fireflies-reference-architecture
Design meeting intelligence architecture with Fireflies.ai GraphQL API, webhooks, and CRM sync. Use when designing new integrations, planning transcript pipelines, or establishing architecture for meeting analytics platforms. Trigger with phrases like "fireflies architecture", "fireflies design", "fireflies project structure", "meeting intelligence pipeline".
What this skill does
# Fireflies.ai Reference Architecture
## Overview
Production architecture for meeting intelligence using Fireflies.ai. Event-driven pipeline: meetings are recorded by the Fireflies bot, transcripts arrive via webhook, then are processed for action items, analytics, and CRM sync.
## Architecture
```
┌──────────────────────────────────────────────────────┐
│ Meeting Sources │
│ Zoom │ Google Meet │ MS Teams │ Upload API │
└──────────┬───────────────────────────────┬───────────┘
│ Bot auto-joins │ uploadAudio
▼ ▼
┌──────────────────────────────────────────────────────┐
│ Fireflies.ai Platform │
│ Transcription → Speaker ID → AI Summary → Actions │
└───────────────────────┬──────────────────────────────┘
│ Webhook: "Transcription completed"
│ Payload: { meetingId, eventType }
▼
┌──────────────────────────────────────────────────────┐
│ Your Webhook Receiver │
│ 1. Verify x-hub-signature (HMAC-SHA256) │
│ 2. ACK 200 immediately │
│ 3. Queue for async processing │
└───────────────────────┬──────────────────────────────┘
│
┌────────────┼────────────┐
▼ ▼ ▼
┌──────────────┐ ┌────────┐ ┌──────────────┐
│ Transcript │ │ Action │ │ Analytics │
│ Storage │ │ Items │ │ Engine │
│ (DB/Search) │ │ (CRM) │ │ (Dashboards) │
└──────────────┘ └────────┘ └──────────────┘
```
## Core Components
### 1. GraphQL Client Layer
```typescript
// lib/fireflies.ts
const FIREFLIES_API = "https://api.fireflies.ai/graphql";
export async function firefliesQuery(query: string, variables?: any) {
const res = await fetch(FIREFLIES_API, {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${process.env.FIREFLIES_API_KEY}`,
},
body: JSON.stringify({ query, variables }),
});
const json = await res.json();
if (json.errors) throw new Error(json.errors[0].message);
return json.data;
}
```
### 2. Webhook Processor
```typescript
// services/webhook-processor.ts
import crypto from "crypto";
interface TranscriptEvent {
meetingId: string;
eventType: string;
clientReferenceId?: string;
}
export async function processWebhookEvent(event: TranscriptEvent) {
// Fetch full transcript
const { transcript } = await firefliesQuery(`
query($id: String!) {
transcript(id: $id) {
id title date duration
organizer_email
speakers { id name }
sentences {
speaker_name text start_time end_time
ai_filters { task question sentiment }
}
summary { overview action_items keywords topics_discussed }
meeting_attendees { displayName email }
analytics {
sentiments { positive_pct negative_pct neutral_pct }
speakers { name duration word_count questions words_per_minute }
}
}
}
`, { id: event.meetingId });
// Process in parallel
await Promise.all([
storeTranscript(transcript),
syncActionItems(transcript),
updateAnalytics(transcript),
]);
return transcript;
}
```
### 3. Transcript Storage
```typescript
// services/transcript-store.ts
interface StoredMeeting {
firefliesId: string;
title: string;
date: string;
duration: number;
speakers: string[];
overview: string;
actionItems: string[];
keywords: string[];
sentiment: { positive: number; negative: number; neutral: number };
}
async function storeTranscript(transcript: any): Promise<StoredMeeting> {
const meeting: StoredMeeting = {
firefliesId: transcript.id,
title: transcript.title,
date: transcript.date,
duration: transcript.duration,
speakers: transcript.speakers.map((s: any) => s.name),
overview: transcript.summary?.overview || "",
actionItems: transcript.summary?.action_items || [],
keywords: transcript.summary?.keywords || [],
sentiment: {
positive: transcript.analytics?.sentiments?.positive_pct || 0,
negative: transcript.analytics?.sentiments?.negative_pct || 0,
neutral: transcript.analytics?.sentiments?.neutral_pct || 0,
},
};
// Store in your database
await db.meetings.upsert({ where: { firefliesId: meeting.firefliesId }, data: meeting });
return meeting;
}
```
### 4. Action Item Sync
```typescript
// services/action-items.ts
async function syncActionItems(transcript: any) {
const items = transcript.summary?.action_items || [];
if (items.length === 0) return;
const attendees = transcript.meeting_attendees?.map((a: any) => a.email) || [];
for (const item of items) {
await taskManager.create({
title: item.slice(0, 200),
source: `Fireflies: ${transcript.title}`,
meetingId: transcript.id,
meetingDate: transcript.date,
participants: attendees,
});
}
console.log(`Synced ${items.length} action items from "${transcript.title}"`);
}
```
### 5. Meeting Analytics
```typescript
// services/analytics.ts
async function buildWeeklyReport() {
const since = new Date(Date.now() - 7 * 86400000).toISOString();
const data = await firefliesQuery(`
query($fromDate: DateTime) {
transcripts(fromDate: $fromDate, limit: 100) {
id title date duration
participants
summary { action_items keywords }
analytics {
speakers { name duration word_count }
sentiments { positive_pct }
}
}
}
`, { fromDate: since });
const meetings = data.transcripts;
return {
totalMeetings: meetings.length,
totalHours: (meetings.reduce((s: number, m: any) => s + m.duration, 0) / 60).toFixed(1),
actionItems: meetings.reduce((s: number, m: any) => s + (m.summary?.action_items?.length || 0), 0),
topKeywords: aggregateKeywords(meetings).slice(0, 10),
avgSentiment: avgSentiment(meetings),
};
}
function aggregateKeywords(meetings: any[]): [string, number][] {
const counts: Record<string, number> = {};
for (const m of meetings) {
for (const kw of m.summary?.keywords || []) {
counts[kw] = (counts[kw] || 0) + 1;
}
}
return Object.entries(counts).sort((a, b) => b[1] - a[1]);
}
```
### 6. Audio Upload Pipeline
```typescript
// services/upload.ts
async function uploadRecording(fileUrl: string, title: string, attendees?: any[]) {
return firefliesQuery(`
mutation($input: AudioUploadInput) {
uploadAudio(input: $input) {
success
title
message
}
}
`, {
input: {
url: fileUrl,
title,
attendees: attendees?.map(a => ({ displayName: a.name, email: a.email })),
webhook: process.env.WEBHOOK_URL,
client_reference_id: `upload-${Date.now()}`,
},
});
}
```
## Project Layout
```
meeting-intelligence/
src/
lib/fireflies.ts # GraphQL client
services/
webhook-processor.ts # Event handler
transcript-store.ts # DB persistence
action-items.ts # CRM/task sync
analytics.ts # Aggregation
upload.ts # Audio upload
api/
webhooks/fireflies.ts # Webhook endpoint
health.ts # Health check
types/fireflies.ts # TypeScript interfaces
tests/
fixtures/ # Recorded API responses
services/ # Service unit tests
```
## Error Handling
| Issue | Cause | Solution |
|-------|-------|----------|
| Missing transcript | `meetingId` invalid | Log and skip, alert on repeated failures |
| Empty summary | Meeting too short | Check duration > 1 min before processing |
| Duplicate webhook | Network retry | Use `meetingId` as idempotency key |
| Rate limit on batch | Many transcripts at once | QuRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.