Home/stef-openclaw-skills
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Harden assessor fallback after Zillow photo failure

Browse Source
This commit is contained in:
Stefano Fiorini
2026-03-28 03:17:51 -05:00
parent 3335e96d35
commit 54854edfc6
5 changed files with 115 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
skills/property-assessor/SKILL.md
View File

@@ -60,6 +60,7 @@ Rules:
- In WhatsApp or similar messaging runs, keep the core assessment on `web-automation` plus `web_fetch`. Treat `web_search` as a fallback discovery aid, not the primary property-analysis path.
- For Zillow/HAR property discovery, photo extraction, and rendered listing review, do **not** start with Brave-backed `web_search` when `web-automation` can open the candidate source directly.
- For CAD/public-record enrichment, prefer official assessor/CAD pages via `web_fetch` first. Use `web-automation` when the official site needs rendered interaction. Do **not** start CAD lookup from generic web-search snippets when the official site is already known or derivable from the address.
- In Texas runs, do **not** use `https://www.texas.gov/propertytaxes/search/` as the CAD lookup path. Use the address-first CAD/helper path or the discovered county CAD pages directly.
- In those messaging runs, do **not** make `scripts/property-assessor assess`, `scripts/property-assessor locate-public-records`, `node zillow-discover.js`, `node har-discover.js`, `node zillow-photos.js`, `node har-photos.js`, `curl`, or `wget` the default core-analysis path.
- From messaging runs, the only subprocess-style step you should attempt by default is the final `scripts/property-assessor render-report` call after the verdict, fair-value range, and report body are complete.
- Do **not** inspect Gmail/email-send skills, mail tooling, or delivery integrations until the assessment is complete and the PDF is either already rendered or ready to render immediately.
@@ -68,6 +69,8 @@ Rules:
- Do **not** use generic `gog` or the Stefano helper `node ~/.openclaw/workspace/integrations/google-workspace/gw.js` for property-assessor report delivery.
- If you need to confirm Luke auth before sending, use `zsh ~/.openclaw/workspace/bin/gog-luke auth list --check --plain`.
- A silent helper is a failed helper in messaging runs. If a background helper produces no useful stdout/stderr and no result within a short bound, stop polling it, treat that path as failed, and continue on the chat-native assessment path instead of narrating that it is still chewing.
- If Zillow photo extraction fails, immediately continue with HAR photo fallback or the next available rendered listing/photo source. Do **not** stop the assessment because one Zillow photo subprocess failed.
- After a Zillow/HAR photo miss, continue the comp and CAD/public-record work in the same run. A photo-source miss is a fallback event, not a terminal state.
- Do **not** leave the user parked behind background helper polling. If a helper has not produced a result quickly, give a concise status update and continue the assessment with the next available non-helper path.
- If the user already instructed you to email/send the finished PDF to a specific target, do **not** ask for a second send confirmation after rendering. Render, send, and report the result.
- If the final PDF render fails, return the complete decision-grade report in chat and say the render/send step failed. Do not restart the whole assessment.