agentleFS
holaroluwaholaroluwa/outbound-skills/skills/reply-rate-analyser/SKILL.md

reply-rate-analyser

Skill0 starsChanged 46 days agoMITView on GitHub

Analyse cold sequence performance data to benchmark it, diagnose the root cause of weak results per touch, and recommend specific A/B tests. Use when the user shares sequence stats (sent, open, reply, positive) or asks "why are my replies low", "is this open rate good", "what should I test", or "diagnose my sequence". Points at the specific broken lever, list, subject, copy, offer, or timing, instead of vague advice.

The file

Files
SKILL.md

Reply Rate Analyser

Low replies are a symptom, not a cause. This skill benchmarks your numbers, points at the specific broken lever, and tells you what to test next.

Input needed

  • Sequence performance data, per touch if possible: sent, delivered, open rate, reply rate, positive reply rate, bounce rate.

Method

  1. Benchmark against rough cold norms and flag what's off:
    • Bounce above ~3%: a list-quality or sending-health problem.
    • Open rate low (under ~40%): subject line, sender reputation, or deliverability.
    • Opens fine but replies low (under ~2-3%): copy, offer, or targeting.
    • Replies but mostly negative: targeting or offer mismatch.
  2. Diagnose per touch, which step leaks and why.
  3. Trace the root cause to a single lever: list/targeting, deliverability, subject, body copy, offer, or timing. Name the most likely culprit first.
  4. Recommend A/B tests: one variable at a time, each with the specific change and the metric it should move.

Output

  • A benchmark read on each metric (good or off, and why).
  • The #1 lever to fix, with the reasoning.
  • 2-3 concrete A/B tests, each isolating one variable, with its success metric.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.