Add web-automation skill

- Browse and scrape web pages using Playwright with Camoufox anti-detection browser
- Supports automated web workflows, authenticated sessions, and bot protection bypass
- Includes scripts for browse, scrape, auth, and local app scanning
- Updated README with skill documentation and system library requirements

README.md

@@ -22,6 +22,26 @@ stef-openclaw-skills/
 | Skill | Purpose | Path |
 |---|---|---|
 | `gitea-api` | Interact with any Gitea instance via REST API (create repos, issues, PRs, releases, branches, clone) without `tea` CLI. | `skills/gitea-api` |
+| `web-automation` | Browse and scrape web pages using Playwright with Camoufox anti-detection browser. For automating web workflows, extracting page content to markdown, handling authenticated sessions, or scraping websites with bot protection. | `skills/web-automation` |
+
+## Skill-Specific Requirements
+
+### web-automation
+
+The `web-automation` skill requires Node.js packages to be installed. When compiling OpenClaw with support for this skill, add the required system libraries:
+
+```bash
+# For Playwright + Camoufox browser dependencies
+export OPENCLAW_DOCKER_APT_PACKAGES="ffmpeg jq curl libnss3 libatk1.0-0 libatk-bridge2.0-0 libcups2 libdrm2 libxkbcommon0 libxcomposite1 libxdamage1 libxfixes3 libxrandr2 libgbm1 libasound2"
+```
+
+After installing the skill, run the first-time setup:
+
+```bash
+cd ~/.openclaw/workspace/skills/web-automation/scripts
+pnpm install
+npx camoufox-js fetch
+```
 
 ## Install Ideas