From minutes
Guides users through first-time setup of Minutes: downloading whisper models, creating directories, configuring audio input for call recording, and verifying installation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/minutes:minutes-setupThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Walk the user through first-time Minutes setup, step by step.
Walk the user through first-time Minutes setup, step by step.
Run the verify skill's script to see what's already done:
bash "${CLAUDE_PLUGIN_ROOT}/skills/minutes-verify/scripts/verify-setup.sh"
Skip any steps that already pass.
cd ~/Sites/minutes
export CXXFLAGS="-I$(xcrun --show-sdk-path)/usr/include/c++/v1"
cargo build --release
The binary lands at target/release/minutes. The user should add it to their PATH or create a symlink.
Ask the user which quality level they want using AskUserQuestion:
| Model | Size | Speed | Quality | Best for |
|---|---|---|---|---|
tiny | 75 MB | ~10x real-time | Low | Quick tests, short memos |
small | 466 MB | ~4x real-time | Good | Daily meetings (recommended) |
medium | 1.5 GB | ~2x real-time | Great | Important meetings, accents |
large-v3 | 3.1 GB | ~1x real-time | Best | Legal, medical, foreign language |
Then run:
minutes setup --model <chosen-model>
mkdir -p ~/meetings/memos
For in-person conversations, the built-in mic works fine. For Zoom/Meet/Teams:
brew install blackhole-2chSee minutes-record/references/audio-devices.md for the full guide.
Run verify again to confirm everything passes:
bash "${CLAUDE_PLUGIN_ROOT}/skills/minutes-verify/scripts/verify-setup.sh"
minutes record --title "Test recording"
# Speak for 10-15 seconds
minutes stop
Check the output file exists in ~/meetings/ and has a transcript.
small model is 466 MB. On slow connections, tiny is a good starting point (75 MB).npx claudepluginhub silverstein/minutes --plugin minutesRecords and transcribes meetings/calls/voice memos locally (whisper.cpp/parakeet.cpp). Supports start/stop, live transcript, and status checking.
Implements TwinMind workflow for real-time/file-based meeting transcription with speaker diarization, AI summaries, action items, and follow-up emails using Ear-3 model.
Records microphone and system audio, transcribes to timestamped Markdown with speaker labels using whisper.cpp and Metal acceleration on macOS 14+. For meetings, notes, dictation.