agentleFS
adityareddy-devadityareddy-dev/deskstudio/skills/email-campaign/SKILL.md

email-campaign

Skill43 starsChanged 23 days agoMITView on GitHub

A sequence of emails that share one template and one voice: the plan, the timing, every subject line, every message with its text part. Use for onboarding, a launch series, a nurture or a re-engagement run.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Run an email sequence as the Design Manager.

    line 7
  2. Very specific:

    Run: Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above.

    line 35

“Common” is measured: kept by at least 6 in 10 of the 7 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

Run an email sequence as the Design Manager.

Deliverable and standard. A sequence plan to standards/copy.md and each email to ${CLAUDE_PLUGIN_ROOT}/skills/desk/standards/email.md, all built on one template picked once, so the series reads as one sender.

Desks.

DeskAgentTierDoes
Growth/Analytics Specialistdesk:growth-analytics-specialistseniorthe sequence logic: how many, when, what each one is for, what to measure
Email Copywriterdesk:email-copywriterbuildersubjects, preheaders, bodies, CTAs, text parts for every email
Copy Editordesk:copy-editorseniorone voice across the run, the banned list
Compliance Designerdesk:compliance-designerseniorfooter, consent and the legal line, once for the series
Email Designerdesk:email-designerbuilderthree template roughs at the senior model, then every email
Art Directordesk:art-directordirectorthe pick of the template, notes on the set
Creative Directordesk:creative-directordirectorsign-off on the template and the set sheet

Inputs. Text (the goal, the audience, the product), a file to draw from (onboarding docs, a feature list), a URL, screenshots to feature.

Proof sizes. email-600, light and dark, per email.

Output under .desk/out/<id>/:

  • sequence.md: a table of number, day, purpose, subject, preheader, CTA, what it measures.
  • NN-<slug>.html and NN-<slug>.txt per email, numbered in send order.
  • subjects.md: three subject options per email with counts, the chosen one marked.
  • set.html: every email at thumbnail size on one sheet, in order.
  • renders/ per email, light and dark.

Run. Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above. Command name for state and events: email-campaign. Changes to the loop for this command:

  • Scope is full. The sequence plan comes first and sets the count (default 5) and days (default 0, 2, 5, 9, 14). Copy for every email follows through the Copy Editor before any build.
  • Roughs are three templates shown on email one. The pick is of the template. Every email is then built in it, up to four in parallel, each polished until proof passes light and dark.
  • Sign-off is on set.html plus email one and the last one in full. Template notes apply to every email in one polish round.

The ask: $ARGUMENTS

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.