india-location-normalizer
von vishalgojha
Coding Agents & IDEsKurzbeschreibung
Normalize Indian real-estate location text into canonical city and locality fields (Mumbai and Pune v1)
Beschreibung
Was dieser Skill macht
Normalizes raw Indian real-estate location text into structured city, locality, and micro-market fields for Mumbai and Pune leads. Uses a curated alias lookup map to resolve shorthands like Andheri W, PCMC, Hinjewadi, and Wakad. Sets confidence scores and flags unresolved matches rather than guessing.
It uses a tiered matching strategy and prefers false-negatives over false-positives, reducing incorrect city or locality assignments that general-purpose text normalizers commonly produce.
Wann du ihn einsetzt
- Mapping 'Andheri W' to its canonical Mumbai locality in a lead record
- Resolving PCMC entries to the correct Pune locality before scoring
- Standardizing Hinjewadi Phase 2 variants prior to CRM storage
- Flagging ambiguous location aliases for manual review
- Cleaning up Mumbai shorthands like 'Scruz' or 'Khar' from WhatsApp-sourced leads
Beispiel-Workflow
User asks: Normalize this lead payload: {raw_location: 'Hinjewadi Phase 2', city: null}
- 1
Validates the input against location-normalizer-input.schema.json
- 2
Looks up 'Hinjewadi Phase 2' in india-location-aliases-v1.json
- 3
Finds an exact alias match (case-insensitive)
- 4
Returns a normalized record with city, locality_canonical, micro_market, matched_alias, confidence, and unresolved_flag
{city: 'Pune', locality_canonical: 'Hinjewadi', micro_market: 'Hinjewadi Phase 2', matched_alias: 'Hinjewadi Phase 2', confidence: 0.95, unresolved_flag: false}
Installation
clawhub install vishalgojha/india-location-normalizerFühre den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.