Why use it

Almost everyone diagnoses this wrong. They rewrite the whole post when the first line was the problem, or rewrite the hook when the truth is that only forty people ever saw it. Three different failures, three different fixes.

What it does

It asks for impressions first, because without them you cannot tell distribution failure from content failure, and those have opposite fixes. Then it names which of the three it was, and what that rules out.

What you get

• Which failure it actually was, and what that rules out

• Permission to stop rewriting a hook that was never the problem

• An honest read on variance, because one post is a sample of one

• One change for next time, not a list of six

What it will not do

Without impressions it will say plainly that this is a read-through rather than a diagnosis, instead of guessing.

What changes when VoiceMoat is connected

The weakest part above is that everything depends on numbers you typed in, and on your memory of what normal looks like.

• get_post Returns the full text and exact figures for that one post, so nothing depends on what was pasted.

• get_analytics Gives your own baseline, which is what turns 500 impressions into half your usual or twice it.

• list_posts Puts the flop next to the posts that worked in the same period, which is usually where the answer is.

• get_voice_insights Shows whether the post had drifted from how you normally write, a cause people rarely consider.

How to use it

1. Download SKILL.md.

2. Drop it into ~/.claude/skills/ for Claude Code, or paste it in as a system prompt.

3. Invoke it by name when you need it.

Free, built by VoiceMoat. Works in Claude and ChatGPT on its own, no account needed.

Power up with VoiceMoat

The connector needs a Pro or Enterprise plan. It works the same way in Claude and in ChatGPT, on both Twitter and LinkedIn. How the connector works or see plans and pricing.