exa-sdk-patterns
Apply production-ready exa-js SDK patterns with type safety, singletons, and wrappers. Use when implementing Exa integrations, refactoring SDK usage, or establishing team coding standards for Exa. Trigger with phrases like "exa SDK patterns", "exa best practices", "exa code patterns", "idiomatic exa", "exa wrapper".
What this skill does
# Exa SDK Patterns
## Overview
Production-ready patterns for the `exa-js` SDK. Covers client singletons, typed wrappers, error handling, retry logic, and response validation for real Exa API methods.
## Prerequisites
- `exa-js` installed and `EXA_API_KEY` configured
- TypeScript project with strict mode
- Familiarity with async/await and error handling
## Instructions
### Step 1: Client Singleton
```typescript
// src/exa/client.ts
import Exa from "exa-js";
let instance: Exa | null = null;
export function getExa(): Exa {
if (!instance) {
const apiKey = process.env.EXA_API_KEY;
if (!apiKey) {
throw new Error("EXA_API_KEY not set. Get one at https://dashboard.exa.ai");
}
instance = new Exa(apiKey);
}
return instance;
}
```
### Step 2: Typed Search Wrapper
```typescript
// src/exa/search.ts
import Exa from "exa-js";
import { getExa } from "./client";
interface ExaSearchOptions {
type?: "auto" | "neural" | "keyword" | "fast" | "instant" | "deep" | "deep-reasoning";
numResults?: number;
includeDomains?: string[];
excludeDomains?: string[];
startPublishedDate?: string;
endPublishedDate?: string;
category?: "company" | "research paper" | "news" | "tweet" | "personal site" | "financial report" | "people";
includeText?: string[];
excludeText?: string[];
}
interface ExaContentsOptions {
text?: boolean | { maxCharacters?: number; includeHtmlTags?: boolean };
highlights?: boolean | { maxCharacters?: number; query?: string };
summary?: boolean | { query?: string };
livecrawl?: "always" | "preferred" | "fallback" | "never";
livecrawlTimeout?: number;
subpages?: number;
subpageTarget?: string | string[];
}
export async function exaSearch(query: string, opts: ExaSearchOptions = {}) {
const exa = getExa();
return exa.search(query, {
type: opts.type ?? "auto",
numResults: opts.numResults ?? 10,
...opts,
});
}
export async function exaSearchWithContents(
query: string,
searchOpts: ExaSearchOptions = {},
contentOpts: ExaContentsOptions = {}
) {
const exa = getExa();
return exa.searchAndContents(query, {
type: searchOpts.type ?? "auto",
numResults: searchOpts.numResults ?? 10,
...searchOpts,
...contentOpts,
});
}
```
### Step 3: Error Handling Wrapper
```typescript
// src/exa/safe.ts
interface ExaResult<T> {
data: T | null;
error: ExaError | null;
}
interface ExaError {
status: number;
message: string;
tag?: string;
requestId?: string;
retryable: boolean;
}
function classifyError(err: any): ExaError {
const status = err.status || err.response?.status || 500;
const retryable = status === 429 || status >= 500;
return {
status,
message: err.message || "Unknown error",
tag: err.error_tag || err.tag,
requestId: err.requestId || err.request_id,
retryable,
};
}
export async function safeExaCall<T>(
operation: () => Promise<T>
): Promise<ExaResult<T>> {
try {
const data = await operation();
return { data, error: null };
} catch (err: any) {
const error = classifyError(err);
console.error(`[Exa Error] ${error.status}: ${error.message}`, {
tag: error.tag,
requestId: error.requestId,
retryable: error.retryable,
});
return { data: null, error };
}
}
// Usage:
// const { data, error } = await safeExaCall(() =>
// exa.searchAndContents("query", { numResults: 5, text: true })
// );
```
### Step 4: Retry with Exponential Backoff
```typescript
// src/exa/retry.ts
export async function withRetry<T>(
operation: () => Promise<T>,
config = { maxRetries: 3, baseDelayMs: 1000, maxDelayMs: 30000 }
): Promise<T> {
for (let attempt = 0; attempt <= config.maxRetries; attempt++) {
try {
return await operation();
} catch (err: any) {
const status = err.status || err.response?.status || 0;
// Only retry on rate limits (429) and server errors (5xx)
if (status !== 429 && (status < 500 || status >= 600)) throw err;
if (attempt === config.maxRetries) throw err;
const delay = Math.min(
config.baseDelayMs * Math.pow(2, attempt) + Math.random() * 500,
config.maxDelayMs
);
console.log(`[Exa] Retry ${attempt + 1}/${config.maxRetries} in ${delay.toFixed(0)}ms`);
await new Promise(r => setTimeout(r, delay));
}
}
throw new Error("Unreachable");
}
// Usage:
// const results = await withRetry(() =>
// exa.searchAndContents("query", { numResults: 5, text: true })
// );
```
### Step 5: Response Validation with Zod
```typescript
// src/exa/validate.ts
import { z } from "zod";
const ExaResultSchema = z.object({
url: z.string().url(),
title: z.string().nullable(),
score: z.number(),
publishedDate: z.string().nullable().optional(),
text: z.string().optional(),
highlights: z.array(z.string()).optional(),
summary: z.string().optional(),
});
const ExaSearchResponseSchema = z.object({
results: z.array(ExaResultSchema),
autopromptString: z.string().optional(),
});
export function validateSearchResponse(response: unknown) {
return ExaSearchResponseSchema.parse(response);
}
```
## Error Handling
| Pattern | Use Case | Benefit |
|---------|----------|---------|
| Singleton | All API calls | Single client instance, consistent config |
| Safe wrapper | Non-critical searches | Prevents uncaught exceptions |
| Retry logic | Rate limits and 5xx | Automatic recovery from transient failures |
| Zod validation | Response processing | Catches unexpected API response changes |
| Typed options | IDE support | Autocomplete and compile-time checks |
## Examples
### Factory Pattern (Multi-tenant)
```typescript
const clients = new Map<string, Exa>();
export function getExaForTenant(tenantId: string): Exa {
if (!clients.has(tenantId)) {
const apiKey = getTenantApiKey(tenantId); // from your config/vault
clients.set(tenantId, new Exa(apiKey));
}
return clients.get(tenantId)!;
}
```
### Combined: Safe + Retry + Typed
```typescript
async function resilientSearch(query: string) {
return safeExaCall(() =>
withRetry(() =>
exaSearchWithContents(
query,
{ type: "neural", numResults: 5 },
{ text: { maxCharacters: 2000 }, highlights: true }
)
)
);
}
```
## Resources
- [exa-js TypeScript SDK](https://docs.exa.ai/sdks/typescript-sdk-specification)
- [Exa Error Codes](https://docs.exa.ai/reference/error-codes)
- [Zod Documentation](https://zod.dev/)
## Next Steps
Apply patterns in `exa-core-workflow-a` for real-world search usage.
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.