Skip to content
Marketing
Skill

/messaging-ab-tester

Generate 3-5 messaging variants for a value proposition, design structured A/B tests, and analyze results to determine which framing resonates most with ICP. Tests can run via LinkedIn organic posts, cold email subject line splits, or both. Pure reasoning for variant generation

From plugin
goose-skills
1.2k200 skills
Install
$ npx -y skills add gooseworks-ai/goose-skills --skill messaging-ab-tester --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/messaging-ab-tester

Context preview

The summary Claude sees to decide when to auto-load this skill.

Generate 3-5 messaging variants for a value proposition, design structured A/B tests, and analyze results to determine which framing resonates most with ICP. Tests can run via LinkedIn organic posts, cold email subject line splits, or both. Pure reasoning for variant generation

SKILL.md

messaging-ab-tester.SKILL.md
name: messaging-ab-tester
description: >
  Generate 3-5 messaging variants for a value proposition, design structured A/B tests,
  and analyze results to determine which framing resonates most with ICP. Tests can run
  via LinkedIn organic posts, cold email subject line splits, or both. Pure reasoning for
  variant generation and analysis — the user deploys the tests through their own tools.
  Use when a team can't decide between messaging angles and needs data, not opinions.
tags: [brand]

Messaging A/B Tester

Stop debating which message is better — test it. Generate messaging variants, deploy them through real channels, and measure which framing actually resonates with your ICP.

**Core principle:** At seed/Series A, you don't have enough traffic for website A/B tests. But you do have enough LinkedIn impressions and cold email sends to test messaging angles fast.

When to Use

  • "Which of these value props should we lead with?"
  • "Test our messaging angles and tell me which works"
  • "I can't decide between [message A] and [message B]"
  • "What messaging resonates most with [ICP]?"
  • "Run a messaging test for [product/feature]"

Phase 0: Intake

What to Test

1. **Core value prop** — The claim or positioning you want to test (e.g., "We help growth teams run outbound 10x faster") 2. **Test goal** — What are you deciding? (Headline for website, cold email angle, LinkedIn content strategy, ad copy direction) 3. **ICP** — Who should this resonate with? (Title, company type, stage) 4. **Current messaging** — What are you using today? (Baseline to beat)

Test Channel

5. **Where to test:**

  • **LinkedIn organic** — Post variants across consecutive days, compare engagement
  • **Cold email** — A/B test subject lines or opening hooks via Smartlead
  • **Both** — Run in parallel for fastest signal

6. **Sample size available:**

  • LinkedIn: followers/typical impressions per post
  • Email: list size available for testing

Constraints

7. **Number of variants** — 3-5 recommended (more = slower signal) 8. **Test duration** — How long to run? (Default: 1 week for LinkedIn, 3-5 days for email)

Phase 1: Generate Messaging Variants

Create 3-5 variants that test different **angles**, not just different words. Each variant should represent a distinct strategic bet:

Variant Types

| Type | What It Tests | Example | |------|--------------|---------| | **Outcome-driven** | Leading with the result | "3x your pipeline in 30 days" | | **Pain-driven** | Leading with the problem | "Tired of spending 4 hours a day on manual prospecting?" | | **Identity-driven** | Leading with who they are | "Built for growth teams who move fast" | | **Proof-driven** | Leading with evidence | "How [Customer] went from 10 to 50 demos/month" | | **Contrast-driven** | Leading with what you're not | "Not another CRM. An outbound engine." |

Variant Template

For each variant:

VARIANT [N]: [Type — e.g., "Outcome-driven"]

Hypothesis: This framing will resonate because [reasoning tied to ICP psychology]

LinkedIn post version:
---
[Full post copy — 100-200 words, native LinkedIn format]
---

Email subject line version:
[Subject line — max 50 chars]

Email opening hook version:
[First 2 sentences of an email]

Headline version:
[Website headline — max 10 words]

Phase 2: Deploy Tests

Option A: LinkedIn Organic Test

**Setup:** 1. Schedule variants as consecutive posts (1 per day, same time of day) 2. Each post should be similar length and format (control for post structure) 3. Don't boost any posts — organic only for clean comparison

**Measurement (after 48 hours per post):**

  • Impressions
  • Reactions (likes, celebrates, etc.)
  • Comments
  • Comment sentiment (positive/negative/neutral)
  • Profile visits (if trackable)
  • DMs received mentioning the post

Option B: Cold Email A/B Test

**Setup via your outreach tool (Smartlead, Instantly, Lemlist, or any tool with A/B testing):** 1. Create campaign with all variants as A/B test sequences 2. Split list evenly across variants (minimum 50 per variant for signal) 3. Same send time, same sender, same CTA — only the messaging changes

**Measurement (after 5 days):**

  • Open rate (tests subject line)
  • Reply rate (tests full message resonance)
  • Positive reply rate (tests conversion quality)
  • Click rate (if link included)

Option C: Both (Recommended)

Run LinkedIn and email in parallel. Different channels may show different winners — that's valuable signal about where each message works best.

Phase 2B: Collect Results

After the test has run for the planned duration, gather your results:

**How to provide data:**

  • **Paste metrics** — Copy open rates, reply rates, engagement numbers directly into the chat
  • **CSV export** — Export campaign analytics from your outreach tool and share the file
  • **Screenshot** — Take a screenshot of your dashboard/analytics and share it
  • **Manual input** — Just tell the agent the numbers: "Variant A got 45% open rate and 3% reply rate, Variant B got 52% open rate and 5% reply rate"

**For LinkedIn tests:** Go to your post analytics (click "View analytics" on each post) and share impressions, reactions, comments, and profile visits per post.

**For email tests:** Export or screenshot your campaign's variant/A-B test results showing sends, opens, and replies per variant.

The agent will normalize whatever format you provide into the scoring framework below.

Phase 3: Analyze Results

Scoring Framework

| Metric | Weight (LinkedIn) | Weight (Email) | |--------|-------------------|----------------| | Engagement rate | 30% | — | | Comment quality | 30% | — | | Open rate | — | 30% | | Reply rate | — | 40% | | Positive reply rate | — | 30% | | Impressions | 20% | — | | Profile visits / clicks | 20% | — |

Statistical Significance Check

For email tests:

  • **Minimum sends per variant:** 50 (for directional signal), 200+ (for confident decisions)
  • **Minimum difference to call a winner:**
Read more
Ships withgoose-skills

Put your AI agent on the growth team. Research customers and competitors, analyze what is working, create the next campaign, and learn from the result.

Get the whole plugin

Other skills on goose-skills.