perplexity-ci-integration
Configure CI/CD for Perplexity Sonar API integrations with GitHub Actions. Use when setting up automated testing, configuring CI pipelines, or integrating Perplexity tests into your build process. Trigger with phrases like "perplexity CI", "perplexity GitHub Actions", "perplexity automated tests", "CI perplexity pipeline".
Best use case
perplexity-ci-integration is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Configure CI/CD for Perplexity Sonar API integrations with GitHub Actions. Use when setting up automated testing, configuring CI pipelines, or integrating Perplexity tests into your build process. Trigger with phrases like "perplexity CI", "perplexity GitHub Actions", "perplexity automated tests", "CI perplexity pipeline".
Teams using perplexity-ci-integration should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/perplexity-ci-integration/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How perplexity-ci-integration Compares
| Feature / Agent | perplexity-ci-integration | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Configure CI/CD for Perplexity Sonar API integrations with GitHub Actions. Use when setting up automated testing, configuring CI pipelines, or integrating Perplexity tests into your build process. Trigger with phrases like "perplexity CI", "perplexity GitHub Actions", "perplexity automated tests", "CI perplexity pipeline".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# Perplexity CI Integration
## Overview
Set up CI/CD pipelines for Perplexity Sonar API integrations. Key CI concerns: live API calls cost money (use mocks for unit tests, reserve live calls for integration tests), API keys must be in GitHub Secrets, and rate limits apply even in CI.
## Prerequisites
- GitHub repository with Actions enabled
- Perplexity API key for CI (separate from production)
- Test suite with mocked and live test separation
## Instructions
### Step 1: Configure GitHub Secret
```bash
set -euo pipefail
# Store API key as a GitHub secret
gh secret set PERPLEXITY_API_KEY --body "pplx-your-ci-key-here"
```
### Step 2: GitHub Actions Workflow
```yaml
# .github/workflows/perplexity-tests.yml
name: Perplexity Integration Tests
on:
push:
branches: [main]
pull_request:
branches: [main]
jobs:
unit-tests:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: "20"
cache: "npm"
- run: npm ci
- run: npm test -- --coverage
# Unit tests use mocked responses — no API key needed
integration-tests:
runs-on: ubuntu-latest
needs: unit-tests
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
env:
PERPLEXITY_API_KEY: ${{ secrets.PERPLEXITY_API_KEY }}
steps:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: "20"
cache: "npm"
- run: npm ci
- name: Run live Perplexity integration tests
run: npm run test:integration
timeout-minutes: 5
```
### Step 3: Test Structure
```typescript
// tests/perplexity.unit.test.ts — runs on every PR, uses mocks
import { describe, it, expect, vi } from "vitest";
import fixture from "./fixtures/sonar-response.json";
vi.mock("openai", () => ({
default: vi.fn().mockImplementation(() => ({
chat: {
completions: {
create: vi.fn().mockResolvedValue(fixture),
},
},
})),
}));
describe("Perplexity Search (mocked)", () => {
it("parses citations from response", async () => {
const { search } = await import("../src/perplexity/search");
const result = await search("test query");
expect(result.citations.length).toBeGreaterThan(0);
});
it("formats answer with citation links", async () => {
const { formatCitationsAsMarkdown } = await import("../src/perplexity/citations");
const formatted = formatCitationsAsMarkdown("See [1] for details", ["https://example.com"]);
expect(formatted).toContain("[1](https://example.com)");
});
});
```
```typescript
// tests/perplexity.integration.test.ts — runs on main only, uses live API
import { describe, it, expect } from "vitest";
const LIVE = !!process.env.PERPLEXITY_API_KEY;
describe.skipIf(!LIVE)("Perplexity Live API", () => {
it("sonar returns answer with citations", async () => {
const { search } = await import("../src/perplexity/search");
const result = await search("What is TypeScript?", {
model: "sonar",
maxTokens: 100,
});
expect(result.answer).toBeTruthy();
expect(result.citations.length).toBeGreaterThan(0);
expect(result.usage.totalTokens).toBeGreaterThan(0);
}, 15000);
it("search_domain_filter restricts sources", async () => {
const { search } = await import("../src/perplexity/search");
const result = await search("Python latest release", {
model: "sonar",
maxTokens: 100,
searchDomainFilter: ["python.org"],
});
expect(result.citations.some((url: string) => url.includes("python.org"))).toBe(true);
