---
name: whatsapp-lead-follow-up
description: "Reconcile lead replies and prepare appropriate follow-up actions from approved conversation access. Use when the user requests whatsapp lead follow-up. Select relevant methods for the requested outcome; unrelated tasks do not require this skill."
metadata:
  version: "1.0.0"
---

# WhatsApp Lead Follow-Up

Reconcile lead replies and prepare appropriate follow-up actions from approved conversation access.

## OLLIE Runtime integration

Use this capability under the active OLLIE Operator. Read live Workspace Context and tenant bindings for client facts and required inputs. This generic package contains no client configuration. Consume ask-ollie-authority-core for authority, outloop-access-fallback for access and recovery, email-lifecycle-core for communication, and the bootstrapper Runtime Contract for ownership, scheduling and completion. Preserve domain constraints; this Skill creates no competing execution path. Use one method, combine skills, or fill missing steps with authorized tools as the task requires.

External access uses the active Workspace’s approved Outloop capabilities. Never request, read, embed or expose credentials. A service named in a method is a possible dependency, not an access grant. Local file and application work uses the host’s authorized tools.

## Required inputs

- Approved lead records
- Authorized conversation access
- Consent and channel policy
- Recent reply history

## Methods

### Identify the conversation

Match a conversation to the intended lead using approved identifiers, not a display name alone. Recheck recent replies before preparing a follow-up.

### Classify current state

Classify answered, awaiting reply, opted out and needs-human states with evidence. Do not treat an unread marker as proof that no reply exists.

### Draft the next action

Draft the next useful message within current consent and workspace policy. Preserve opt-outs and avoid duplicating an action already owned by another workflow.

### Verify authorized delivery

For an authorized send, read back the stored conversation state and update the relevant record through Runtime. No background scanner or schedule is created by this skill.

## Completion

Verify findings against source evidence and read back the resulting artifact or authorized change. Report inputs used, methods selected, output location, assumptions and unresolved dependencies. Do not report a plan, queue entry, draft, test fixture or accepted request as a completed external action. Use the task’s requested format; if a tool is unavailable, finish independent work and identify the exact unfulfilled deliverable.

## Test before relying on it

Read [the synthetic evaluation cases](references/evaluation.md) for activation, output and isolation checks. These cases are test instructions, not evidence that a host or provider test has passed.