mcpField
V
vapi

vapi

github.com/gracebotlyData & databases070 installsUpdated 31w ago
Repository

About vapi

A skill for analyzing Vapi voice-call data in Getflowetic. It defines event-field mappings and dashboard metrics for tracking call outcomes, assistant performance, and costs.

Key features

  1. 01Maps Vapi call fields to event data
  2. 02Defines call volume and success metrics
  3. 03Tracks duration and per-call cost
  4. 04Outlines assistant comparison dashboards
  5. 05Supports legacy field-name aliases

Use cases

  1. 01Build call-volume and success dashboards
  2. 02Compare call counts by assistant
  3. 03Review call duration and spending

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/gracebotly/flowetic-app --skill vapi

After installing, type/vapiin Claude Code to confirm it loaded.

Bundled filesfield-semantics.yaml

Details

From the project README

Vapi Platform Skill

Overview

Vapi is a voice AI platform for building phone agents. Users connect Vapi assistants to Getflowetic to monitor call performance, track costs, and analyze conversation outcomes.

Vocabulary

  • call: A single voice interaction between an assistant and a caller
  • assistant: A configured Vapi voice agent with a system prompt, model, and voice
  • ended_reason: Why the call terminated (hangup, voicemail, error, silence-timeout, max-duration)
  • cost: Per-call cost in USD based on duration + model usage
  • transcript: Full text of the conversation
  • status: Call outcome — ended (success) or other values (failure)

Key Metrics for Dashboards

  • Call Volume: Total calls over time — trend chart on started_at
  • Success Rate: Percentage of calls with status=success — hero stat
  • Avg Duration: Average call length in ms — supporting metric card
  • Cost per Call: Total cost divided by call count — supporting metric
  • Assistant Breakdown: Calls per assistant — pie chart on assistant_name/workflow_name

Event Field Mapping

The Vapi import route normalizes call data into the standard event schema. These are the fields that appear in event.state:

Event FieldSemantic TypeDashboard Use
workflow_ididentifierMaps to assistant_id — count only
workflow_namedimensionMaps to assistant name — breakdown charts
execution_idsurrogate_keyMaps to call_id — "Total Calls" KPI
statusdimensionSuccess rate percentage — hero stat
duration_msmeasure (avg)"Avg Call Duration" metric card
started_attime_dimensionTimeseries trend axis
ended_attime_dimensionDetail only
platformconstantAlways "vapi" — skip

These fields also appear in event.labels:

  • assistant_id, assistant_name, call_id, status

Dashboard Templates

  • voice-analytics: Call volume trend, success rate, avg duration, assistant breakdown
  • assistant-performance: Per-assistant comparison with call counts and durations
  • cost-tracker: Cost trends over time, cost per call, total spend

Mapping Heuristics (Legacy Aliases)

These field name variations should resolve to the canonical names above:

  • duration: call_duration_seconds | duration | call_length → duration_ms
  • status: status | call_status | outcome → status
  • cost: cost_usd | cost | price → cost

Comments

Markdown supported