agentleFS
bobmmaobobmmao/agent-workflow-skills/skills/growth/apple-mail-sales/SKILL.md

apple_mail_sales

Skill0 starsChanged 5 months agoMITView on GitHub

Read Apple Mail unread inbox messages, classify promo spam vs genuine business replies, forward substantive inquiries to operator.com, and mark obvious sales-promo spam as junk.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill only for Apple Mail workflows on macOS.

    line 6
  2. Distinctive:

    do not junk it automatically

    line 54
  3. Distinctive:

    prefer mark read and summarize

    line 55
  4. Very specific:

    When the user asks to process unread emails, prefer running ~/.openclaw/workspace-sales/bin/mail_triage_once directly.

    line 60

≈ “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

Use this skill only for Apple Mail workflows on macOS.

Helper commands:

  • ~/.openclaw/workspace-sales/bin/mail_permission_test
  • ~/.openclaw/workspace-sales/bin/mail_unread_list
  • ~/.openclaw/workspace-sales/bin/mail_read_message <message_id>
  • ~/.openclaw/workspace-sales/bin/mail_mark_read <message_id>
  • ~/.openclaw/workspace-sales/bin/mail_mark_junk <message_id>
  • ~/.openclaw/workspace-sales/bin/mail_send <recipient_name> <recipient_email> <subject_file> <body_file>
  • ~/.openclaw/workspace-sales/bin/mail_forward_summary <message_id> operator.com <summary_file>

Rules:

  • Forward genuine business inquiries and meaningful replies to operator.com
  • Mark obvious promotional spam as junk
  • Be conservative when uncertain

Forward if the email contains substantive business intent such as:

  • product inquiry
  • request for catalog
  • quotation or price request
  • MOQ question
  • OEM or ODM interest
  • customization request
  • sample request
  • shipping or payment discussion
  • distributor / wholesaler / retailer / importer / channel cooperation discussion
  • real follow-up to our previous outreach

A message is stronger if it includes real sender identity:

  • full name
  • company name
  • title
  • signature block
  • business context

Mark as junk if it mainly sells us services such as:

  • SEO
  • backlinks
  • traffic growth
  • guaranteed sales
  • guaranteed orders
  • guaranteed leads
  • PR distribution
  • ad services
  • lead generation services
  • promises of more customers or revenue in the next few weeks

If uncertain:

  • do not junk it automatically
  • prefer mark read and summarize

Single-command inbox triage:

  • ~/.openclaw/workspace-sales/bin/mail_triage_once

When the user asks to process unread emails, prefer running ~/.openclaw/workspace-sales/bin/mail_triage_once directly.

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.