Expand property assessor documentation

This commit is contained in:
2026-03-27 21:39:06 -05:00
parent 19adb919fc
commit 954374ce48

View File

@@ -1,84 +1,326 @@
# property-assessor
Decision-grade residential property assessment with required photo review, comp checks, carry-cost underwriting, and explicit buy/pass guidance.
Decision-grade residential property assessment skill for OpenClaw.
## What this skill is for
This skill is for evaluating a condo, townhouse, house, or similar residential property from an address or listing URL and ending with a practical recommendation such as `buy`, `pass`, or `only below X`.
- 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`
## Overview
`property-assessor` is a workflow skill, not just a scraper. It is meant to:
- normalize the target property across listing sources
- build a baseline fact set
- review listing photos before making condition claims
- compare the property against nearby or same-building comps
- underwrite taxes, HOA, insurance, and realistic carrying costs
- identify risk drivers
- produce a concise but decision-grade verdict
The skill is designed for real-world purchase decisions, especially when you need a fast read on whether a property is worth pursuing.
## Accepted inputs
The skill can start from any of:
- a street address
- a Zillow listing URL
- a HAR listing URL
- an address plus user constraints such as:
- investment only
- owner-occupant
- long-term rental
- short-term rental
- target distance/location requirements
Preferred starting point is the address when available, because it makes source reconciliation easier.
## Core workflow
Default operating sequence:
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.
2. Discover accessible listing and public-record sources for the same property.
3. Establish a baseline fact set from the best available source.
4. Cross-check the same property on other sources.
5. Review listing photos before making condition claims.
6. Pull same-building comps for condos or nearby comps for houses/townhomes.
7. Underwrite carry costs and risk drivers.
8. End with a specific recommendation and fair-value range.
## Required photo-review workflow
## Source priority
Photo review is mandatory when a listing source exposes photos.
Unless the user asks otherwise, preferred source order is:
Preferred source order:
1. Zillow
2. HAR
2. Redfin
3. Realtor.com
4. Brokerage mirror or other accessible listing mirror
4. HAR / Homes.com / brokerage mirrors
5. county or appraisal pages
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.
Use high-quality mirrors to confirm facts, not to override a clearly better primary listing without reason.
## Minimum data to capture
For the target property, capture as many of these as the sources support:
- address
- list price or last known list price
- property type
- beds / baths
- square footage
- lot size if relevant
- year built
- HOA fee and included services
- taxes
- days on market
- price history
- parking
- waterfront / flood clues
- subdivision or building name
- same-building or nearby active inventory
- listing photos and visible condition cues
- included appliances and obvious missing appliances
- flooring mix, especially carpet
## Photo-review requirement
Photo review is mandatory when the listing sources expose photos.
Do not make strong condition claims from structured text alone if photos are available.
### What counts as acceptable photo access
Preferred photo sources are:
- a scrollable all-photos page
- an expanded photo grid
- a photo page that exposes the full set
- a modal/lightbox only if the site does not provide a better all-photos path
Do not treat these as full photo review by themselves:
- the listing hero image
- a collage preview
- a photo count without image access
- listing shell text that mentions photos
### What to inspect in the photos
At minimum, evaluate:
- overall finish level: dated, average, lightly updated, fully updated
- kitchen condition: cabinets, counters, backsplash, appliances
- bathroom condition: vanity, tile, surrounds, fixtures
- flooring: tile, vinyl, laminate, hardwood, carpet
- obvious make-ready issues: paint, trim, wear, damage, mismatched finishes
- visible missing items: refrigerator, washer/dryer, range hood, dishwasher
- signs of deferred maintenance or water intrusion
- exterior and common-area condition where visible
- waterfront-facing elements, balconies, decks, sliders, and windows when relevant
### If photo review is incomplete
If the agent cannot access enough photos to make a credible read:
- say so explicitly
- lower confidence
- avoid strong turnkey claims
- continue the broader underwriting work, but mark condition as limited-confidence
## Zillow and HAR integration
This skill now expects the dedicated `web-automation` extractors first.
This skill now expects the dedicated `web-automation` extractors first instead of fragile ad hoc gallery automation.
### Zillow
### Zillow first
Run:
```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
