exa-local-dev-loop
Configure Exa local development with hot reload, testing, and mock responses. Use when setting up a development environment, writing tests against Exa, or establishing a fast iteration cycle. Trigger with phrases like "exa dev setup", "exa local development", "exa test setup", "develop with exa", "mock exa".
What this skill does
# Exa Local Dev Loop
## Overview
Set up a fast, reproducible local development workflow for Exa integrations. Covers project structure, mock responses for unit tests, integration test patterns, and hot-reload configuration.
## Prerequisites
- `exa-js` installed and `EXA_API_KEY` configured
- Node.js 18+ with npm/pnpm
- `vitest` for testing (or `jest`)
## Instructions
### Step 1: Project Structure
```
my-exa-project/
├── src/
│ ├── exa/
│ │ ├── client.ts # Singleton Exa client
│ │ ├── search.ts # Search wrappers
│ │ └── types.ts # Typed interfaces
│ └── index.ts
├── tests/
│ ├── exa.unit.test.ts # Mock-based unit tests
│ └── exa.integration.test.ts # Real API tests (needs key)
├── .env.local # Local secrets (git-ignored)
├── .env.example # Template for team
├── tsconfig.json
├── vitest.config.ts
└── package.json
```
### Step 2: Package Setup
```json
{
"scripts": {
"dev": "tsx watch src/index.ts",
"test": "vitest",
"test:unit": "vitest --testPathPattern=unit",
"test:integration": "vitest --testPathPattern=integration",
"build": "tsc"
},
"dependencies": {
"exa-js": "^1.0.0"
},
"devDependencies": {
"tsx": "^4.0.0",
"vitest": "^2.0.0",
"typescript": "^5.0.0"
}
}
```
### Step 3: Mock Exa for Unit Tests
```typescript
// tests/exa.unit.test.ts
import { describe, it, expect, vi, beforeEach } from "vitest";
// Mock the exa-js module
vi.mock("exa-js", () => {
return {
default: vi.fn().mockImplementation(() => ({
search: vi.fn().mockResolvedValue({
results: [
{ url: "https://example.com/1", title: "Test Result 1", score: 0.95 },
{ url: "https://example.com/2", title: "Test Result 2", score: 0.87 },
],
}),
searchAndContents: vi.fn().mockResolvedValue({
results: [
{
url: "https://example.com/1",
title: "Test Result 1",
score: 0.95,
text: "This is the full text content of the page.",
highlights: ["Key excerpt from the page"],
summary: "A summary of the page content.",
},
],
}),
findSimilar: vi.fn().mockResolvedValue({
results: [
{ url: "https://similar.com/1", title: "Similar Page", score: 0.82 },
],
}),
getContents: vi.fn().mockResolvedValue({
results: [
{ url: "https://example.com/1", title: "Page", text: "Content" },
],
}),
})),
};
});
import Exa from "exa-js";
describe("Exa Search", () => {
let exa: any;
beforeEach(() => {
exa = new Exa("test-key");
});
it("should return search results", async () => {
const result = await exa.search("test query", { numResults: 5 });
expect(result.results).toHaveLength(2);
expect(result.results[0].score).toBeGreaterThan(0.9);
});
it("should return content with searchAndContents", async () => {
const result = await exa.searchAndContents("test", { text: true });
expect(result.results[0].text).toBeDefined();
expect(result.results[0].highlights).toHaveLength(1);
});
});
```
### Step 4: Integration Tests (Real API)
```typescript
// tests/exa.integration.test.ts
import { describe, it, expect } from "vitest";
import Exa from "exa-js";
// Skip if no API key available (CI without secrets)
const describeWithKey = process.env.EXA_API_KEY
? describe
: describe.skip;
describeWithKey("Exa Integration", () => {
const exa = new Exa(process.env.EXA_API_KEY!);
it("should execute a basic search", async () => {
const result = await exa.search("test connectivity", { numResults: 1 });
expect(result.results.length).toBeGreaterThanOrEqual(1);
expect(result.results[0].url).toMatch(/^https?:\/\//);
}, 10000); // 10s timeout for API calls
it("should return text content", async () => {
const result = await exa.searchAndContents("TypeScript tutorial", {
numResults: 1,
text: { maxCharacters: 500 },
});
expect(result.results[0].text).toBeDefined();
expect(result.results[0].text!.length).toBeGreaterThan(0);
}, 15000);
it("should find similar pages", async () => {
const result = await exa.findSimilar("https://nodejs.org", {
numResults: 3,
});
expect(result.results.length).toBeGreaterThanOrEqual(1);
}, 10000);
});
```
### Step 5: Environment Configuration
```bash
set -euo pipefail
# Create .env.example template (commit this)
cat > .env.example << 'EOF'
# Exa API — get key at https://dashboard.exa.ai
EXA_API_KEY=
EOF
# Create local env (git-ignored)
cp .env.example .env.local
echo "EXA_API_KEY=your-key-here" > .env.local
```
## Error Handling
| Error | Cause | Solution |
|-------|-------|----------|
| `Cannot find module 'exa-js'` | Not installed | Run `npm install exa-js` |
| Test timeout | Slow API response | Increase vitest timeout to 15000ms |
| Mock not applied | Import order issue | Ensure `vi.mock()` is before imports |
| Integration test fails in CI | No API key secret | Add `EXA_API_KEY` to CI secrets or skip |
## Examples
### Vitest Config for Exa Projects
```typescript
// vitest.config.ts
import { defineConfig } from "vitest/config";
export default defineConfig({
test: {
globals: true,
environment: "node",
testTimeout: 15000, // Exa API calls can take a few seconds
setupFiles: ["dotenv/config"],
},
});
```
## Resources
- [Vitest Documentation](https://vitest.dev/)
- [tsx Documentation](https://github.com/privatenumber/tsx)
- [exa-js on npm](https://www.npmjs.com/package/exa-js)
## Next Steps
See `exa-sdk-patterns` for production-ready code patterns.
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.