Execute Perplexity primary workflow: Core Workflow A. Use when implementing primary use case, building main features, or core integration tasks. Trigger with phrases like "perplexity main workflow", "primary task with perplexity".
From perplexity-packnpx claudepluginhub nickloveinvesting/nick-love-plugins --plugin perplexity-packThis skill is limited to using the following tools:
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.
Primary money-path workflow for Perplexity. This is the most common use case. Perplexity is an AI-powered answer engine that grounds its responses in real-time web searches, providing cited, up-to-date answers rather than responses based solely on training data. It is particularly valuable for research tasks that require current information, such as market analysis, technology trend monitoring, or fact-checking against live sources.
perplexity-install-auth setupAuthenticate with the Perplexity API and select the appropriate model — sonar for fast web-grounded answers or sonar-pro for deeper research with extended search coverage. Configure your system prompt if you want to shape the response format, language, or domain focus for your use case.
// Step 1 implementation
Submit your research query to the Perplexity chat completions endpoint. The model will retrieve relevant web sources and synthesize a grounded answer. Examine the citations field in the response to identify which sources were consulted. Verify that the cited pages actually support the claims made in the answer before presenting the information externally.
// Step 2 implementation
Extract the answer text and citations from the API response. Format the citations as hyperlinks or footnotes according to your output requirements. If the answer is being incorporated into a document or report, note the query date alongside each citation since web content can change over time.
// Step 3 implementation
| Error | Cause | Solution |
|---|---|---|
| Error 1 | Cause | Solution |
| Error 2 | Cause | Solution |
// Complete workflow example
For secondary workflow, see perplexity-core-workflow-b.