page-local secrets/cookies. 3) Protect credentials: the login credentials live in the config JSON you pass; treat that file securely and avoid storing plaintext secrets in shared locations (use ephemeral files or limited-permission directories). 4) Avoid writing outputDir as root-owned system paths unless intended. 5) Consider running the tool in a sandboxed container or VM because Chromium is launched with --no-sandbox (common for headless automation but reduces process isolation). If you want stronger assurance, request the publisher to declare required binaries in registry metadata and provide a vetted installation path for puppeteer-core.
Capability Analysis
Type: OpenClaw Skill
Name: sjht-web-screenshot
Version: 1.0.0
The skill is a utility designed to capture screenshots of web pages, specifically targeting Single Page Applications (SPAs) that require authentication. It uses Puppeteer and Node.js to automate browser tasks, including form-based login and direct interaction with Vue/Pinia state stores to maintain session state during navigation. The code in `scripts/screenshot.js` and the instructions in `SKILL.md` are well-documented and align with the stated functionality, with no evidence of data exfiltration, backdoors, or malicious prompt injection.
Capability Assessment
Purpose & Capability
The name/description, SKILL.md, and the included Node script all align: the tool captures screenshots, supports SPA form login and direct Pinia store login, and writes PNGs/result.json. One inconsistency: the registry metadata lists no required binaries/env but SKILL.md and the script clearly require Node, puppeteer-core, and a Chromium binary (e.g. /usr/bin/chromium-browser). This is likely an omission in metadata rather than malicious.
Instruction Scope
SKILL.md instructs running the included script with a JSON config file; the script reads only that provided config, navigates to baseUrl/pages, and writes screenshots/result.json to the configured outputDir. It executes arbitrary JS inside the target pages (page.evaluate) to set input values, call Pinia store methods, and invoke Vue router — this is necessary for the claimed SPA login/navigation features but means the skill will run code inside whatever page you point it to (so pointing at untrusted sites or injecting untrusted config could expose page-local secrets).
Install Mechanism
This is an instruction-only skill with a shipped script; there is no install hook or remote download. That keeps risk low. The SKILL.md asks you to ensure puppeteer-core and Chromium are present (no installer provided), so the operator must install those dependencies manually.
Credentials
The skill requests no environment variables or credentials from the runtime environment. The only credentials it uses are those you provide in the config JSON (username/password or storeLogin args). There are no other undeclared secrets or credentials in the files.
Persistence & Privilege
always is false and the skill doesn't attempt to modify agent/system-wide configuration. It creates files in the supplied outputDir (as expected). It does run Chromium with --no-sandbox flags (common for CI/headless usage) — not a privilege escalation request from the skill, but an operational note.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install sjht-web-screenshot - After installation, invoke the skill by name or use
/sjht-web-screenshot - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
v1.0.0 — Major overhaul: Migrated from shell script to Node.js with Puppeteer, introducing robust SPA login and advanced screenshot automation.
- Replaced shell script (screenshot.sh) with a Node.js script (screenshot.js) using Puppeteer for modern browser control.
- Supports full login automation for Vue/React/Angular SPAs via CSS selector-based or store-based methods.
- Screenshots are configured via JSON, enabling batch capture with per-page wait, naming, and descriptions.
- Automatically generates a result.json metadata file with detailed capture info.
- Enhanced troubleshooting and advanced config options, such as custom login flows and capturing the login page itself.
Metadata
Frequently Asked Questions
What is sjht-web-screenshot?
Capture screenshots of web pages running on local or remote servers using Puppeteer in headless Chromium. Use when user asks to screenshot web pages, capture... It is an AI Agent Skill for Claude Code / OpenClaw, with 188 downloads so far.
How do I install sjht-web-screenshot?
Run "/install sjht-web-screenshot" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is sjht-web-screenshot free?
Yes, sjht-web-screenshot is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does sjht-web-screenshot support?
sjht-web-screenshot is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created sjht-web-screenshot?
It is built and maintained by Aowind (@aowind); the current version is v1.0.0.
More Skills