.claude/skills/voice-meeting/SKILL.md
Record meetings with voice transcription and create meeting notes
npx skillsauth add DavidROliverBA/ArchitectKB .claude/skills/voice-meetingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Record a meeting using voice capture and automatically create a meeting note with transcript.
/voice-meeting start <title>
/voice-meeting start <title> for <project>
/voice-meeting stop
/voice-meeting status
/voice-meeting start Weekly Team Sync
/voice-meeting start Architecture Review for Project - Alpha
/voice-meeting stop
/voice-meeting status
Before using this skill, ensure:
ws://localhost:4000cd ~/Documents/GitHub/claude-voice && npm run start:serverstart action:Parse the command for:
Use the voice_listen_continuous MCP tool with action "start":
mcp__voice-mcp__voice_listen_continuous({
action: "start",
title: "<meeting title>"
})
Store the session_id returned for later use
Inform the user:
/voice-meeting stop when finished/voice-meeting statusstop action:Use the voice_listen_continuous MCP tool with action "stop":
mcp__voice-mcp__voice_listen_continuous({
action: "stop"
})
Retrieve the full transcript and segments from the response
Generate filename: Meeting - YYYY-MM-DD {{title}}.md
Create the meeting note in Meetings/ folder:
---
type: Meeting
title: { { title } }
created: { { DATE } }
modified: { { DATE } }
tags: [voice-recorded]
date: "{{DATE}}"
project: { { project_link or null } }
attendees: []
summary: { { AI-generated summary of transcript } }
collections: null
recordingSession: { { session_id } }
duration: { { duration_ms formatted as HH:MM:SS } }
wordCount: { { word_count } }
---
# {{title}}
## Recording Info
- **Session ID**: {{session_id}}
- **Duration**: {{duration formatted}}
- **Word Count**: {{word_count}}
## Attendees
(To be filled in)
## Transcript
{{full_transcript}}
## AI Summary
{{Generate 3-5 bullet point summary of the meeting}}
## Action Items
{{Extract any action items mentioned in transcript, or leave template:}}
- [ ]
## Decisions Made
## {{Extract any decisions mentioned, or leave template:}}
## Follow-up
-
status action:Use the voice_listen_continuous MCP tool with action "status":
mcp__voice-mcp__voice_listen_continuous({
action: "status"
})
Report:
stop is calledtools
--- context: fork --- # /youtube Save a YouTube video as both a Weblink (quick reference) and a detailed Page (full analysis). ## Usage ``` /youtube <url> /youtube <url> <optional title override> ``` ## Examples ``` /youtube https://www.youtube.com/watch?v=0TpON5T-Sw4 /youtube https://youtu.be/abc123 AWS re:Invent Keynote ``` ## Prerequisites This skill uses the MCP Docker YouTube tools: - `mcp__MCP_DOCKER__get_video_info` - Video metadata - `mcp__MCP_DOCKER__get_transcript` - Full trans
data-ai
Create and manage git worktrees for parallel agent sessions
testing
--- context: fork --- # /wipe Generate a context handoff summary, clear the session, and resume in a fresh conversation. Detects environment and provides automated (tmux) or manual workflow. ## Usage ``` /wipe /wipe quick # Minimal handoff, just essentials /wipe detailed # Comprehensive handoff with full context ``` ## Instructions When the user invokes `/wipe`: ### Phase 1: Detect Environment First, check the terminal environment: ```bash echo "Environment Detection:"
data-ai
--- context: fork --- # /weekly-summary Generate comprehensive weekly summary from daily notes, meetings, tasks, and project updates using parallel sub-agents. ## Usage ``` /weekly-summary /weekly-summary --last-week /weekly-summary --from 2026-01-01 --to 2026-01-07 /weekly-summary --output page # Create Page note instead of just outputting ``` ## Instructions This skill uses **5 parallel sub-agents** to gather data concurrently from different vault areas, then synthesizes a comprehensi