---
name: community-engagement-reply-assistant
description: "Turns a pile of comments, DMs, and mentions into on-brand replies that sound like a person, with two options for trolls and a flag on anything that needs a human. Use when a brand's comments, DMs, and mentions have piled up and each needs a reply in the brand voice, including complaints and trolls. Do not use for writing the original posts or captions, or formal support tickets that need account access. Related topics: Marketing, Social Media, Communication."
---

# Community Engagement Reply Assistant

Turns a pile of comments, DMs, and mentions into on-brand replies that sound like a person, with two options for trolls and a flag on anything that needs a human.

## When to use

Use this skill when a brand's comments, DMs, and mentions have piled up and each needs a reply in the brand voice, including complaints and trolls. Do not use it for writing the original posts or captions, or formal support tickets that need account access.

## Workflow

1. Ask the user for each input listed below in a single message, skipping any they have already given. Where options are listed, offer them, but accept other answers too.
2. Sort the messages by type and platform, so each reply gets the right length and register before any drafting starts.
3. Write one reply per message that names the specific thing the person said, confirming none could be pasted under a different comment.
4. For each complaint, acknowledge the exact problem first, then give the fix or the route to DM or support with what to send.
5. For each troll or bad-faith message, draft a disarming reply and a non-engagement reply, and recommend one with a reason.
6. List every message that should be escalated to a human with the reason, so nothing legal, safety-related, or press-related is answered in public.

## Inputs

- **Brand voice** (choose one: Warm and personal, Professional, Playful and witty, Minimal and direct)
- **Messages to reply to** (longer free text)
- **Context** (longer free text)
- **Message type** (choose one: Praise, Question, Complaint, Feature request, Troll or bad faith, Mixed)
- **Goal of the replies** (choose any: Build loyalty, Move to DM or support, Defuse tension, Encourage sharing, Correct misinformation)

## Output

One reply per message in the order given, each labelled with the message it answers and the platform, trolls with two options and a recommendation, then a short escalation list with reasons.

## Prompt template

Fill the inputs into this template and follow it as the full instruction.

### Community Engagement Reply Assistant

Draft replies to the messages below that sound like a human who cares, not a support macro.

- Brand voice: {{Brand voice}}
- Messages to reply to: {{Messages to reply to}}
- Context: {{Context}}
- Message type: {{Message type}}
- Goal of the replies: {{Goal of the replies}}

Work through the messages in order and write one reply per message. Match each reply to the platform's norms: one or two short lines with room for an emoji on Instagram and TikTok, fuller sentences on LinkedIn, and a thread-friendly reply on X. Name the specific thing the person said, so the reply could not be pasted under any other comment.

For complaints, acknowledge the exact problem before offering the fix, and never write "sorry for any inconvenience". When the fix needs account details, move the conversation to DM or support in the reply and say what to send. For feature requests, say whether it is planned, under consideration, or not on the roadmap, without promising a date. For trolls, give two options: a disarming reply with light humour and a polite non-engagement reply, and recommend one.

End with an escalation list: any message that involves a legal threat, a safety issue, a refund dispute, press, or an angry long-time customer, with one line on why it should be answered by a human and not in public.

## Pitfalls

- Replying to a complaint with a generic apology template, which reads as a macro and makes the commenter angrier.
- Arguing facts with a troll in public, which feeds the thread and makes the brand look defensive.
- Promising a feature date in a reply to a request, which becomes a public commitment the product team never made.
- Using LinkedIn-length replies on Instagram, where a paragraph under a comment looks corporate.
