meeting-scribelisted

# Meeting Scribe -- Transcribe, Correct, Canvas, Summarize ## What this skill does Take a meeting **audio file** (or an already-transcribed `.txt`) that the user drops into the configured drop-zone, and produce three artifacts: 1. A **corrected transcript** (light-touch cleanup, speech features preserved) 2. A **visual canvas** (single self-contained HTML, the whole meeting at a glance) 3. A **summary** (Markdown, with an AI-insights section) Transcription runs **locally** via Whisper (no external app). The artifacts are written **directly to the configured output destination** -- never echoed in full to chat (echoing then writing generates the same content twice as output tokens and bloats context). The user reviews at the destination and requests edits there. All machine-specific behavior -- where audio lands, which Whisper model to use, where artifacts go, what language to write in -- comes from a per-user config file, NOT from this document. This skill is the orchestration logic only; it is portable across users and machines. ## Configuration On load (when the user invokes this skill), **read the config first**: ```bash cat ~/.config/meeting-transcripts/config.json ``` - **If it exists** -> parse it and use its values for every path / model / language decision below. Do not narrate this read. - **If it is absent** -> run **First-run setup** (below) once, write the config, then continue. ### Config schema ```json { "engine": "faster-whisper", "model": "large