agentleFS
brennantimbrennantim/claude-skills/send-email/SKILL.md

send-email

Skill0 starsChanged 9 months agoMITView on GitHub

Send email via AgentMail API. Use when the user asks to send, compose, draft, email, or message someone. Supports plain text, HTML bodies, CC/BCC recipients, and file attachments.

  • Reads credentials
  • Installs packages

28 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use aeon-update, auto-workflow and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • aaronjmarsSkill

    aeon-update

    Pull framework updates from the upstream Aeon repo into this instance - 3-way merges canon's new commits into a PR, never clobbering operator config.

    Also in 4 projects that use this

  • aaronjmarsSkill

    auto-workflow

    Two-mode aeon.yml workflow builder - analyze inspects URLs and emits a tiered, signal-verified skill-enablement plan plus an aeon.yml diff; enable flips slugs to enabled:true and opens a PR.

    Also in 4 projects that use this

  • +10 more from aaronjmars

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 23 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the user asks you to send an email:

    line 48
  2. Distinctive:

    Extract the subject: If not explicitly stated, compose a concise subject from the message context.

    line 52
  3. Distinctive:

    Compose the body: Use the user's words as the starting point.

    line 54
  4. Very specific:

    Use --html only if the user explicitly asks for HTML formatting, or the content genuinely requires it (tables, styled layouts, rich …

    line 57
  5. Distinctive:

    Default to plain text. Most emails should be plain text.

    line 58
  6. Distinctive:

    Look for "CC", "copy", "also send to", "loop in" to detect CC recipients.

    line 61
  7. Distinctive:

    Look for "BCC", "blind copy" to detect BCC recipients.

    line 62
  8. Very specific:

    If the user mentions "attach", "include the file", "send the PDF", or references a specific file path, use --attach with the absolute path …

    line 65

“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “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 Email with AgentMail

Send emails by running the bundled Python script. The script uses only Python stdlib (no pip install needed). It requires the AGENTMAIL_API_KEY environment variable.

Usage

python3 ~/.claude/skills/send-email/scripts/send_email.py "TO" "SUBJECT" "BODY" [OPTIONS]

Options

FlagDescriptionDefault
--cc EMAILCC recipient (repeatable)None
--bcc EMAILBCC recipient (repeatable)None
--reply-to EMAILReply-to addressNone
--htmlTreat body as HTMLOff (plain text)
--attach PATHAttach file (repeatable, max 10 MB each)None
--inbox-id IDUse a specific inboxAuto-discovers first inbox

Examples

Basic email:

python3 ~/.claude/skills/send-email/scripts/send_email.py "alice@example.com" "Quick update" "The deploy went through. All good."

With CC and attachment:

python3 ~/.claude/skills/send-email/scripts/send_email.py "bob@example.com" "Monthly report" "Report attached." --cc manager@example.com --attach report.pdf

HTML email:

python3 ~/.claude/skills/send-email/scripts/send_email.py "team@example.com" "Release notes" "<h2>v2.1</h2><ul><li>New dashboard</li><li>Bug fixes</li></ul>" --html

Interpreting user requests

When the user asks you to send an email:

  1. Extract the recipient from their request. If they say a name without an email address, ask for the address.
  2. Extract the subject. If not explicitly stated, compose a concise subject from the message context.
  3. Compose the body. Use the user's words as the starting point. Write in a natural, professional tone unless they specify otherwise. Keep it plain text by default.
  4. Detect HTML vs plain text:
    • Use --html only if the user explicitly asks for HTML formatting, or the content genuinely requires it (tables, styled layouts, rich formatting).
    • Default to plain text. Most emails should be plain text.
  5. Handle CC/BCC:
    • Look for "CC", "copy", "also send to", "loop in" to detect CC recipients.
    • Look for "BCC", "blind copy" to detect BCC recipients.
  6. Handle attachments:
    • If the user mentions "attach", "include the file", "send the PDF", or references a specific file path, use --attach with the absolute path to the file.
  7. Run the script and report whether the email was sent. Include the recipient and subject in your confirmation.
  8. If the script fails, read the error output and explain the issue clearly. Common fixes:
    • Missing API key: tell them to set AGENTMAIL_API_KEY
    • Rate limit: free tier allows 100 emails/day
    • Bad address: check the recipient email format

Environment setup

The script loads AGENTMAIL_API_KEY from the project .env file (or ~/.env as fallback). If not found in any .env or the environment, the script exits with setup instructions.

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.