Agent skill
retell
Mapping guidance for Retell AI voice agent events. Covers call metrics, agent performance, disconnect reasons, and conversation analytics.
Install this agent skill to your Project
npx add-skill https://github.com/gracebotly/flowetic-app/tree/main/workspace/skills/retell
Metadata
Additional technical details for this skill
- author
- getflowetic
- phase scope
- all
SKILL.md
Retell Platform Skill
Overview
Retell is a conversational AI platform for building voice agents. Users connect Retell agents to Getflowetic to monitor call quality, track agent performance, and analyze conversation patterns.
Vocabulary
- call: A single voice interaction between a Retell agent and a caller
- agent: A configured Retell voice agent with an LLM backend and voice
- call_status: Call outcome —
endedorcompleted(success) vs other (failure) - disconnect_reason: Why the call ended (agent_hangup, user_hangup, error, silence, max_duration)
- duration_ms: Call length in milliseconds
- start_timestamp / end_timestamp: Unix timestamps for call timing
Key Metrics for Dashboards
- Call Volume: Total calls over time — trend chart on started_at
- Success Rate: Percentage of calls with successful outcome — hero stat
- Avg Duration: Average call length in ms — supporting metric card
- Agent Breakdown: Calls per agent — pie chart on agent_name/workflow_name
- Disconnect Reasons: Why calls end — pie chart for quality monitoring
Event Field Mapping
The Retell import route normalizes call data into the standard event schema. These are the fields that appear in event.state:
| Event Field | Semantic Type | Dashboard Use |
|---|---|---|
| workflow_id | identifier | Maps to agent_id — count only |
| workflow_name | dimension | Maps to agent_name — breakdown charts |
| execution_id | surrogate_key | Maps to call_id — "Total Calls" KPI |
| status | dimension | Success rate percentage — hero stat |
| duration_ms | measure (avg) | "Avg Call Duration" metric card |
| started_at | time_dimension | Timeseries trend axis |
| ended_at | time_dimension | Detail only |
| platform | constant | Always "retell" — skip |
These fields also appear in event.labels:
- agent_id, agent_name, call_id, status
Dashboard Templates
- voice-analytics: Call volume trend, success rate, avg duration, agent breakdown
- agent-performance: Per-agent comparison, disconnect reasons, quality metrics
- quality-monitor: Disconnect reason trends, error rates, duration outliers
Mapping Heuristics (Legacy Aliases)
- call_status → status
- agent_id → workflow_id
- agent_name → workflow_name
- call_id → execution_id
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
gracebotly/flowetic-app
business-outcomes-advisor
Skeleton-intelligent revenue strategy for AI automation agencies. Frames proposals through monetization lenses across all UI types — dashboards, product pages, and admin panels. Knows the full skeleton catalog, SaaS wrapper productization flow, and enrichment boundaries. Active in propose phase only. Max 1-2 questions, plain language, agency-native vocabulary.
gracebotly/flowetic-app
ui-ux-pro-max
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.
gracebotly/flowetic-app
make
Mapping guidance for Make.com (Integromat) scenario events. Covers execution metrics, scenario performance, operation counts, and module analytics.
gracebotly/flowetic-app
data-dashboard-intelligence
Universal intelligence for turning normalized event data into premium, story-driven dashboards. Covers field-to-component mapping, aggregation selection, dashboard story structure, hero stat detection, and graceful degradation. Use this skill whenever generating a dashboard spec, editing dashboard components, choosing chart types, deciding aggregation methods, handling empty or sparse data, writing component headlines, ordering components on a dashboard, or picking which metric should be the hero stat. Even if the user doesn't say "dashboard intelligence", use this skill for ANY dashboard generation or editing task.
gracebotly/flowetic-app
vapi
Mapping guidance for Vapi voice AI events. Covers call metrics, assistant performance, cost tracking, and transcript handling. Use for any Vapi-connected dashboard generation or editing task.
gracebotly/flowetic-app
n8n
Dashboard-first journey guidance for n8n. Use when a user connected n8n and wants a Workflow Activity Dashboard (default) with auto-mapping and live preview, and optionally to turn a workflow into a product.
Didn't find tool you were looking for?