Confirm successful installation by checking the skill directory location:
.cursor/skills/send-email
Restart Cursor to activate send-email. Access via /send-email in your agent's command palette.
โ
Security Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
If the user does NOT specify a sender email in their initial request, AUTOMATICALLY use [email protected] as the default sender. DO NOT ask the user which email to send from.
Only ask the user for a different sender email if they explicitly mention wanting to use their own email address.
When using the default [email protected], proceed directly to Step 2 and ask for the 126 email authorization code.
Step 2: Identify Email Provider and Collect Credentials
Based on the sender's email address domain, identify the email provider and request the appropriate credentials.
Email Provider Detection
@gmail.com, @googlemail.com โ Gmail
@outlook.com, @hotmail.com, @live.com, @office365.com โ Outlook/Office 365
@qq.com, @vip.qq.com โ QQ Mail
@163.com, @126.com โ NetEase Mail
@aliyun.com, @aliyun-inc.com โ Aliyun Mail
@sendgrid.net, @*.sendgrid.net โ SendGrid
@*.mailgun.org โ Mailgun
Other domains โ Custom SMTP (ask for server, port, username, password)
Custom SMTP (Other domains)
Ask the user to provide:
SMTP Server Address
SMTP Port
Username
Password
Step 3: Auto-detect and Handle Markdown Content
The script automatically detects if the email content is in Markdown format by looking for common patterns:
Headers (#, ##, ###)
Bold/italic text (**bold**, *italic*)
Lists (- item or 1. item)
Code blocks (```)
Links ([text](url))
If Markdown is detected, the content is automatically converted to beautifully styled HTML with:
Professional typography and spacing
Color-coded headers
Styled tables and code blocks
Responsive design for email clients
You don't need to manually specify --content-type html for Markdown content - it's handled automatically!
Step 4: Collect Optional Information (if needed)
--from-name: Display name for sender (e.g., "John Doe")
--content-type html: For HTML formatted emails (defaults to plain text, but auto-converts Markdown)
--attach: File path(s) to attach (can specify multiple)
--template: Use template file instead of content
--template-vars: JSON string of template variables
Step 5: Confirm and Send
Before sending, confirm with the user:
Ready to send:
From: [Sender Email]
To: [Recipient Email]
Subject: [Subject]
Content Type: [Plain/HTML]
Attachments: [List of attachments or None]
Proceed to send? (y/n)
If confirmed, execute the send_email.py script with all collected parameters.
โบClaude Desktop or compatible AI client with skill support
โบClear understanding of task or problem to solve
โบWillingness to iterate and refine outputs
Time Estimate
15-45 minutes depending on use case complexity
Steps
1Install skill using provided installation command
2Test with simple use case relevant to your work
3Evaluate output quality and relevance
4Iterate on prompts to improve results
5Integrate into regular workflow if valuable
Common Pitfalls
โ Expecting perfect results without iteration
โ Not providing enough context in prompts
โ Using skill for tasks outside its intended scope
โ Accepting outputs without review and validation
Best Practices
โ Do
+Start with clear, specific prompts
+Provide relevant context and constraints
+Review and refine all outputs before using
+Iterate to improve output quality
+Document successful prompt patterns
โ Don't
โDon't use without understanding skill limitations
โDon't skip validation of outputs
โDon't share sensitive information in prompts
โDon't expect skill to replace human judgment
๐ก Pro Tips
โ Be specific about desired format and style
โ Ask for multiple options to choose from
โ Request explanations to understand reasoning
โ Combine AI efficiency with human expertise
When to Use This
โ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
โ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
Learning Path
1Familiarize yourself with skill capabilities and limitations
2Start with low-risk, non-critical tasks
3Progress to more complex and valuable use cases
4Build expertise through regular use and experimentation
