← All plays
AG
Alta Growth
Creator

Benchmark Check

Know if your numbers are good, compared to market standards

Raised by customers on 80+ calls in the past year

Compares your reply, meeting and bounce rates to market standards - computed the same way benchmarks are - so you know where you really stand.

Learn
Luna
Reviewed by Alta

What it does

  1. Cleans your numbers the way benchmarks are computed
  2. Picks the right benchmark for your channel and segment
  3. Compares reply, meeting and bounce rates side by side
  4. Names the one or two gaps worth fixing first

You give it

  • The campaigns to include
  • Your channel and segment

You get

  • Your rates next to market standards
  • The gaps worth fixing

Why it works

A rate only means something next to a fair comparison. Computing both sides the same way stops teams from fixing what is not broken.

Run this play

Copy the SKILL.md below into your agent
Works in Alta, Claude, Cursor and Codex
Runs on
Luna
Category
Learn
CostAlta credits per run, shown before it runs
ApprovalEvery run stops at a draft for you
--- name: benchmark-check description: Compare outbound rates to market standards, cleaned the way benchmarks are computed (delivered-only denominators, per-campaign averages). Use when someone asks if their reply rate is good, about benchmarks or industry averages. agent: Luna category: Learn ends_in: report --- # Benchmark Check Most teams compare a raw pooled rate to a cleaned benchmark and think they are losing. ## How it runs 1. **Clean your numbers** the way benchmarks are computed - delivered messages as the denominator, averaged per campaign 2. **Pick the right benchmark** for your channel, segment and deal size 3. **Compare** reply, positive reply, meeting and bounce rates 4. **Name the gaps** worth fixing first 5. **Write the report** ## Rules - Always show how each number was computed - Never compare a raw rate to a cleaned benchmark - Cite the source of every benchmark ## What you get - Your rates next to market standards, computed the same way - The one or two gaps worth fixing
- Your numbers and the benchmark use the same denominator - Every benchmark has a cited source - The report ends with at most two priorities
The play fileSKILL.md

This is the whole play. Read it, copy it, or change it for your team - it runs the same in Alta, Claude, Cursor and Codex.

Install this play
Claude app or claude.aiUpload the zip as a skill

Download the zip, then upload it as a skill in your Claude settings. Code execution needs to be on.

Claude CodeDrop the folder in

Unzip it into your skills folder. Claude Code finds it on its own.

~/.claude/skills/
Cursor and other agentsAdd the SKILL.md

Put the folder where your agent reads skills, for example:

.cursor/skills/

Run it where you work

Same play, same result. Pick the place you already are.

In Alta

One click

Open Skills in Alta, pick the play and press Run. Or ask Ask Alta to run it for the companies you care about.

In Claude

Ask in plain words

Connect Alta to Claude and describe the target. Claude loads the play, the agent does the work, and the draft opens in Alta for you to approve.

In Cursor or Codex

Drop in the file

Add the SKILL.md to your agent's skills folder with the Alta plugin connected. Edit it like code, and keep your team's version in the repo.