"handle", "respond", "reply", "conversation"?
WORKFLOW 1: Handle Conversation
← Skill registry
Business operationsPublic skills
Customer Service Operations
AI-powered customer service — KB-first resolution, churn prediction, intelligent routing, and satisfaction tracking. Triage → Understand → Resolve → Respond → Close.
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 customer service workflows — triage conversations, assess churn risk, resolve with KB-first approach, route intelligently, and track satisfaction. Use when handling support conversations, checking customer health, assessing churn risk, finding help articles, drafting responses, escalating issues, reviewing…
Architecture
How Customer Service Operations 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
Customer Service Operations 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-customer-service
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.
"churn", "at risk", "health", "retention"?
WORKFLOW 2: Churn Prevention
"queue", "backlog", "waiting", "SLA"?
WORKFLOW 3: Queue Management
"metrics", "CSAT", "NPS", "performance"?
WORKFLOW 4: Service Metrics
"escalate", "transfer", "assign"?
WORKFLOW 5: Routing & Escalation
Unclear?
Ask: "Would you like me to handle a conversation, check customer health, or review the queue?"
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.
016-7 calls
Handle Conversation
Full triage → understand → resolve → respond loop
023 calls
Churn Prevention
Risk assessment with actionable retention signals
032-3 calls
Queue Management
Queue health with agent capacity and SLA risks
042 calls
Service Metrics
CSAT, NPS, FCR, response time dashboard
052-3 calls
Routing & Escalation
Intelligent assignment with context handoff
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-customer-service retains responsibility for authentication, validation, and the connected system.
list_conversations
get_conversation
start_conversation
reply_conversation
add_internal_note
get_customer_profile
get_customer_health
get_interaction_history
assess_churn_risk
search_knowledge_base
suggest_response
get_canned_responses
resolve_conversation
assign_agent
escalate
get_queue_status
get_satisfaction_scores
get_service_metrics
list_agents
merge_conversations
Working rules
What the agent should do.
- Follow the decision guide, use the declared tool boundary, and verify the result before responding.
Operating boundaries
What the agent should avoid.
- Review the complete SKILL.md before enabling this skill for production work.
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-customer-service, and confirm the declared tools are available before asking the agent to use the workflow.
Install the skill
# Claude Code
git clone https://github.com/zavora-ai/skill-customer-service-operations.git \
~/.skills/skills/customer-service-operations
# ADK-Rust
cp -r customer-service-operations /path/to/project/.skills/skills/ADK-Rust loading shape
let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("customer-service-operations").await?;
let agent = LlmAgentBuilder::new("agent")
.instruction(skill.instructions())
.tools(skill.allowed_tools(toolset)?)
.build()?;The repository's compatibility statement: Requires mcp-customer-service server connected. Optional: mcp-crm for customer context, mcp-email for outbound, mcp-slack for escalation alerts.
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.
Overview ↗README.mdSkill instructions ↗SKILL.mdCross Mcp Workflows ↗references/cross-mcp-workflows.mdExamples ↗references/examples.mdTool Sequences ↗references/tool-sequences.mdChurn Score ↗scripts/churn_score.pyQueue Status Report ↗assets/queue-status-report.mdService Metrics Report ↗assets/service-metrics-report.md
Keep exploring
More in business operations.
Agriculture ManagementFarm operations for AI agents — field management, crop planning, weather intelligence, satellite monitoring (NDVI), commodity markets, IoT sensors, yield estimation, and pest/disease detection.34 allowed toolsBanking OperationsReal-time banking intelligence for AI agents — account monitoring, transaction analysis, anomaly detection, and payment initiation across Plaid (US/EU), Mono (Africa), and Open Banking (UK/EU).15 allowed toolsCRM Customer ManagementEnterprise CRM workflow orchestration for AI agents — customer 360 lookups, deal pipeline management, activity logging, and multi-MCP onboarding across Salesforce, HubSpot, Zoho CRM, and Pipedrive.27 allowed tools
Source record
Repository metadata for this skill entry.
- License
- Apache-2.0
- Allowed tools
- 20
- References
- 3
- Revision
- 60b8c7804fe3
- Updated
- May 31, 2026