
Most people have no idea what they actually sound like in meetings. This skill runs the numbers on your own behavior: talk time ratio, filler words, hedging language, monologue length, and how long you go without interrupting. It compares each meeting against your 30-day baseline so you see what was unusual about you, not just what happened. If you've tagged meetings with /minutes-tag, it will show you what you do differently in meetings you win versus ones you lose. The output is one concrete thing to try next time, not a personality audit. It uses a Python script for the counting because LLMs are terrible at exact token math. Trigger it with "how did I do" or "coach me" or just "mirror."
$ npx -y skills add silverstein/minutes --skill minutes-mirror --agent claude-codeInstalls into .claude/skills of the current project.
Self-coaching analysis based on your own meeting transcripts. Two modes:
The point is not to roast you. The point is to give you a kind, evidence-based mirror to behaviors that are usually invisible to you because you're inside them.
Mirror needs to know which speaker label in the transcript is the user. Real transcripts use one of two formats:
[Mat 0:00] Hey there. — first-name labels from voice enrollment[SPEAKER_0 0:00] Hey there. — generic labels from diarizationEither way, mirror needs to know which label maps to the user. Check sources in order:
1. Enrolled voice profile:
minutes voices --json 2>/dev/null
Sponsors