"call", "dial", "phone"?
initiate_call / schedule_call
← Skill registry
Communication & knowledgePublic skills
Voice & Communications
Voice operations for AI agents — calls, transcription, sentiment analysis, IVR management, recordings, and call center analytics via Twilio, Vonage, and Deepgram.
What this skill teaches
A reusable playbook for a specific kind of work.
An MCP server tells an agent which actions are available. A skill adds the judgment around those actions: how to recognize the job, which sequence to follow, what to avoid, and how to decide that the result is complete.
Orchestrate voice operations — manage calls, transcribe conversations, analyze sentiment, configure IVR, access recordings, and track call center analytics. Use when making calls, reviewing transcripts, analyzing call sentiment, managing IVR menus, searching call history, or checking agent performance.
Architecture
How Voice & Communications guides an ADK-Rust agent.
The skill stays readable and portable because it contains instructions rather than service credentials or business data. ADK-Rust supplies it to the agent, the agent chooses from its reviewed tool boundary, and the connected MCP server performs the authenticated operation.
01
User request
The agent receives a goal expressed in ordinary language.
02
Voice & Communications skill
Matches intent, supplies the decision guide, and narrows the tool boundary.
03
ADK-Rust agent
Plans the workflow and streams each meaningful step through the runtime.
04
mcp-voice
Executes authenticated operations against the system that owns the capability.
05
Verified result
The skill's completion rules shape the evidence returned to the user.
Decision guide
How the agent turns a request into the right action.
These routes come directly from the skill instructions. They help the model recognize intent and select a focused tool or workflow instead of improvising across the entire capability surface.
"transcript", "what was said"?
get_transcript / search_transcripts
"sentiment", "how did it go", "tone"?
analyze_sentiment / get_sentiment_trends
"IVR", "menu", "routing"?
get_ivr_menu / update_ivr_menu
"recording", "listen"?
list_recordings / get_recording
"metrics", "performance", "agents"?
get_call_metrics / get_agent_stats
"queue", "wait time"?
list_queues
"transfer", "route"?
transfer_call / route_call
Proven workflows
Repeatable sequences for useful outcomes.
A workflow joins several tool calls into a task the user actually recognizes. The skill explains the sequence and the intended result while ADK-Rust streams the agent's progress through the shared runtime.
013 calls
Post-Call Intelligence
Action items from every call
022-3 calls
Call Center Monitoring
Queue health + agent performance
031 calls
Sentiment Analysis
Detect unhappy customers early
042 calls
IVR Management
Optimize call routing
051 calls
Transcript Search
Find any conversation by keyword
Tool boundary
The skill may use 20 documented tools.
This allowlist is declared by the skill. It keeps the agent focused on the actions needed for this job while mcp-voice retains responsibility for authentication, validation, and the connected system.
list_calls
get_call
initiate_call
transfer_call
end_call
schedule_call
get_transcript
get_call_summary
analyze_sentiment
search_transcripts
get_ivr_menu
update_ivr_menu
list_queues
route_call
list_recordings
get_recording
delete_recording
get_call_metrics
get_agent_stats
get_sentiment_trends
Working rules
What the agent should do.
- Transcribe every call for searchability
- Analyze sentiment on customer-facing calls
- Log call summaries to CRM automatically
- Delete recordings when requested (GDPR)
Operating boundaries
What the agent should avoid.
- Don't initiate calls without explicit user request
- Don't delete recordings without GDPR/legal justification
- Don't expose call recordings to unauthorized parties
Install and connect
Add the skill beside the capability it expects.
Install the repository where your ADK-Rust skill loader can discover it, connect mcp-voice, and confirm the declared tools are available before asking the agent to use the workflow.
Install the skill
git clone https://github.com/zavora-ai/skill-voice-communications.git ~/.skills/skills/voice-communicationsADK-Rust loading shape
let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("voice-communications").await?;
let agent = LlmAgentBuilder::new("agent")
.instruction(skill.instructions())
.tools(skill.allowed_tools(toolset)?)
.build()?;The repository's compatibility statement: Requires mcp-voice server connected (Twilio, Vonage, Deepgram).
Official documentation
Read the complete skill package.
The repository remains authoritative for its exact instructions, examples, helper scripts, assets, MCP requirements, license, and later updates.
Keep exploring
More in communication & knowledge.
Analytics & Reporting Skill (Revenue Intelligence)Revenue intelligence for AI agents — metrics, funnels, anomaly detection, forecasting, and dashboards. Don't just pull numbers — find the story, explain why, and recommend action.22 allowed toolsCalendar & SchedulingSmart scheduling for AI agents — find free time across timezones, book meetings, manage events, and coordinate calendars via Google Calendar and Microsoft Graph.10 allowed toolsContent ManagementUnified content platform for AI agents — articles, social media, YouTube, media library, SEO, and publishing workflows via mcp-cms (26 tools).11 allowed tools
Source record
Repository metadata for this skill entry.
- License
- Apache-2.0
- Allowed tools
- 20
- References
- 3
- Revision
- 2aa0e535ca4b
- Updated
- May 31, 2026