agentleFS
nitrosendnitrosend/claude/skills/send-transactional/SKILL.md

send-transactional

Skill3 starsChanged 7 months agoMITView on GitHub

Send transactional emails or SMS for app-triggered communications: receipts, password resets, OTPs, order confirmations, shipping notifications, system alerts. Single recipient, immediate delivery, no campaign or approval needed. Use when: "transactional email", "receipt email", "password reset email", "send notification email", "order confirmation", "OTP email", or "system email".

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create a template with nitro_manage_template via the composition contract (composition_mode: "intent" → fill the returned next_call → …

    line 38
  2. Very specific:

    Use the data field for personalization:

    line 48
  3. Very specific:

    Do not model transactional sends as MCP flows.

    line 67
  4. Very specific:

    Always offer to do a dry run first: nitro_send_message or POST /v1/my/messages with dry_run: true validates without sending.

    line 104
  5. Distinctive:

    Every live send must have a stable idempotency key.

    line 109
  6. Very specific:

    Before the first live email, inspect brand_subdomain in nitro_get_status.

    line 117

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Send Transactional

Help the user send or set up transactional emails/SMS — immediate, single-recipient messages triggered by application events.

Understand the Use Case

Common transactional email types:

  • Password reset: OTP or magic link
  • Order confirmation: Receipt with order details
  • Shipping notification: Tracking info
  • Welcome/verification: Account activation
  • System alert: Service status, security notice
  • Invoice/receipt: Payment confirmation

Design Approach

Quick Send (Plain Text)

For a one-off send from Claude over MCP, use nitro_send_message:

channel: "email"
to: "user@example.com"
subject: "Your order #1234 is confirmed"
body: "Thank you for your order..."

Branded Template

For on-brand transactional emails:

  1. Create a template with nitro_manage_template via the composition contract (composition_mode: "intent" → fill the returned next_call → persist with composition_mode: "draft"; see the compose-email skill)
  2. For a one-off MCP send, call nitro_send_message with template_id
  3. For application-triggered production sends, wire POST /v1/my/messages or ns.messages.send using template_id

Live sends require an idempotency_key — reuse the same stable key on retry to prevent duplicate delivery.

Merge Variables

Use the data field for personalization:

data: { order_id: "1234", customer: { name: "Alice" }, amount: "$49.99" }

Reference in templates/body as {{ data.order_id }}, {{ data.amount }}, or nested paths like {{ data.customer.name }}.

Key Differences from Marketing Email

MarketingTransactional
AudienceLists/segmentsSingle recipient
Requires subscriptionYesNo
CAN-SPAM footerRequiredSkipped
Unsubscribe linkRequiredNot needed
DeliveryCampaign workflowImmediate
TrackingOpens/clicks trackedOpens/clicks tracked (engagement tracking stays enabled)

Do not model transactional sends as MCP flows. Use nitro_send_message for one-off MCP sends, normal flow email steps for lifecycle automation, and API/SDK transactional sends for application events.

For Developers

Help developers integrate transactional emails into their apps:

API Integration

POST https://api.nitrosend.com/v1/my/messages
Authorization: Bearer nskey_live_...
Idempotency-Key: verification-user-123-attempt-1
Content-Type: application/json

{
  "channel": "email",
  "to": "user@example.com",
  "subject": "Your verification code",
  "body": "Your code is: 123456",
  "data": { "code": "123456" }
}

SDK Integration

import { Nitrosend } from '@nitrosend/sdk'
const ns = new Nitrosend('nskey_live_...')
await ns.messages.send({
  channel: 'email',
  to: 'user@example.com',
  subject: 'Your verification code',
  template_id: 42,
  data: { code: '123456' }
}, 'verification-user-123-attempt-1')

Dry Run

Always offer to do a dry run first: nitro_send_message or POST /v1/my/messages with dry_run: true validates without sending.

Idempotency

Every live send must have a stable idempotency key. Reuse it only for an exact retry of the same recipient and payload; use a new key for a different logical message. MCP uses idempotency_key, the REST API uses the Idempotency-Key header, and the Node SDK accepts the key as the second argument to messages.send.

Nitrosend Sender Readiness

Before the first live email, inspect brand_subdomain in nitro_get_status. If preparation is required, use nitro_manage_domains(operation: "prepare_brand_subdomain"), poll until it is ready, then select it explicitly. A first authenticated send may return sender_identity_provisioning; that response is retryable, but no message was stored or queued. Retry with the same idempotency key only after readiness and selection.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.