}, 15000);
});
```
### Step 4: Cost-Aware CI
```yaml
# Only run live tests on main branch pushes (not every PR)
# Budget: ~$0.01 per test run (2 sonar queries at $0.005 each)
# Monthly estimate: 30 pushes/month = $0.30
# Add a weekly full integration test
weekly-integration:
runs-on: ubuntu-latest
if: github.event.schedule == '0 6 * * 1'
env:
PERPLEXITY_API_KEY: ${{ secrets.PERPLEXITY_API_KEY }}
steps:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: "20"
- run: npm ci
- run: npm run test:integration:full
timeout-minutes: 10
```
## Error Handling
| Issue | Cause | Solution |
|-------|-------|----------|
| Secret not found | Missing GitHub secret | Run `gh secret set PERPLEXITY_API_KEY` |
| Integration tests timeout | Complex sonar-pro queries | Use `sonar` with `max_tokens: 100` in CI |
| 429 in CI | Parallel jobs hitting rate limit | Serialize integration tests |
| High CI costs | Running live tests on every PR | Gate live tests on main branch only |
## Output
- Unit test suite with mocked Perplexity responses (runs on every PR)
- Integration test suite with live API (runs on main pushes)
- Cost-optimized CI that limits API calls
- GitHub Actions workflow file
## Resources
- [GitHub Actions Documentation](https://docs.github.com/en/actions)
- [Vitest Documentation](https://vitest.dev/)
## Next Steps
For deployment patterns, see `perplexity-deploy-integration`.Related Skills
running-integration-tests
Execute integration tests validating component interactions and system integration. Use when performing specialized testing. Trigger with phrases like "run integration tests", "test integration", or "validate component interactions".
workhuman-deploy-integration
Workhuman deploy integration for employee recognition and rewards API. Use when integrating Workhuman Social Recognition, or building recognition workflows with HRIS systems. Trigger: "workhuman deploy integration".
workhuman-ci-integration
Workhuman ci integration for employee recognition and rewards API. Use when integrating Workhuman Social Recognition, or building recognition workflows with HRIS systems. Trigger: "workhuman ci integration".
wispr-deploy-integration
Wispr Flow deploy integration for voice-to-text API integration. Use when integrating Wispr Flow dictation, WebSocket streaming, or building voice-powered applications. Trigger: "wispr deploy integration".
wispr-ci-integration
Wispr Flow ci integration for voice-to-text API integration. Use when integrating Wispr Flow dictation, WebSocket streaming, or building voice-powered applications. Trigger: "wispr ci integration".
windsurf-ci-integration
Integrate Windsurf Cascade workflows into CI/CD pipelines and team automation. Use when automating Cascade tasks in GitHub Actions, enforcing AI code quality gates, or setting up Windsurf config validation in CI. Trigger with phrases like "windsurf CI", "windsurf GitHub Actions", "windsurf automation", "cascade CI", "windsurf pipeline".
webflow-deploy-integration
Deploy Webflow-powered applications to Vercel, Fly.io, and Google Cloud Run with proper secrets management and Webflow-specific health checks. Trigger with phrases like "deploy webflow", "webflow Vercel", "webflow production deploy", "webflow Cloud Run", "webflow Fly.io".
webflow-ci-integration
Configure Webflow CI/CD with GitHub Actions — automated CMS validation, integration tests with test tokens, and publish-on-merge workflows. Use when setting up automated testing or CI pipelines for Webflow integrations. Trigger with phrases like "webflow CI", "webflow GitHub Actions", "webflow automated tests", "CI webflow", "webflow pipeline".
vercel-deploy-integration
Deploy and manage Vercel production deployments with promotion, rollback, and multi-region strategies. Use when deploying to production, configuring deployment regions, or setting up blue-green deployment patterns on Vercel. Trigger with phrases like "deploy vercel", "vercel production deploy", "vercel promote", "vercel rollback", "vercel regions".
veeva-deploy-integration
Veeva Vault deploy integration for REST API and clinical operations. Use when working with Veeva Vault document management and CRM. Trigger: "veeva deploy integration".
veeva-ci-integration
Veeva Vault ci integration for REST API and clinical operations. Use when working with Veeva Vault document management and CRM. Trigger: "veeva ci integration".
vastai-deploy-integration
Deploy ML training jobs and inference services on Vast.ai GPU cloud. Use when deploying GPU workloads, configuring Docker images, or setting up automated deployment scripts. Trigger with phrases like "deploy vastai", "vastai deployment", "vastai docker", "vastai production deploy".