Refresh property assessor and web automation docs

docs/web-automation.md

@@ -15,6 +15,7 @@ Automated web browsing and scraping using Playwright-compatible CloakBrowser, wi
 - Use `node skills/web-automation/scripts/extract.js "<URL>"` for one-shot extraction from a single URL
 - Use `npx tsx scrape.ts ...` for markdown scraping modes
 - Use `npx tsx browse.ts ...`, `auth.ts`, or `flow.ts` for interactive or authenticated flows
+- Use `node skills/web-automation/scripts/zillow-photos.js "<listing-url>"` or `har-photos.js` for real-estate photo extraction before attempting generic gallery automation
 
 ## Requirements
 
@@ -59,6 +60,17 @@ pnpm rebuild better-sqlite3 esbuild
 
 Without this, helper scripts may fail before launch because the native bindings are missing.
 
+## Prerequisite check
+
+Before running automation, verify the local install and CloakBrowser wiring:
+
+```bash
+cd ~/.openclaw/workspace/skills/web-automation/scripts
+node check-install.js
+```
+
+If this fails, stop and fix setup before troubleshooting site automation.
+
 ## Exec approvals allowlist
 
 If OpenClaw keeps prompting for approval when running this skill, add a local allowlist for the main agent:
@@ -80,13 +92,24 @@ Notes:
 - If `node` lives somewhere else, replace `/opt/homebrew/bin/node` with the output of `which node`.
 - If matching is inconsistent, replace `~/.openclaw/...` with the full absolute path for the machine.
 - Keep the allowlist scoped to the main agent unless there is a clear reason to widen it.
+- Prefer file-based commands like `node check-install.js`, `node zillow-photos.js ...`, and `node har-photos.js ...` over inline `node -e ...`. Inline interpreter eval is more likely to trigger approval friction.
 
 ## Common commands
 
 ```bash
+# Install / wiring check
+cd ~/.openclaw/workspace/skills/web-automation/scripts
+node check-install.js
+
 # One-shot JSON extraction
 node skills/web-automation/scripts/extract.js "https://example.com"
 
+# Zillow photo extraction
+node skills/web-automation/scripts/zillow-photos.js "https://www.zillow.com/homedetails/..."
+
+# HAR photo extraction
+node skills/web-automation/scripts/har-photos.js "https://www.har.com/homedetail/..."
+
 # Browse a page with persistent profile
 npx tsx browse.ts --url "https://example.com"
 
@@ -100,6 +123,58 @@ npx tsx auth.ts --url "https://example.com/login"
 npx tsx flow.ts --instruction 'go to https://search.fiorinis.com then type "pippo" then press enter then wait 2s'
 ```
 
+## Real-estate photo extraction
+
+Use the dedicated Zillow and HAR extractors before trying a free-form gallery flow.
+
+### Zillow
+
+```bash
+cd ~/.openclaw/workspace/skills/web-automation/scripts
+node zillow-photos.js "https://www.zillow.com/homedetails/4141-Whiteley-Dr-Corpus-Christi-TX-78418/2103723704_zpid/"
+```
+
+What it does:
+- opens the listing page with CloakBrowser
+- tries the `See all photos` / `See all X photos` entry point
+- if Zillow keeps the click path flaky, falls back to the listing's embedded `__NEXT_DATA__` payload
+- returns direct `photos.zillowstatic.com` image URLs as JSON
+
+Expected success shape:
+- `complete: true`
+- `expectedPhotoCount` matches `photoCount`
+- `imageUrls` contains the listing photo set
+
+### HAR
+
+```bash
+cd ~/.openclaw/workspace/skills/web-automation/scripts
+node har-photos.js "https://www.har.com/homedetail/4141-whiteley-dr-corpus-christi-tx-78418/14069438"
+```
+
+What it does:
+- opens the HAR listing page
+- clicks `Show all photos` / `View all photos`
+- extracts the direct `pics.harstatic.com` image URLs from the all-photos page
+
+Expected success shape:
+- `complete: true`
+- `expectedPhotoCount` matches `photoCount`
+- `imageUrls` contains the listing photo set
+
+### Test commands
+
+From `skills/web-automation/scripts`:
+
+```bash
+node check-install.js
+npm run test:photos
+node zillow-photos.js "<zillow-listing-url>"
+node har-photos.js "<har-listing-url>"
+```
+
+Use the live Zillow and HAR URLs above for a known-good regression check.
+
 ## One-shot extraction (`extract.js`)
 
 Use `extract.js` when the task is just: open one URL, render it, and return structured content.