perplexity-observability
Set up monitoring for Perplexity Sonar API metrics including latency, costs, and citation counts. Track integration health in production.
Install
mkdir -p .claude/skills/perplexity-observability && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4784" && unzip -o skill.zip -d .claude/skills/perplexity-observability && rm skill.zipInstalls to .claude/skills/perplexity-observability
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Set up monitoring for Perplexity Sonar API with latency, cost, citationKey capabilities
- →Instrument Perplexity client for latency and error tracking
- →Export metrics in Prometheus format
- →Calculate citation quality scores based on domain authority
- →Estimate query costs based on model-specific token rates
- →Define alert thresholds for latency, citation counts, and error rates
How it works
The skill provides a wrapper for the Perplexity client to capture execution metrics and includes logic to export these to Prometheus, score citation quality, and calculate costs per model.
Inputs & outputs
When to use perplexity-observability
- →Implementing monitoring dashboards
- →Setting up production alerts
- →Tracking per-model API costs
- →Monitoring search latency
About perplexity-observability
This skill helps you instrument the Perplexity client to track key performance signals. It includes templates for defining alert thresholds for latency, cost, and citation quality.
Set up comprehensive observability for Perplexity integrations with metrics, traces, and alerts. Use when implementing monitoring for Perplexity operations, setting up dashboards, or configuring alerting for Perplexity integration health. Trigger with phrases like "perplexity monitoring", "perplexity metrics", "perplexity observability", "monitor perplexity", "perplexity alerts", "perplexity tracing".
When not to use it
- →Replacing incident response procedures
- →Handling non-Perplexity API integrations
Prerequisites
Limitations
- →Requires manual configuration of alert rules in Prometheus or Alertmanager
- →Citation quality scoring relies on a predefined list of authoritative domains
How it compares
Unlike manual logging, this provides structured templates for specific Perplexity signals like citation counts and model-specific cost estimation.
Compared to similar skills
perplexity-observability side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| perplexity-observability (this skill) | 1 | 2mo | No flags | Intermediate |
| langfuse | 7 | 8mo | No flags | Intermediate |
| instantly-observability | 2 | 2mo | Caution | Intermediate |
| documenso-observability | 0 | 2mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
langfuse
davila7
Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation.
instantly-observability
jeremylongshore
Set up comprehensive observability for Instantly integrations with metrics, traces, and alerts. Use when implementing monitoring for Instantly operations, setting up dashboards, or configuring alerting for Instantly integration health. Trigger with phrases like "instantly monitoring", "instantly metrics", "instantly observability", "monitor instantly", "instantly alerts", "instantly tracing".
documenso-observability
jeremylongshore
Implement monitoring, logging, and tracing for Documenso integrations. Use when setting up observability, implementing metrics collection, or debugging production issues. Trigger with phrases like "documenso monitoring", "documenso metrics", "documenso logging", "documenso tracing", "documenso observability".
setup-sap-btp-logging
leotrinh
Automates the setup of sap-btp-cloud-logging-client in a project.
mcp-builder
anthropics
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
telegram-mini-app
davila7
Expert in building Telegram Mini Apps (TWA) - web apps that run inside Telegram with native-like experience. Covers the TON ecosystem, Telegram Web App API, payments, user authentication, and building viral mini apps that monetize. Use when: telegram mini app, TWA, telegram web app, TON app, mini app.