brevard-bidder-ai-skills

Interactively debug source code — set breakpoints, step through execution line by line, inspect live variable state, evaluate expressions against the running program, and navigate the call stack to trace root causes. Use when a program crashes, raises unexpected exceptions, produces wrong output, when you need to understand how execution reached a certain state, or when print-statement debugging isn't revealing enough.

BidDeed.AI auction intelligence pipeline operations. Use when triggering scrapers, running analysis, generating reports, debugging pipeline stages, or checking county auction data. Covers the 12-stage Everest Ascent pipeline: Discovery → Scraping → Title → Lien Priority → Tax Certs → Demographics → ML Score → Max Bid → Decision Log → Report → Disposition → Archive.

Full end-to-end testing for BidDeed.AI and ZoneWise applications. Launches parallel sub-agents to research the codebase, then uses agent-browser to test every user journey — taking screenshots, validating UI/UX, and querying Supabase to verify records. Run after implementation to validate everything before commit and Render deploy.

Direct Supabase/Postgres operations for BidDeed.AI and ZoneWise. Query, insert, update, and validate data in Supabase tables. Use when validating auction pipeline results, checking insights logs, debugging data issues, or running ad hoc queries against production data.