AGENT SKILL

retellai-observability

Set up comprehensive observability for Retell AI integrations with metrics, traces, and alerts. Use when implementing monitoring for Retell AI operations, setting up dashboards, or configuring alerting for Retell AI integration health. Trigger with phrases like "retellai monitoring", "retellai metrics", "retellai observability", "monitor retellai", "retellai alerts", "retellai tracing".

License 许可
MIT
最近更新
2026-05-26
Stars
★ 0
Forks
0

01 前言 Front Matter

name
retellai-observability
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
version
1.0.0
description
Set up comprehensive observability for Retell AI integrations with metrics, traces, and alerts. Use when implementing monitoring for Retell AI operations, setting up dashboards, or configuring alerting for Retell AI integration health. Trigger with phrases like "retellai monitoring", "retellai metrics", "retellai observability", "monitor retellai", "retellai alerts", "retellai tracing".
allowed-tools
Read, Write, Edit
compatible-with
claude-code, codex, openclaw

03 SKILL.md 正文

Retell AI Observability

Overview

Monitor Retell AI voice agent performance, call quality, and costs. Key signals include call completion rate (successful conversations vs dropped/failed calls), average call duration, latency between user speech and agent response (conversational latency), per-minute cost tracking, and agent-level success metrics (did the voice agent accomplish its goal).

Prerequisites

  • Retell AI account with active voice agents
  • API access for call data queries
  • Webhook endpoint for real-time call events

Instructions

Step 1: Monitor Call Quality via Webhooks

// retell-webhook-handler.ts
app.post('/webhooks/retell', (req, res) => {
  const { call_id, agent_id, status, duration_seconds, cost_usd, disconnect_reason } = req.body;

  emitCounter('retell_calls_total', 1, { agent: agent_id, status });
  emitHistogram('retell_call_duration_sec', duration_seconds, { agent: agent_id });
  emitCounter('retell_cost_usd', cost_usd, { agent: agent_id });

  if (disconnect_reason === 'agent_error' || disconnect_reason === 'system_error') {
    emitCounter('retell_call_errors_total', 1, { agent: agent_id, reason: disconnect_reason });
  }

  res.sendStatus(200);  # HTTP 200 OK
});

Step 2: Track Conversational Latency

set -euo pipefail
# Query recent calls for response latency metrics
curl "https://api.retellai.com/v1/calls?limit=20&sort=-created_at" \
  -H "Authorization: Bearer $RETELL_API_KEY" | \
  jq '.[] | {
    call_id, agent_name, duration_sec: .duration,
    avg_response_latency_ms: .avg_agent_response_latency_ms,
    cost_usd: .cost,
    disconnect_reason
  }'

Step 3: Monitor Per-Agent Performance

// Track which agents are performing well vs poorly
async function agentPerformanceReport() {
  const agents = await retellApi.listAgents();
  for (const agent of agents) {
    const calls = await retellApi.listCalls({ agent_id: agent.agent_id, limit: 100 });
    const completed = calls.filter(c => c.status === 'completed').length;
    const avgDuration = calls.reduce((s, c) => s + c.duration, 0) / calls.length;
    const totalCost = calls.reduce((s, c) => s + c.cost, 0);

    emitGauge('retell_agent_completion_rate', completed / calls.length * 100, { agent: agent.agent_name });
    emitGauge('retell_agent_avg_duration_sec', avgDuration, { agent: agent.agent_name });
    emitGauge('retell_agent_total_cost_usd', totalCost, { agent: agent.agent_name });
  }
}

Step 4: Alert on Voice Quality Issues

groups:
  - name: retell
    rules:
      - alert: RetellHighDropRate
        expr: rate(retell_calls_total{status="failed"}[1h]) / rate(retell_calls_total[1h]) > 0.1
        annotations: { summary: "Retell call failure rate exceeds 10%" }
      - alert: RetellHighLatency
        expr: histogram_quantile(0.95, rate(retell_response_latency_ms_bucket[1h])) > 2000  # 2000: 2 seconds in ms
        annotations: { summary: "Retell agent response latency P95 exceeds 2 seconds" }
      - alert: RetellCostSpike
        expr: increase(retell_cost_usd[1h]) > 50
        annotations: { summary: "Retell voice costs exceed $50/hour" }
      - alert: RetellShortCalls
        expr: histogram_quantile(0.25, rate(retell_call_duration_sec_bucket[1h])) < 10
        annotations: { summary: "25% of calls ending in <10 seconds (agent issue?)" }

Step 5: Dashboard Panels

Track: call volume by agent, call completion rate (pie chart), duration distribution, per-minute cost trend, conversational latency p50/p95, disconnect reasons breakdown, and daily cost by agent. Short calls (<10s) often indicate agent prompt issues where the bot fails to engage.

Error Handling

Issue Cause Solution
High call drop rate Agent prompt causing hang-ups Review and simplify agent greeting prompt
Latency >2 seconds LLM response slow Use faster model or reduce prompt complexity
Unexpected high costs Long average call duration Add conversation time limits in agent config
No webhook events Endpoint unreachable Verify webhook URL and SSL certificate

Examples

Basic usage: Apply retellai observability to a standard project setup with default configuration options.

Advanced scenario: Customize retellai observability for production environments with multiple constraints and team-specific requirements.

Output

  • Configuration files or code changes applied to the project
  • Validation report confirming correct implementation
  • Summary of changes made and their rationale

Resources

  • Official monitoring documentation
  • Community best practices and patterns
  • Related skills in this plugin pack

04 同仓库更多 Skills

SamuelChien
SamuelChien/mega-skills-collection

zustand-store-ts

Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state/action separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.

★ 0
SamuelChien
SamuelChien/mega-skills-collection

zustand-store-creator

Zustand Store Creator - Auto-activating skill for Frontend Development. Triggers on: zustand store creator, zustand store creator Part of the Frontend Development skill category.

★ 0
SamuelChien
SamuelChien/mega-skills-collection

zero-trust-config-helper

Zero Trust Config Helper - Auto-activating skill for Security Advanced. Triggers on: zero trust config helper, zero trust config helper Part of the Security Advanced skill category.

★ 0
SamuelChien
SamuelChien/mega-skills-collection

zapier-integration-helper

Zapier Integration Helper - Auto-activating skill for Business Automation. Triggers on: zapier integration helper, zapier integration helper Part of the Business Automation skill category.

★ 0
SamuelChien
SamuelChien/mega-skills-collection

zai-cli

Execute z.AI CLI providing vision, search, reader, and GitHub exploration via CLI and MCP. Use when user needs image/video analysis, OCR, UI-to-code conversion, error diagnosis, real-time web search, web page to markdown extraction, or GitHub code exploration. Trigger with phrases like "analyze this image", "search the web for", "read this page", "explore this repo", or "use zai". Requires Z_AI_API_KEY.

★ 0
SamuelChien
SamuelChien/mega-skills-collection

yt-research

Research competitor YouTube channels, niches, and trending topics for your content strategy. Use this skill whenever the user says "research channels", "analyze competitors", "find trending topics", "niche analysis", "competitive research", "what are other creators doing", "scrape YouTube channels", or wants to understand the competitive landscape for a specific tool or topic area. Use when working with yt research. Trigger with 'yt', 'research'.

★ 0