India Location Normalizer for Openclaw

A high-precision normalization tool for mapping Indian real-estate location aliases to canonical city and locality records.

vishalgojha
v1.0.1
Feb 23, 2026
0
1.5k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install india-location-normalizer

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install india-location-normalizer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is India Location Normalizer?

The India Location Normalizer is a dedicated Openclaw Skills component designed to handle the complexity of Indian real-estate data. It specifically addresses the challenge of resolving messy, informal locality aliases—common in lead generation—into standardized canonical formats for Mumbai and Pune. By integrating this skill into your workflow, you ensure that location data is consistent, accurate, and ready for advanced analytics or scoring.

This skill operates as a processing layer within a larger agentic chain, leveraging authoritative lookup maps and strict validation schemas to prevent data corruption. Unlike generic extractors, this Openclaw Skills module focuses on high-precision matching, ensuring that shorthand like Scruz or PCMC is correctly attributed to its canonical counterpart without the risk of false positives.

India Location Normalizer Use Cases

  • Normalizing Mumbai and Pune location aliases extracted from real-estate leads.
  • Mapping shorthand terms like Scruz, Hinjewadi variants, or Andheri W to standardized locality names.
  • Preparing lead data for downstream sentiment scoring or priority ranking.
  • Enhancing the accuracy of location-based data storage and reporting via Openclaw Skills.

How India Location Normalizer Works

  1. Receives a lead-location payload from a supervisor agent within the Openclaw Skills framework.
  2. Validates the input data against a predefined JSON schema to ensure structural integrity.
  3. Cross-references aliases against an authoritative lookup map (india-location-aliases-v1.json).
  4. Applies a multi-stage matching logic: exact alias match, token-normalized match, and conservative fuzzy matching.
  5. Generates a normalized record containing canonical city, locality, and confidence metrics.
  6. Performs a final output validation against the target schema before returning the result.

India Location Normalizer Setup

To use this within the Openclaw Skills ecosystem, include it in your workflow chain. Ensure reference files are present in your project directory:

# Check for required reference files
ls references/india-location-aliases-v1.json
ls references/location-normalizer-input.schema.json

Configure your agent supervisor to route output from your lead-extractor directly to the india-location-normalizer.

India Location Normalizer Data Schema & Taxonomy

Field Description
city The canonical city name (e.g., Mumbai, Pune)
locality_canonical The standardized name of the locality
micro_market The specific market segment within the locality
matched_alias The original input string that triggered the match
confidence Numeric score representing the match certainty
unresolved_flag Boolean flag indicating if the match was ambiguous

India Location Normalizer Advanced Features

  • Integrated token-normalization to handle punctuation and whitespace variations automatically.
  • Sophisticated ambiguity handling with specific flags for manual review of low-confidence matches.
  • Designed for seamless chaining with lead-extractors and sentiment-priority-scorers in Openclaw Skills pipelines.
  • Strict boundary enforcement preventing unauthorized data writes or external communication, ensuring data privacy.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*