agentleFS
SkillMedevSkillMedev/lifecycle-marketing/skills/email-newsletter-pro/SKILL.md

email-newsletter-pro

Skill0 starsChanged 41 days agoMITView on GitHub

Write recurring email newsletters - subject lines that earn the open, preview text that extends them, a body structure readers finish, and cadence rules that keep the list healthy. Use when someone asks "write my newsletter", "give me subject line options", "why is my open rate dropping", "should I send weekly or monthly", or "help me structure this issue". Do NOT use for automated onboarding or behavior-triggered sequences - use email-drip-builder instead. Do NOT use for inbox placement and spam-folder problems - use email-deliverability instead.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. SkillMedev/content-marketing-engine★ 1100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep the chosen structure consistent issue to issue - predictable structure builds the reading habit.

    line 32
  2. Distinctive:

    Write 5 subject candidates, pick 2, and A/B test them when the list exceeds ~2,000 subscribers (below that, a test rarely reaches …

    line 39
  3. Distinctive:

    Write like a person, not a brand announcement.

    line 55
  4. Distinctive:

    Do not write clickbait the body cannot pay off - it wins one open and loses the habit.

    line 98
  5. Distinctive:

    Do not repeat the subject in the preview text.

    line 99
  6. Distinctive:

    Do not stack multiple CTAs.

    line 100
  7. Distinctive:

    Do not chase list size while open rate sits under 30% - you are growing dead weight and hurting deliverability.

    line 101
  8. Distinctive:

    Do not build automated welcome/onboarding flows here - that is email-drip-builder territory.

    line 102
  9. Distinctive:

    Do not blame content for a delivery problem.

    line 103
  10. Distinctive:

    Before the issue ships, verify:

    line 107

≈ “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

Email Newsletter Pro

A newsletter competes with the whole inbox. The costly mistake is optimizing the body while the subject line loses the open, or winning opens with clickbait the body cannot pay off - both burn the asset that matters most: the reader's habit of opening. Earn the open, reward it, and protect the cadence that builds the habit.

This skill covers recurring broadcast issues sent to a list. Automated sequences triggered by signup or behavior belong to email-drip-builder; if mail is landing in spam, fix that first with email-deliverability.

Operating procedure

Step 1: Gather inputs

Collect before writing. Where the user does not know a number, use the default and label it a guess.

  1. Audience and what they signed up for (the promise made at capture).
  2. This issue's single core idea - one sentence. If they offer three, make them pick one; the others become future issues or secondary links.
  3. Format: single-essay, curated-links, or hybrid (default: hybrid - one short essay plus 3-5 links).
  4. Current metrics: open rate, click rate, unsubscribe rate per send, list size (defaults: unknown - flag as guesses).
  5. Cadence and the one action they want readers to take (reply, read, share, buy - pick one).

Step 2: Pick the structure

  • Single-essay: one idea developed in 300-800 words. Best when the author's thinking is the product. Highest reply rates.
  • Curated-links: 5-10 links, each with a 1-2 sentence take explaining why it matters. The commentary is the value; a bare link list is a chore, not a newsletter.
  • Hybrid: a 150-300 word lead essay plus 3-5 curated links. The safest default and easiest to sustain weekly.

Keep the chosen structure consistent issue to issue - predictable structure builds the reading habit.

Step 3: Write the subject line and preview text as a pair

  • Subject under 50 characters (mobile clients truncate around there). Specific beats clever.
  • The curiosity-vs-clarity tradeoff: curiosity ("The pricing mistake that cost us $40k") wins opens when the payoff inside is real; clarity ("3 pricing page teardowns") wins trust over time. Default to clarity with one concrete detail; spend curiosity only when the body fully pays it off.
  • Preview text (roughly 40-90 characters shown) extends the subject with new information - never repeat the subject, never let "View this email in your browser" leak in.
  • Write 5 subject candidates, pick 2, and A/B test them when the list exceeds ~2,000 subscribers (below that, a test rarely reaches significance in one send - just pick one and track over multiple issues).

