extract-my-action-items

Extract Action Items Extract action items from a Fireflies transcript using parallel subagents. Catches items automated summaries miss. Two modes: All attendees (default): No target specified — extract action items for every participant Single person: Target specified — extract action items for that person only Phase 1: Determine Mode Parse the user's invocation: If a target person is specified → single-person mode Otherwise → all-attendees mode Extract the search criteria (date, keyword, or transcript ID) from the invocation. Phase 2: Fetch & Preprocess (Subagent) The transcript API returns a JSON array (or an MCP wrapper containing one). Extract to plain text before chunking. You should inspect the user's local hooks config and avoid running commands that are blocked by the hooks. MCP based extraction mkdir -p .claude/scratchpad node -e " const fs = require('fs'); let data = JSON.parse(fs.readFileSync(process.argv[1], 'utf8')); // Handle MCP wrapper: if top-level array has a .text field containing the real transcript, parse that if (data.length === 1 && typeof data[0]?.text === 'string') { // Extract speaker lines from the text content const lines = data[0].text.split(' \n ').filter(l => l.match(/^[A-Za-z].?:/)); fs.writeFileSync('.claude/scratchpad/transcript.txt', lines.join(' \n ')); const speakers = [...new Set(lines.map(l => l.split(':')[0].trim()))].sort(); console.log('Speakers:', JSON.stringify(speakers)); console.log('Total lines:', lines.length); } else { // Standard array of {speaker_name, text} objects const lines = data.map(e => (e.speaker_name || 'Unknown') + ': ' + (e.text || '')); fs.writeFileSync('.claude/scratchpad/transcript.txt', lines.join(' \n ')); const speakers = [...new Set(data.map(e => e.speaker_name).filter(Boolean))].sort(); console.log('Speakers:', JSON.stringify(speakers)); console.log('Total lines:', lines.length); } " [ TRANSCRIPT_JSON_FILE ] If the transcript JSON was saved to a tool-results file by the MCP client, pass that file path as the argument. API based extraction CRITICAL: The orchestrator MUST NOT call any Fireflies MCP tools directly. ALL Fireflies interaction happens inside this subagent. Launch a single general-purpose subagent with this prompt: Search Fireflies for a transcript matching: [SEARCH_CRITERIA] 1. Call mcp__fireflies__fireflies_get_transcripts to find the transcript (by date, keyword, or ID). 2. Call mcp__fireflies__fireflies_get_summary and mcp__fireflies__fireflies_get_transcript in parallel for the matched transcript. 3. The transcript API returns a JSON array. Extract to plain text: - With jq: jq -r '.[].text' < raw_transcript.json > .claude/scratchpad/transcript.txt - Fallback: python3 -c "import json,sys; print('\n'.join(e['text'] for e in json.load(sys.stdin)))" < raw_transcript.json > .claude/scratchpad/transcript.txt 4. Count lines: wc -l < .claude/scratchpad/transcript.txt 5. Extract the distinct speaker list from the transcript JSON: python3 -c "import json,sys; data=json.load(sys.stdin); print('\n'.join(sorted(set(e.get('speaker_name','') for e in data if e.get('speaker_name')))))" < raw_transcript.json Return EXACTLY this (no other text): - meeting_title: