Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Data-driven parsing and multiline handling updates from real WhatsApp dumps
What This Skill Does
Parses raw WhatsApp chat exports in TXT or JSON format into a normalized array of message objects, each with a timestamp, sender, and content field. Handles multiline continuation lines, timestamp collisions, and system boilerplate like group creation notices or encryption messages.
It handles WhatsApp-specific format quirks like DD/MM/YYYY timestamps, multiline continuations, and system event lines that generic parsers mishandle or drop.
When to use it
- Converting a WhatsApp group export TXT into structured JSON
- Preprocessing chat dumps before running lead extraction
- Cleaning multiline messages into single normalized records
- Auditing raw chat history with preserved message ordering
- Feeding parsed messages into downstream analysis or scoring pipelines
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Parse this WhatsApp group export and return structured message objects
- 1Accepts the raw WhatsApp TXT or JSON export as input
- 2Detects the source format and identifies timestamp, sender, and content boundaries
- 3Normalizes each message into an RFC 3339 timestamp, a non-empty sender string, and a content string
- 4Merges multiline continuation lines into their preceding message record
- 5Validates the output array against the parsed-message-array schema and returns it
A JSON array of message objects, each containing timestamp (RFC 3339), sender, and content fields