fireflies-local-dev-loop
Configure Fireflies.ai local development with hot reload and testing. Use when setting up a development environment, configuring test workflows, or establishing a fast iteration cycle with Fireflies.ai. Trigger with phrases like "fireflies dev setup", "fireflies local development", "fireflies dev environment", "develop with fireflies".
Install
mkdir -p .claude/skills/fireflies-local-dev-loop && curl -L -o skill.zip "https://mcp.directory/api/skills/download/9124" && unzip -o skill.zip -d .claude/skills/fireflies-local-dev-loop && rm skill.zipInstalls to .claude/skills/fireflies-local-dev-loop
About this skill
Fireflies.ai Local Dev Loop
Overview
Set up a fast local development workflow for Fireflies.ai integrations: project structure, mock data for offline development, test helpers, and API response recording for replay.
Prerequisites
- Completed
fireflies-install-authsetup - Node.js 18+ with npm/pnpm
- Vitest for testing
Instructions
Step 1: Project Structure
my-fireflies-app/
src/
lib/
fireflies-client.ts # GraphQL client (see fireflies-sdk-patterns)
transcript-service.ts # Business logic layer
types/
fireflies.ts # TypeScript interfaces
tests/
fixtures/
transcript.json # Recorded API responses
fireflies-client.test.ts
transcript-service.test.ts
.env.local # FIREFLIES_API_KEY (git-ignored)
.env.example # Template without secrets
Step 2: Record Real API Responses as Fixtures
// scripts/record-fixtures.ts
import { FirefliesClient } from "../src/lib/fireflies-client";
import { writeFileSync, mkdirSync } from "fs";
async function recordFixtures() {
const client = new FirefliesClient();
mkdirSync("tests/fixtures", { recursive: true });
// Record user
const user = await client.query(`{ user { name email user_id is_admin } }`);
writeFileSync("tests/fixtures/user.json", JSON.stringify(user, null, 2));
// Record transcript list
const list = await client.query(`{
transcripts(limit: 3) {
id title date duration organizer_email
summary { overview action_items keywords }
}
}`);
writeFileSync("tests/fixtures/transcripts.json", JSON.stringify(list, null, 2));
// Record single transcript with sentences
const id = list.transcripts[0]?.id;
if (id) {
const full = await client.query(`
query($id: String!) {
transcript(id: $id) {
id title date duration
speakers { id name }
sentences { speaker_name text start_time end_time }
summary { overview action_items keywords }
analytics {
sentiments { positive_pct negative_pct neutral_pct }
speakers { name duration word_count }
}
}
}
`, { id });
writeFileSync("tests/fixtures/transcript-full.json", JSON.stringify(full, null, 2));
}
console.log("Fixtures recorded in tests/fixtures/");
}
recordFixtures().catch(console.error);
Step 3: Mock Client for Tests
// tests/helpers/mock-fireflies.ts
import { readFileSync } from "fs";
export function createMockClient() {
const fixtures: Record<string, any> = {};
return {
loadFixture(name: string) {
fixtures[name] = JSON.parse(
readFileSync(`tests/fixtures/${name}.json`, "utf-8")
);
},
async query(gql: string, variables?: Record<string, any>) {
// Match query to fixture by operation
if (gql.includes("transcripts(")) return fixtures["transcripts"];
if (gql.includes("transcript(id:")) return fixtures["transcript-full"];
if (gql.includes("user {")) return fixtures["user"];
throw new Error(`No fixture for query: ${gql.slice(0, 50)}`);
},
};
}
Step 4: Write Tests
// tests/transcript-service.test.ts
import { describe, it, expect, vi, beforeEach } from "vitest";
import { createMockClient } from "./helpers/mock-fireflies";
describe("Transcript Service", () => {
let mockClient: ReturnType<typeof createMockClient>;
beforeEach(() => {
mockClient = createMockClient();
mockClient.loadFixture("transcripts");
mockClient.loadFixture("transcript-full");
});
it("should list recent transcripts", async () => {
const data = await mockClient.query("{ transcripts(limit: 3) { id title } }");
expect(data.transcripts).toBeDefined();
expect(data.transcripts.length).toBeGreaterThan(0);
});
it("should fetch full transcript with sentences", async () => {
const data = await mockClient.query(
`query($id: String!) { transcript(id: $id) { sentences { text } } }`,
{ id: "test-id" }
);
expect(data.transcript.sentences).toBeDefined();
});
it("should handle API errors gracefully", async () => {
const errorClient = {
query: vi.fn().mockRejectedValue(new Error("Fireflies: auth_failed")),
};
await expect(errorClient.query("{ user { email } }"))
.rejects.toThrow("auth_failed");
});
});
Step 5: Development Scripts
{
"scripts": {
"dev": "tsx watch src/index.ts",
"test": "vitest",
"test:watch": "vitest --watch",
"record-fixtures": "tsx scripts/record-fixtures.ts",
"typecheck": "tsc --noEmit"
}
}
Step 6: Environment Setup
set -euo pipefail
# Create .env from template
cp .env.example .env.local
# .env.example
echo 'FIREFLIES_API_KEY=your-key-here' > .env.example
# .gitignore additions
echo '.env.local' >> .gitignore
echo 'tests/fixtures/*.json' >> .gitignore
Error Handling
| Error | Cause | Solution |
|---|---|---|
| Fixture not found | Fixtures not recorded | Run npm run record-fixtures |
| Auth error in tests | Using real API key in CI | Use mock client, not real API |
| Type mismatch | API schema changed | Re-record fixtures, update types |
| Rate limit during recording | Too many fixture requests | Record once, commit fixtures |
Output
- Project structure with typed client and service layers
- Recorded API fixtures for offline testing
- Mock client for unit tests
- Dev scripts with hot reload and watch mode
Resources
Next Steps
See fireflies-sdk-patterns for production-ready client patterns.
More by jeremylongshore
View all skills by jeremylongshore →You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
pdf-to-markdown
aliceisjustplaying
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
Related MCP Servers
Browse all serversOfficial Laravel-focused MCP server for augmenting AI-powered local development. Provides deep context about your Larave
Foundry Toolkit: Deploy, test, and analyze smart contracts on EVM networks and local Anvil with powerful blockchain dev
Unlock AI-powered automation for Postman for API testing. Streamline workflows, code sync, and team collaboration with f
DebuggAI enables zero-config end to end testing for web applications, offering secure tunnels, easy setup, and detailed
Analyze your Cursor Chat History for coding insights, development patterns, and best practices with powerful search and
Simplify local cloud development with LocalStack tools to manage your container and related tasks. Ideal for Google Clou
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.