Successful Zillow photo access means one of these happened:
The returned `imageUrls` are the photo-review set. Review those images before making condition claims.
- the `See all photos` / `See all X photos` path opened a usable all-photos experience, or
- the rendered Zillow listing shell already exposed the full direct Zillow image set and the extracted count matches the announced count
Important rule:
- when the extractor returns `imageUrls`, that returned set is the photo-review set
For smaller listings, review the full extracted set when practical. For a 20-30 photo listing, that usually means all photos.
### HAR fallback
If Zillow does not expose a reliable image set, use HAR next:
```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.
Successful HAR photo access means:
## Approval-safe command shape
- the HAR listing opened
- `Show all photos` / `View all photos` exposed the photo page
- direct `pics.harstatic.com` image URLs were extracted
For chat-driven runs, prefer file-based commands under `~/.openclaw/workspace/skills/web-automation/scripts`.
As with Zillow, the returned `imageUrls` are the review set for condition analysis.
### Practical photo-source order
Use this action order:
1. Zillow extractor
2. HAR extractor
3. Realtor.com photo page
4. brokerage mirror or other accessible listing mirror
Do not stop after the first failed source if a fallback source can still expose the photos.
## Approval-safe execution
For chat-driven property assessments, prefer file-based commands under:
```text
~/.openclaw/workspace/skills/web-automation/scripts
```
Good command shape:
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
Why this matters:
- OpenClaw exec approvals are easier to allowlist for stable file paths
- inline interpreter eval is more likely to trigger approval friction
- the installed approval allowlist is typically already scoped to the `*.js` files under the `web-automation/scripts` directory
## Make-ready normalization
Condition should be translated into a rough make-ready range so pricing and comp comparisons stay realistic.
Use simple buckets:
- light make-ready
- paint, fixtures, minor hardware, small patching
- medium make-ready
- partial flooring replacement, appliance replacement, bathroom refresh
- heavy make-ready
- significant kitchen/bath work, widespread flooring, visible deferred maintenance
Call out carpet separately when present, especially in bedrooms, stairs, or living areas.
## Underwriting expectations
The final assessment should show a simple carrying-cost view including:
- principal and interest if available
- taxes per month
- HOA per month if applicable
- insurance estimate or explicit uncertainty
- realistic carry range after maintenance, vacancy, and property-specific risk
Strong caution flags include:
- high HOA relative to price or expected rent
- older waterfront or coastal exposure
- unknown reserve or assessment history for condos
- many active units in the same building or micro-area
- stale days on market with weak price action
- no clear rent support
## Output contract
The final answer should stay concise but decision-grade.
Recommended structure:
1. Snapshot
2. What I like
3. What I do not like
4. Comp view
5. Underwriting / carry view
6. Risks and diligence items
7. Verdict with fair-value range and offer guidance
The output must explicitly include:
The final assessment should explicitly include:
- `Photo source attempts: ...`
- `Photo review: completed via <source>` or `Photo review: not completed`
- `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.
If photo review was completed:
- summarize the condition read from the photos
- mention obvious finish level, flooring, appliance presence, and make-ready signals
If not completed:
- mark condition confidence as limited
- explain why photo access was incomplete
## Example validation flow
Use these commands for a known-good regression check.
### Verify extractor prerequisites
```bash
cd ~/.openclaw/workspace/skills/web-automation/scripts
node check-install.js
npm run test:photos
```
### Zillow regression check
```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/"
```
Expected shape:
- `complete: true`
- `expectedPhotoCount: 29`
- `photoCount: 29`
### HAR regression check
```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"
```
Expected shape:
- `complete: true`
- `expectedPhotoCount: 29`
- `photoCount: 29`
### Skill-level validation
When testing `property-assessor` itself, confirm the resulting assessment:
- attempts Zillow first
- falls back to HAR if needed
- references actual photo access, not just listing text
- includes the required `Photo source attempts` line
- includes the required `Photo review` line
- makes condition claims consistent with the reviewed image set
## Related files
- installed skill instructions:
- `~/.openclaw/workspace/skills/property-assessor/SKILL.md`
- repo skill instructions:
- `skills/property-assessor/SKILL.md`
- photo extractor docs:
- `docs/web-automation.md`