openclaw-whatsapp-skills

Reply to an inbound WhatsApp message routed through the TimelinesAI webhook. Triggers on payloads shaped like {chat_id, text, sender_phone, sender_name} from the TimelinesAI webhook receiver. Verifies the chat belongs to the allowed sender JID before sending, and honors stop-reply labels (needs-human / escalate / pause-bot) so a human can pause the bot on any chat with one tag.

Given a TimelinesAI message_uid, poll GET /messages/{uid}/status_history and return the Sent / Delivered / Read timeline. Use after a send to confirm a message actually reached the recipient's device, or to answer "did X receive Y" questions from the user.

Multi-turn lead qualification over WhatsApp. Asks a fixed sequence of questions across turns, stores each answer as a note on the chat, and tags the chat with the current discovery stage. At the end of the sequence, applies a qualification rule and tags the chat `qualified` or `disqualified`, then stops replying. State survives skill restarts because it lives on the chat, not in the skill process.

Send a transactional or event-triggered WhatsApp message via the TimelinesAI public API. Two modes: by phone number (creates a new chat if needed) or into an existing chat by chat_id. Writes JSON payloads to a file to avoid UTF-8 encoding traps. Returns the message_uid so downstream skills can poll delivery status.