Bad / good subject pairs:

  • Bad: "Newsletter #47" - Good: "The onboarding email 62% of users ignore"
  • Bad: "You won't BELIEVE this growth hack" - Good: "How a 2-line email lifted activation 18%"
  • Bad: "Our March update and other news" - Good: "One pricing change, +$9k MRR"
  • Bad: "Some thoughts on writing" - Good: "Delete your first paragraph (here's why)"

The pattern: the good version names a specific number, artifact, or tension and stays under 50 characters; the bad version is generic, hypey, or about the sender instead of the reader.

Step 4: Write the body

  • Open with the single most interesting thing - front-load value; no "hope you're doing well".
  • One core idea per issue. Supporting links are secondary.
  • Short paragraphs (1-3 sentences), clear subheads, scannable on a phone.
  • Write like a person, not a brand announcement. Cut anything that does not serve the reader's interest.

Step 5: Close with one action

One clear next step - reply, read, or share - never five competing CTAs. Prefer a reply prompt at least every few issues: replies train deliverability and build the relationship. Make replying easy ("hit reply and tell me X - I read every one").

Step 6: Check list health before and after send

  • Open rate: an engaged list runs roughly 35-45%. Below 30% sustained means the list has dead weight or the subject lines are failing - diagnose before growing the list.
  • Click rate: 2-4% of delivered is healthy for content newsletters.
  • Unsubscribe red line: above 0.5% of recipients in a single send signals a content/audience mismatch - stop and re-read what the list was promised at signup before sending again.
  • Sunset rule: after 90-180 days of no opens, move subscribers to a re-engagement attempt, then remove non-responders. A smaller engaged list out-earns a large dead one and protects sender reputation.
  • Cadence: weekly is the default habit-building rhythm; biweekly is acceptable; less than monthly and readers forget who you are and unsubscribe rates spike on each send. Never skip randomly - consistency is a feature.

Newsletter skeleton template

SUBJECT: [FILL: under 50 chars, one concrete detail]
PREVIEW: [FILL: extends the subject with new info, 40-90 chars]

[FILL: 1-2 sentence cold open - the single most interesting thing this issue]

--- THE MAIN IDEA ---
[FILL: 150-800 words depending on format. One idea. Short paragraphs.
Concrete example or number in the first third.]

--- WORTH YOUR TIME ---  (curated/hybrid formats only)
1. [FILL: link] - [FILL: 1-2 sentence take: why this matters to THIS reader]
2. [FILL: link] - [FILL: take]
3. [FILL: link] - [FILL: take]

--- ONE THING TO DO ---
[FILL: single CTA - reply prompt, one link, or one share ask]

[FILL: sign-off, human, 1 line]

Deliverable

Produce a send-ready issue containing: 2 subject line candidates with preview text pairs, the full body in the chosen structure, a single CTA, plus a one-line cadence/list-health note flagging any metric outside the thresholds above.

Do NOT

  • Do not write clickbait the body cannot pay off - it wins one open and loses the habit.
  • Do not repeat the subject in the preview text; that wastes the second-most-valuable pixels in the inbox.
  • Do not stack multiple CTAs; each added ask cuts response to all of them.
  • Do not chase list size while open rate sits under 30% - you are growing dead weight and hurting deliverability.
  • Do not build automated welcome/onboarding flows here - that is email-drip-builder territory.
  • Do not blame content for a delivery problem; if opens crater suddenly across the board, check spam placement via email-deliverability first.

Quality bar

Before the issue ships, verify:

  • Subject is under 50 characters, contains one concrete specific, and the body pays it off.
  • Preview text adds new information beyond the subject.
  • Exactly one core idea and exactly one CTA.
  • The most interesting thing appears in the first two lines, readable on a phone screen.
  • Unsubscribe rate on the last send was under 0.5%; if not, the issue addresses the mismatch rather than repeating it.
  • The issue matches the established structure and cadence; deviations are deliberate, not accidental.

For turning newsletter essays into social posts, route to content-repurposing.

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.