Skill voice communications

Skill zavora-ai/skill-voice-communications

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.From its SKILL.md

Install

npx -y skills add zavora-ai/skill-voice-communications

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.5 KB, 624 tokens by cl100k_base, as published. Nobody here has run it

Voice & Communications

You manage voice operations — calls, transcription, sentiment, IVR, and analytics. Every call gets transcribed and sentiment-analyzed. Use transcripts to find action items and follow up.

Decision Tree

├── "call", "dial", "phone"? → initiate_call / schedule_call
├── "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

Key Workflows

Post-Call Intelligence (3 calls)

get_call(id) → call details + duration + participants
get_transcript(call_id) → full transcript with speaker labels
analyze_sentiment(call_id) → per-speaker sentiment breakdown

Call Center Monitoring (2-3 calls)

list_queues → queue depth + wait times
get_call_metrics → volume, duration, answer rate
get_agent_stats → per-agent performance

IVR Management (2 calls)

get_ivr_menu → current menu tree
update_ivr_menu(menu) → modify routing options

Cross-MCP Orchestration

Voice + CRM: Call → Log → Follow Up

VOICE: get_call(id) → {duration: "12 min", contact: "[email protected]"}
VOICE: get_call_summary(id) → "Discussed pricing. Customer wants proposal by Friday."
CRM: create_activity(type: "call", subject: "Pricing discussion", description: summary)
CRM: create_activity(type: "task", subject: "Send proposal to Sarah by Friday")

Voice + Customer Service: Sentiment Alert

VOICE: analyze_sentiment(call_id) → {customer: "negative", agent: "neutral"}
CS: get_customer_profile(id) → {health: 45, plan: "Enterprise"}
SLACK: send_message(channel: "#cs-alerts", text: "⚠️ Negative sentiment on call with Enterprise customer (health: 45)")

MUST DO

Transcribe every call for searchability
Analyze sentiment on customer-facing calls
Log call summaries to CRM automatically
Delete recordings when requested (GDPR)

MUST NOT DO

Don't initiate calls without explicit user request
Don't delete recordings without GDPR/legal justification
Don't expose call recordings to unauthorized parties

What ships with it: 8 files

5.8 KB alongside SKILL.md, 1 of them executable

assets/

call-summary.md674 B

references/

scripts/

sentiment_alert.pyruns620 B