What it does
Runs an end-to-end pipeline for meeting or call capture: transcribe audio (stereo or diarized), align the transcript with the user's real-time memo, and distill the result into a prioritized Obsidian vault note using templates and vault-aware semantic searches. Produces an aligned timeline plus a draft note that integrates vault citations.
When to use it
- Capture standups, interviews, calls, or lectures where you want a clean vault-ready note.
- When you have in-session memo lines and audio segments and want them combined into a single structured deliverable.
- To produce action items, decisions, and insights prioritized by what the user actually noted.
What's included
- Scripts: transcription/align/distill CLI scripts under skills/aside/scripts (transcribe, align, distill).
- References: templates folder with note templates (
1on1-idea-exchange, discovery-call, etc.).
- Instructions: environment notes (fluidaudiocli, diarize), argument formats, mode inference rules, and detailed distillation guidance in the SKILL.md.
Compatible agents
Inferred: agents able to run Python/Bash, call local CLIs, and interact with Obsidian-style vaults (Claude Code, Copilot/Code agents, local Python-capable assistants).
Not yet audited
This skill has not been reviewed by our automated audit pipeline yet.
