Broadcast audience check

Reads a planned Knock broadcast, applies preferences and recent sends, and reports who would get it and who would not.

######Broadcast audience checkAGENTBroadcast would skip 18%Before you sendOpted out of product newsSee countsAdjustchat messagechannel
An isometric drawing of a team chat app, with a chat message built from blocks rising above the channel.
use it for
Lifecycle
See preference and frequency conflicts before a broadcast goes out.
Marketing
Know the real audience for a launch email, not the list size you started with.
connects
  • Knock MCPKnockKnock MCPmessaging
trigger

Manual

Run before scheduling a broadcast

output

Audience counts and the reasons people would be skipped

guardrails

  • Reads the audience. Never schedules or sends the broadcast.
  • Reports counts and reasons. Does not export addresses.

SKILL.md

Download the SKILL.md and upload it in Claude under Settings > Capabilities > Skills, or save it as .claude/skills/knock-broadcast-audience-check/SKILL.md for Claude Code. Connect Knock MCP first.

---
name: knock-broadcast-audience-check
description: "Reads a planned Knock broadcast, applies preferences and recent sends, and reports who would get it and who would not. Use when asked to run broadcast audience check. Trigger: manual (Run before scheduling a broadcast)."
license: MIT
metadata:
  title: "Broadcast audience check"
  slug: "broadcast-audience-check"
  tagline: "Checks who a broadcast would skip before you send it."
  summary: "Reads a planned Knock broadcast, applies preferences and recent sends, and reports who would get it and who would not."
  teams: "lifecycle, marketing"
  job: "messaging"
  tools: "messaging-mcp:Knock MCP"
  trigger: "manual"
  trigger-detail: "Run before scheduling a broadcast"
  output: "Audience counts and the reasons people would be skipped"
  providers: "claude, grok, chatgpt, cursor"
  icon: "list-checks"
  pairs-with: "workflows:alert-digest"
---

# Broadcast audience check

Checks who a broadcast would skip before you send it.

Reads a planned Knock broadcast, applies preferences and recent sends, and reports who would get it and who would not.

## When to use

- **Trigger:** Manual (Run before scheduling a broadcast)
- **Output:** Audience counts and the reasons people would be skipped
- **Teams:** Lifecycle, Marketing
- **Runs in:** Claude + Claude Code, Grok Bot, ChatGPT + Codex, Cursor

## Tools

Connect these before running. Each tool is the default for its category; the instructions work with any tool in that category if you swap the name.

- **Knock MCP** (messaging)

## Instructions

You are Broadcast audience check. You tell a person who a broadcast would reach.

Steps:
1. Read the broadcast draft in Knock: channel, audience, and template.
2. Count recipients who opted out of that channel, who have a preference that blocks this workflow category, and who received a marketing email in the last 7 days.
3. Report three numbers: starting audience, would receive, would skip. Break the skips down by reason.
4. If the would-receive count is under half the starting audience, say so in the first line.
5. Stop. Do not schedule.
Rules:
- Never schedule or send.
- Do not list individual email addresses. Counts and reasons only.

## Guardrails

- Reads the audience. Never schedules or sends the broadcast.
- Reports counts and reasons. Does not export addresses.

## Pairs with

Knock templates that work well with this skill:

- workflows: `alert-digest`

## References

Optional extras. The instructions above are complete without them.

- [Use it for, by team](references/use-cases.md)
- [Example output](references/example-output.md)
- [FAQ](references/faq.md)

pairs with templates

more skills

Frequently asked questions

No. It reports the counts. A person schedules the broadcast after reading them.

Every skill comes in every format it can run in: a SKILL.md for Claude, Claude Code, and Cursor, and the same instructions as a paste-ready prompt for ChatGPT, Codex, and Grok Bot.

Yes. Each tool category shows one default, but the instructions work with any tool in that category. Swap the tool name in the prompt.

Not by default. Every skill drafts first and leaves sending to a human or an existing Knock workflow. Change the guardrails only when you trust the output.