lead-extractor
vishalgojha 作
Search & Research概要
Extract structured real-estate lead records from parsed message objects.
説明
このスキルでできること
Extracts structured lead records from parsed WhatsApp real-estate messages. Classifies each message as an inventory listing or buyer requirement, and pulls name, phone, budget, and property details into a validated schema. Designed to run after message-parser and before india-location-normalizer.
Handles India-specific number formats, price notation (Lakh, Cr, psf), and real estate terminology that generic extractors misparse or ignore.
使いどころ
- Finding all buyer inquiries in a WhatsApp broker group export
- Pulling contact details and budgets from real estate chat dumps
- Separating listing posts from demand posts in mixed group chats
- Parsing spaced or country-code phone numbers from informal messages
- Deduplicating repeat contacts across a bulk message dataset
ワークフロー例
User asks: Extract all leads from this WhatsApp broker group export
- 1
Validates parsed message input against the parsed-message-input schema
- 2
Applies India real estate extraction rules to detect lead-candidate messages
- 3
Classifies each candidate as inventory_listing or buyer_requirement
- 4
Builds lead records with name, phone, budget, location, and deal type fields
- 5
Validates output records against the output-leads schema and deduplicates by stable key
Array of validated lead objects with structured fields including lead_id, name, phone, record_type, budget, and location_hint
インストール
clawhub install vishalgojha/lead-extractorCLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。