"notify", "alert", "send push"?
send_notification / send_from_template
← Skill registry
Communication & knowledgePublic skills
Notification Delivery
Multi-channel notifications for AI agents — push, SMS, email, in-app with templates, scheduling, preference respect, and delivery tracking via mcp-notifications.
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.
Deliver notifications via push, SMS, email, in-app, and webhooks — manage templates, schedule delivery, track status, and respect user preferences. Use when sending notifications, managing templates, checking delivery status, scheduling alerts, or configuring preferences.
Architecture
How Notification Delivery 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
Notification Delivery 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-notifications
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.
"broadcast", "announce to all"?
broadcast (requires approval for large audiences)
"schedule", "send later"?
schedule_notification
"status", "delivered?"?
get_status / get_delivery_stats
"template", "create template"?
list_templates / create_template
"preferences", "opt out"?
get_preferences / update_preferences
"retry", "resend"?
retry_notification
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.
012 calls
Send (preference-aware)
Check prefs → deliver via best channel
022 calls
Broadcast
Template → multiple recipients
031 calls
Schedule
Future delivery
041 calls
Track
Delivery confirmation
Tool boundary
The skill may use 13 documented tools.
This allowlist is declared by the skill. It keeps the agent focused on the actions needed for this job while mcp-notifications retains responsibility for authentication, validation, and the connected system.
send_notification
send_from_template
broadcast
schedule_notification
list_notifications
get_status
retry_notification
list_templates
get_template
create_template
get_preferences
update_preferences
get_delivery_stats
Working rules
What the agent should do.
- Check user preferences before sending (respect opt-outs)
- Rate limit — don't send more than 3 notifications/hour to same user
- Use templates for consistency
- Include unsubscribe mechanism on marketing notifications
Operating boundaries
What the agent should avoid.
- Don't bypass opt-outs
- Don't use "critical" priority for non-critical content
- Don't broadcast without explicit approval
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-notifications, 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-notification-delivery.git \
~/.skills/skills/notification-deliveryADK-Rust loading shape
let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("notification-delivery").await?;
let agent = LlmAgentBuilder::new("agent")
.instruction(skill.instructions())
.tools(skill.allowed_tools(toolset)?)
.build()?;The repository's compatibility statement: Requires mcp-notifications server connected.
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
- 13
- References
- 3
- Revision
- 34030eeb7b0a
- Updated
- May 31, 2026