Contains person name/email/phone?
WORKFLOW 1: Customer 360 Lookup
← Skill registry
Business operationsPublic skills
CRM Customer Management
Enterprise 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.
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 CRM workflows across Salesforce, HubSpot, Zoho, and Pipedrive — customer 360 lookups, deal pipeline management, activity logging, and customer onboarding. Use when looking up a customer, checking deal status, logging a call or meeting, reviewing pipeline health, onboarding a new customer, finding stalled…
Architecture
How CRM Customer Management 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
CRM Customer Management 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-crm
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.
Mentions "deal", "opportunity", "pipeline", "forecast"?
WORKFLOW 2: Deal Management
Mentions "call", "meeting", "email", "activity", "log"?
WORKFLOW 3: Activity Logging
Mentions "onboard", "new customer", "set up"?
WORKFLOW 4: Customer Onboarding
Mentions "pipeline", "review", "health", "stalled"?
WORKFLOW 5: Pipeline Review
Unclear?
Ask: "Would you like me to look up a customer, manage a deal, or review the pipeline?"
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.
015-6 calls
Customer 360 Lookup
Complete customer picture in one response
024-5 calls
Deal Management
Create, advance, or check deal status
033-4 calls
Activity Logging
Record interactions with proper context
048-9 calls
Customer Onboarding
Full setup with duplicate detection
053-4 calls
Pipeline Review
Health summary with at-risk deal alerts
Tool boundary
The skill may use 27 documented tools.
This allowlist is declared by the skill. It keeps the agent focused on the actions needed for this job while mcp-crm retains responsibility for authentication, validation, and the connected system.
search_contacts
get_contact
create_contact
update_contact
delete_contact
list_companies
get_company
create_company
update_company
search_companies
list_deals
get_deal
create_deal
update_deal
move_deal_stage
search_deals
delete_deal
list_activities
create_activity
update_activity
list_pipelines
get_pipeline_summary
list_notes
create_note
associate_contact_company
associate_deal_contact
list_deal_contacts
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-crm, and confirm the declared tools are available before asking the agent to use the workflow.
Install the skill
# Clone into your skills directory
git clone https://github.com/zavora-ai/skill-crm-customer-management.git \
~/.skills/skills/crm-customer-managementADK-Rust loading shape
let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("crm-customer-management").await?;
let agent = LlmAgentBuilder::new("agent")
.instruction(skill.instructions())
.tools(skill.allowed_tools(toolset)?)
.build()?;The repository's compatibility statement: Requires mcp-crm server connected. Optional: mcp-email, mcp-calendar, mcp-slack for multi-MCP workflows.
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.mdScore Pipeline ↗scripts/score_pipeline.pyValidate Contact ↗scripts/validate_contact.pyCustomer 360 Report ↗assets/customer-360-report.mdPipeline Review Report ↗assets/pipeline-review-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 toolsCustomer Service OperationsAI-powered customer service — KB-first resolution, churn prediction, intelligent routing, and satisfaction tracking. Triage → Understand → Resolve → Respond → Close.20 allowed tools
Source record
Repository metadata for this skill entry.
- License
- Apache-2.0
- Allowed tools
- 27
- References
- 3
- Revision
- 263d1147118a
- Updated
- May 31, 2026