Skip to content
cccskills
FreePublished on GitHub

outbound-ab-test

Use this skill when you want to test what works in outbound instead of guessing: "A/B test my cold emails", "design an outbound experiment", "which variant won", "testing plan for our sequences". Picks the variable worth testing (list, angle, offer, first line, CTA, channel, timing), writes the hypothesis, splits the audience fairly, sets the sample size and decision rule, and reads the result honestly, including when it is a tie. Produces a test plan, a log entry and the decision.

The English summary is being prepared. Showing the original description.

prosyo-ai/gtm-skill11 stars(GitHub 11 + cccskills 0)

Run score Not tested

See how to install

Files included (1)

  • SKILL.md3.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Use this to run outbound tests that produce decisions. Most outbound "tests" compare 40 sends to 40 sends and crown a winner by noise.

Inputs

  • The current campaign and its baseline numbers.
  • The metric to improve (usually positive reply rate or meetings per 100 contacts).
  • How many contacts per week the team can send to the test.

The play

1. Test the biggest lever first

Impact order, roughly: list and segment > angle and offer > first line and personalization > CTA > subject line > send time. Testing send time while the list is wrong wastes a month.

2. Write a hypothesis

"Leading with the hiring trigger instead of the pain will raise positive replies for SDR leaders, because the trigger shows why now." One variable changes; everything else stays the same.

3. Size it

Required contacts per variant depend on baseline and the lift you want to detect:

Baseline positive reply rateDetect 2x liftDetect 1.5x lift
1%~2,300 per variant~7,700 per variant
2%~1,150~3,800
4%~550~1,900

(Approximate, 80% power, 5% significance.) Rare outcomes need big samples. If volume cannot reach the size, test bigger changes (detect 2x), use total reply rate as a leading metric (it has a higher baseline), or run the test across several weeks of sends.

4. Split fairly

Random assignment within the same segment, same senders spread across both variants, same days and times. Never run variant A this week and B next week.

5. Decide in advance

Write the stop rule: the sample size, the metric, and what counts as a win. Check for guardrails too: bounce and unsubscribe rates must not rise.

6. Read and log

Report both variants with counts, the difference and whether it clears the rule. "No difference" is a result: keep the cheaper or simpler variant. Log every test so the team does not re-run old ones.

Output format

Test: <name>   Hypothesis: <...>
Variable: <one>   Held constant: <list, senders, timing, steps>
Metric: <primary> | Guardrails: bounces, opt-outs
Size: N per variant | Expected duration: N weeks
Decision rule: <...>
Readout: A x/N (x%) vs B x/N (x%) → winner / no difference → action

What good looks like

  • One variable per test.
  • Sample size decided before launch.
  • The log shows what was learned, including tests that changed nothing.
  • The common mistake is judging on open rates, which are inflated by privacy features and say nothing about replies.

Rules

  • MUST change only one variable per test.
  • MUST set sample size and decision rule before launch.
  • NEVER declare a winner below the planned sample, and never on fewer than 200 contacts per variant.
  • NEVER use open rate as the deciding metric.

Example prompts

  • "Design a test: trigger-led vs pain-led first email for VP Sales. We send 400 a week."
  • "Here are results for two variants. Is B really better?"
  • "Plan the next 3 outbound experiments for our team, in order of impact."

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

abm-account-plan

Free

Use this skill when you run account-based marketing or sales on a short list of named accounts: "build an ABM plan", "account plan for our top 20", "how do we break into this enterprise account", "1:1 ABM program". Picks the accounts and the ABM tier (1:1, 1:few, 1:many), maps the buying group, writes the account insight and value hypothesis, plans coordinated sales and marketing plays by stage, and sets the metrics (engagement, meetings, pipeline) that show it is working.

The English summary is being prepared. Showing the original description.

prosyo-ai/gtm-skill11Updated Oct 23, 2026

account-research-brief

Free

Use this skill when you need to research a target company before outreach, a first call or an account plan: "research this account", "what should I know about Acme before the call", "find a reason to reach out". Produces a one-page account brief with what the company does, current priorities, recent trigger events, likely pains tied to your offer, the people to contact and three specific outreach angles, each with its source. Built for SDRs, AEs and founders doing B2B sales.

The English summary is being prepared. Showing the original description.

prosyo-ai/gtm-skill11Updated Oct 23, 2026

account-tiering

Free

Use this skill when you need to decide which accounts get the most effort: "tier my account list", "which accounts should get 1:1 research", "prioritise my territory", "score these companies". Scores every account on ICP fit and timing, assigns Tier 1, 2 or 3 with a clear effort level for each tier, and explains the score so reps trust it. Produces a tiered account list and the operating rules for how much research, personalization and channel effort each tier gets.

The English summary is being prepared. Showing the original description.

prosyo-ai/gtm-skill11Updated Oct 23, 2026

aeo-answer-optimizer

Free

Use this skill when you want your brand recommended and cited by AI assistants and answer engines (ChatGPT, Claude, Gemini, Perplexity, AI Overviews): "answer engine optimisation", "get cited by ChatGPT", "AEO audit", "why doesn't AI recommend us", "generative engine optimization". Finds the questions buyers ask assistants in your category, checks how answers describe you today, and rewrites pages so they give extractable, factual, well-structured answers with clear entities, comparisons, schema and third-party corroboration.

The English summary is being prepared. Showing the original description.

prosyo-ai/gtm-skill11Updated Oct 23, 2026

breakup-email

Free

Use this skill when you want to close the loop with a prospect who has not replied after several touches, or a deal that went silent: "write a breakup email", "last email in the sequence", "close the loop politely". Writes a short, gracious final email that gives an easy out, invites a one-word reply, leaves the door open for later and often gets more replies than any earlier step. Includes versions for cold sequences, stalled deals and lost champions.

The English summary is being prepared. Showing the original description.

prosyo-ai/gtm-skill11Updated Oct 23, 2026

buyer-persona-builder

Free

Use this skill when you need B2B buyer personas that sales and marketing will actually use: before writing outreach to a new title, when messaging feels generic, or when a deal stalls because the wrong person is engaged. Builds a persona per role in the buying committee with goals, pains in their own words, what they are measured on, objections, trusted sources and the message angle that works, plus a do-not-say list. Covers economic buyers, champions, users and blockers.

The English summary is being prepared. Showing the original description.

prosyo-ai/gtm-skill11Updated Oct 23, 2026

See all skills by prosyo-ai

Report a problem with this skill