Refresh property assessor and web automation docs

README.md

@@ -20,9 +20,10 @@ This repository contains practical OpenClaw skills and companion integrations. I
 | `gitea-api` | Interact with Gitea via REST API (repos, issues, PRs, releases, branches, user info). | `skills/gitea-api` |
 | `nordvpn-client` | Install, log in to, connect, disconnect, and verify NordVPN sessions across Linux CLI and macOS NordLynx/WireGuard backends. | `skills/nordvpn-client` |
 | `portainer` | Manage Portainer stacks via API (list, start/stop/restart, update, prune images). | `skills/portainer` |
+| `property-assessor` | Assess a residential property from an address or listing URL with comps, carry costs, risks, and required photo review using Zillow first and HAR fallback. | `skills/property-assessor` |
 | `searxng` | Search through a local or self-hosted SearXNG instance for web, news, images, and more. | `skills/searxng` |
 | `us-cpa` | Federal individual 1040 workflow for tax questions, case intake, preparation, review, and draft e-file-ready export. | `skills/us-cpa` |
-| `web-automation` | One-shot extraction plus broader browsing/scraping with Playwright-compatible CloakBrowser (auth flows, extraction, bot-protected sites). | `skills/web-automation` |
+| `web-automation` | One-shot extraction plus broader browsing/scraping with Playwright-compatible CloakBrowser, including dedicated Zillow and HAR photo extractors. | `skills/web-automation` |
 
 ## Integrations
 

docs/README.md

@@ -8,9 +8,10 @@ This folder contains detailed docs for each skill in this repository.
 - [`gitea-api`](gitea-api.md) — REST-based Gitea automation (no `tea` CLI required)
 - [`nordvpn-client`](nordvpn-client.md) — Cross-platform NordVPN install, login, connect, disconnect, and verification with Linux CLI and macOS NordLynx/WireGuard support
 - [`portainer`](portainer.md) — Portainer stack management (list, lifecycle, updates, image pruning)
+- [`property-assessor`](property-assessor.md) — Residential property assessment with underwriting, risks, and required Zillow/HAR photo review workflow
 - [`searxng`](searxng.md) — Privacy-respecting metasearch via a local or self-hosted SearXNG instance
 - [`us-cpa`](us-cpa.md) — Federal individual 1040 workflow for tax questions, case intake, preparation, review, and draft e-file-ready export
-- [`web-automation`](web-automation.md) — One-shot extraction plus Playwright-compatible CloakBrowser browser automation and scraping
+- [`web-automation`](web-automation.md) — One-shot extraction plus Playwright-compatible CloakBrowser browser automation, scraping, and dedicated Zillow/HAR photo extraction
 
 ## Integrations
 

docs/property-assessor.md

@@ -0,0 +1,84 @@
+# property-assessor
+
+Decision-grade residential property assessment with required photo review, comp checks, carry-cost underwriting, and explicit buy/pass guidance.
+
+## What this skill is for
+
+- Assessing a property from an address, Zillow URL, HAR URL, or other listing source
+- Reconciling baseline facts across multiple listing/public sources
+- Reviewing listing photos before making condition claims
+- Producing a practical verdict such as `buy`, `pass`, or `only below X`
+
+## Core workflow
+
+1. Normalize the address and property type.
+2. Build a baseline fact set from the best available listing or record source.
+3. Cross-check facts on other sources.
+4. Review photos before making condition claims.
+5. Pull comps.
+6. Underwrite carry costs and risk factors.
+7. End with a clear verdict and fair-value guidance.
+
+## Required photo-review workflow
+
+Photo review is mandatory when a listing source exposes photos.
+
+Preferred source order:
+1. Zillow
+2. HAR
+3. Realtor.com
+4. Brokerage mirror or other accessible listing mirror
+
+Rules:
+- Do not claim condition from structured text alone when listing photos are available.
+- Prefer accessible all-photos views, photo grids, or scrollable photo pages over fragile next-arrow traversal.
+- If the primary source fails but a fallback source exposes the photos, continue with the fallback.
+- If photo review is incomplete, say so explicitly and lower confidence.
+
+## Zillow and HAR integration
+
+This skill now expects the dedicated `web-automation` extractors first.
+
+### Zillow
+
+```bash
+cd ~/.openclaw/workspace/skills/web-automation/scripts
+node zillow-photos.js "<zillow-listing-url>"
+```
+
+Success means:
+- the Zillow all-photos page opened, or
+- Zillow's rendered listing shell already exposed the full direct image set and the extracted count matches the announced count
+
+The returned `imageUrls` are the photo-review set. Review those images before making condition claims.
+
+### HAR fallback
+
+```bash
+cd ~/.openclaw/workspace/skills/web-automation/scripts
+node har-photos.js "<har-listing-url>"
+```
+
+Use HAR when Zillow does not expose a reliable photo set. The returned `imageUrls` are the review set for the fallback path.
+
+## Approval-safe command shape
+
+For chat-driven runs, prefer file-based commands under `~/.openclaw/workspace/skills/web-automation/scripts`.
+
+Good:
+- `node check-install.js`
+- `node zillow-photos.js "<url>"`
+- `node har-photos.js "<url>"`
+
+Avoid when possible:
+- `node -e "..."`
+- `node --input-type=module -e "..."`
+
+## Output requirements
+
+The final assessment should explicitly include:
+- `Photo source attempts: ...`
+- `Photo review: completed via <source>` or `Photo review: not completed`
+
+If photo review was completed, briefly summarize the condition read from the photos.
+If not, mark condition confidence as limited and explain why.

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.