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

docs: forbid silent helper polling in whatsapp runs

Browse Source
This commit is contained in:
Stefano Fiorini
2026-03-28 01:34:23 -05:00
parent 3d7ce7617c
commit d2d43df24d
2 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/property-assessor.md
View File

@@ -69,6 +69,8 @@ Operational rule:
- If the user asks `update?` or `and?` mid-run, treat that as a status request and continue the same assessment rather than restarting or stopping at the last checkpoint.
- In WhatsApp or similar messaging runs, keep the core analysis on native `web_search`, `web_fetch`, and bounded browser actions. Do not make helper subprocesses the default path for discovery, CAD lookup, or photo extraction.
- In those messaging runs, reserve subprocess use for a single final `render-report` attempt after the verdict and fair-value range are complete.
- In those messaging runs, do not start Gmail/email-send skill discovery or delivery tooling until the report content is complete and the PDF is ready to render or already rendered.
- Treat a silent helper as a failed helper in messaging runs. If a helper produces no useful output within a short bound, abandon it and continue with the chat-native path instead of repeatedly polling it.
- If final PDF render/send fails, return the completed decision-grade report in chat and report delivery failure separately rather than restarting the whole assessment.
### `assess`

5
skills/property-assessor/SKILL.md
View File

@@ -59,6 +59,9 @@ Rules:
- In WhatsApp or similar messaging runs, keep the core assessment on native chat-safe tools: `web_search`, `web_fetch`, and bounded `web-automation` browsing/extraction.
- 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.
- 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.
- 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 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.
- Do **not** run `npm install`, `npm ci`, or other dependency-setup commands during a normal chat assessment flow when the local skill already has `node_modules` present.
- On this machine, treat `property-assessor` dependencies as already installed. Use the helper entrypoints directly unless the wrapper itself explicitly reports missing local dependencies.
@@ -123,6 +126,8 @@ Agent follow-through rule:
- Only after the verdict and fair-value range are established should you render/send the PDF.
- If the analysis still cannot be completed, explain the first real blocker, not just that the helper was preliminary.
- If the user sends `update?`, `and?`, or similar mid-run, answer with status and keep the original assessment going. Do not treat that message as a reset or a cue to stop at the last helper checkpoint.
- In WhatsApp or similar messaging runs, do **not** start a background `assess` helper and then wait on repeated zero-output polls. That counts as a failed path; abandon it and continue with native search/fetch/browser work.
- In WhatsApp or similar messaging runs, do **not** start mail-sending or mail-skill discovery before the report content, verdict, and delivery artifact are ready.
## Public-record enrichment