agentleFS
MelvynxMelvynx/ai-maxxing-skills/skills/lumail/SKILL.md

lumail

Skill32 starsChanged 25 days agoMITView on GitHub

Manage Lumail email marketing from Claude with the Lumail CLI or MCP. Use for setup and login, sending domains and DNS, subscribers, tags, double opt-in, transactional emails (OTP codes), campaigns, workflows (automations), segments, API keys and analytics.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Add or update a subscriber with tags: MCP add_subscriber.

    line 18

≈ “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

Connect first:

npx lumail@latest setup --authenticate   # installs the Lumail MCP + skills for your agent, opens the browser to authorize
npx lumail@latest auth test              # checks the saved login, fails: run the setup-lumail skill

The "copy the prompt" button in the Lumail onboarding does the same. Once connected, prefer the Lumail MCP tools and fall back to the CLI (lumail --help, then lumail <resource> --help). Never invent flags. Pass --json when parsing, and never print API keys.

Where each job lives:

  • Count or find subscribers: MCP count_subscribers, get_subscriber; CLI lumail subscribers list, lumail subscribers get <email>.
  • Add or update a subscriber with tags: MCP add_subscriber; CLI lumail subscribers create --help.
  • Tags: MCP list_tags, get_or_create_tags; CLI lumail tags list, lumail tags create.
  • API key for an app (OTP emails, signups): lumail tokens --help. Create it yourself and store it only in the app env.
  • Transactional email (login code): MCP send_email; CLI lumail emails --help.
  • Sending domain and web domain: lumail domain --help, then add the DNS records it returns in Cloudflare yourself.
  • Anything else: lumail tools list, lumail tools get <tool>, lumail tools run <tool> --params '<json>'.

For signups from an app, upsert the person on signup or purchase with a tag per product (student, customer, <product-slug>), through one server helper so the API key never reaches the browser. Double opt-in is on by default and keeps a new subscriber "pending confirmation" until they click the email: keep it for cold forms, and create buyers and account signups as subscribed (skip double opt-in) so tag workflows fire right away.

Create campaigns and workflows as drafts; send, schedule or publish only when the user asks. Before writing a campaign body or a workflow graph, load the format guide with MCP get_skill and {"type":"campaign"} or {"type":"workflow"}. For a workflow, create it, read it back with get_workflow, then configure the full graph in one call (a trigger such as "tag added", then the email steps) with the exact updatedAt value. After any change, read back the saved object and render it to check content and links.

Reply in the user's language with what changed, a link, and anything left to do.

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.