feat: add safe Playwright scraper skill

skills/playwright-safe/SKILL.md

@@ -0,0 +1,68 @@
+---
+name: playwright-safe
+description: Use when a page needs JavaScript rendering or moderate anti-bot handling and the agent should use a single local Playwright scraper instead of generic web fetch tooling.
+---
+
+# Playwright Safe
+
+Single-entry Playwright scraper for dynamic or moderately bot-protected pages.
+
+## When To Use
+
+- Page content depends on client-side rendering
+- Generic `scrape` or `webfetch` is likely to miss rendered content
+- The task needs one direct page extraction with lightweight stealth behavior
+
+## Do Not Use
+
+- For multi-step browser workflows with login/stateful interaction
+- For site-specific automation flows
+- When the page can be handled by a simpler built-in fetch path
+
+## Setup
+
+```bash
+cd ~/.openclaw/workspace/skills/playwright-safe
+npm install
+npx playwright install chromium
+```
+
+## Command
+
+```bash
+node scripts/playwright-safe.js "<URL>"
+```
+
+Only pass a user-provided `http` or `https` URL.
+
+## Options
+
+```bash
+WAIT_TIME=5000 node scripts/playwright-safe.js "<URL>"
+SCREENSHOT_PATH=/tmp/page.png node scripts/playwright-safe.js "<URL>"
+SAVE_HTML=true node scripts/playwright-safe.js "<URL>"
+HEADLESS=false node scripts/playwright-safe.js "<URL>"
+USER_AGENT="Mozilla/5.0 ..." node scripts/playwright-safe.js "<URL>"
+```
+
+## Output
+
+The script prints JSON only, suitable for direct agent consumption. Fields include:
+
+- `requestedUrl`
+- `finalUrl`
+- `title`
+- `content`
+- `metaDescription`
+- `status`
+- `elapsedSeconds`
+- `challengeDetected`
+- optional `screenshot`
+- optional `htmlFile`
+
+## Safety Notes
+
+- Stealth and anti-bot shaping are retained
+- Chromium sandbox remains enabled
+- No sandbox-disabling flags are used
+- No site-specific extractors or foreign tool dependencies are used