← Back to Skills Marketplace
771
Downloads
0
Stars
3
Active Installs
7
Versions
Install in OpenClaw
/install lead-extractor
Description
Extract structured real-estate lead records from parsed message objects. Use when users ask to find leads in WhatsApp exports, extract name-phone-budget, or...
README (SKILL.md)
Lead Extractor
Identify lead signals in parsed messages and emit strict lead objects.
Quick Triggers
- Find all buyer leads from this WhatsApp chat.
- Extract contact details and budget from these messages.
- Identify serious property inquiries from parsed messages.
Recommended Chain
message-parser -> lead-extractor -> india-location-normalizer
Execute Workflow
- Accept parsed messages from Supervisor.
- Validate input with
references/parsed-message-input.schema.json. - Apply chat-specific extraction rules from
references/extraction-rules-re-india-v1.md. - Determine
dataset_modefrom Supervisor context:- default:
broker_group - allowed:
broker_group,buyer_inquiry,mixed
- default:
- Detect lead-candidate messages using inquiry intent, contact details, and property-related preferences.
- Classify
record_type:inventory_listingfor broker inventory/availability posts (default in broker groups)buyer_requirementfor explicit "required/chahiye looking for" demand posts- drop non-lead/system noise instead of emitting
noise_or_system
- Handle multiline listings as one candidate record when body lines contain price, area, or location details.
- Build lead records with:
- required:
lead_id,name,phone,record_type - optional:
dataset_mode,property_type,budget,deal_type,asset_class,price_basis,area_sqft,area_basis,location_hint,raw_text,source,created_at
- required:
- Normalize phone extraction from spaced variants such as
+91 98205 82462and98200 78845. - Distinguish price intent from rate intent:
- examples:
3.5 Lakh rent(monthly),60K psf(per-sqft),4.25 Cr(total)
- Deduplicate leads by stable keys when records clearly refer to the same person.
- Validate output with
references/output-leads.schema.json. - Return only validated lead objects.
Enforce Boundaries
- Never write or update persistent storage.
- Never modify source messages.
- Never generate summaries.
- Never suggest or execute follow-up actions.
- Never send communication or invoke external side effects.
Handle Errors
- Reject invalid parsed-message input.
- Emit an empty array when no lead evidence exists.
- Return field-level validation errors when extracted records violate schema.
Usage Guidance
This skill appears to do only what it says: validate parsed WhatsApp messages, apply local rules, and return structured lead objects. Before installing, consider privacy and data governance: the skill will process PII (names, phone numbers, budgets), so ensure you only feed it data you are allowed to share and that your agent environment / logs won't leak outputs. The 'never' rules in SKILL.md are instructions — they are not an enforcement mechanism; verify that other installed skills or the agent's runtime won't capture or forward extracted leads. If you need stronger guarantees (no network egress, no logging), run it in a constrained environment or audit the agent runtime policies. If the maintainer later adds code, external endpoints, or requests credentials, re-evaluate immediately.
Capability Analysis
Type: OpenClaw Skill
Name: lead-extractor
Version: 1.0.6
The skill is designed for extracting and structuring real-estate lead data from parsed messages. Crucially, the `SKILL.md` explicitly defines 'Enforce Boundaries' that forbid writing to persistent storage, modifying source messages, generating summaries, suggesting/executing follow-up actions, or sending communications/invoking external side effects. This is further reinforced in the `agents/openai.yaml` default prompt. The `references/extraction-rules-re-india-v1.md` provides detailed, task-specific instructions for data processing without any malicious directives or prompt injection attempts. All files align with the stated purpose and actively prevent high-risk behaviors.
Capability Assessment
Purpose & Capability
Name/description, schemas, and extraction rules all align: the skill only needs parsed message arrays and emits validated lead objects. There are no unexpected environment variables, binaries, or unrelated requirements.
Instruction Scope
SKILL.md explicitly restricts runtime actions to validating input, applying local extraction rules, building/validating lead objects, deduplicating, and returning results. It also states hard boundaries (no storage, no outbound actions). The instructions only reference included schema and rules files — no external endpoints or unrelated system paths are mentioned.
Install Mechanism
Instruction-only skill with no install spec and no code files to execute; nothing is written to disk or fetched during install. This is the lowest-risk install model and matches the skill's stated role.
Credentials
The skill requests no environment variables, credentials, or config paths. All required data comes from the parsed-message input; this is proportionate to the stated extraction task. Note: the skill will process personal data (names, phones) which is expected for this purpose.
Persistence & Privilege
always:false and default invocation settings are appropriate. The SKILL.md explicitly disallows writes or outbound communication. The skill does not request persistent presence or modify other skills' configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install lead-extractor - After installation, invoke the skill by name or use
/lead-extractor - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.6
Align broker-group contracts: dataset_mode, record_type, and expanded summary/prioritization schemas.
v1.0.5
Data-driven extraction rules for Indian broker chat patterns
v1.0.4
Preserve RE-India title and improve install-facing guidance
v1.0.3
Improve use-when clarity and chain guidance
v1.0.2
Rename display title with RE-India suffix
v1.0.1
Append RE-India suffix to display names
v1.0.0
Initial release of lead-extractor.
- Extracts structured real-estate lead records from parsed message objects.
- Identifies buyer or seller inquiries, contact details, and property preferences in messages.
- Validates input and output against strict schemas.
- Deduplicates leads referencing the same person.
- Emits only validated lead objects; no storage, summaries, messaging, or actions.
Metadata
Frequently Asked Questions
What is Lead Extractor?
Extract structured real-estate lead records from parsed message objects. Use when users ask to find leads in WhatsApp exports, extract name-phone-budget, or... It is an AI Agent Skill for Claude Code / OpenClaw, with 771 downloads so far.
How do I install Lead Extractor?
Run "/install lead-extractor" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Lead Extractor free?
Yes, Lead Extractor is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Lead Extractor support?
Lead Extractor is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Lead Extractor?
It is built and maintained by Vishal (@vishalgojha); the current version is v1.0.6.
More Skills