newsletter-forge
Skill0 starsChanged 4 months agoMITView on GitHub
Draft an email newsletter issue built around one idea with a strong open and a single call to action. Use whenever the user asks to write a newsletter, an email issue, "this week's edition", a broadcast to subscribers, or wants to turn notes/links into a sendable email. Trigger even when they only give a rough topic or a pile of links to shape into an issue.
In this repository8 other files it gives its agents.
- commit-craftSkill
- inbox-triageSkill
- incident-postmortemSkill
- landing-copySkill
- meeting-to-actionsSkill
- pr-review-guardianSkill
- social-repurposeSkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 45
Write to one person, not "everyone".
≈ “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.
Files
Newsletter Forge
A newsletter earns the next open by being worth this one. Structure each issue around a single idea, open with a reason to keep reading, and ask for exactly one action. Sprawl kills open rates.
Issue architecture
- Subject line — curiosity or value, ≤50 chars, no clickbait you can't cash. Give 3 options.
- Preview text — the ~90 chars after the subject in the inbox. Extend the subject, don't repeat it.
- Open — first 1-2 sentences carry the whole email. A specific hook: a story beat, a sharp claim, a question the reader also has. No "Hope you're doing well!".
- One big idea — the issue is about one thing. Develop it: setup → insight → why it matters to the reader.
- Scannable body — short paragraphs, subheads if long, bold sparingly for the one line that matters. Assume skimming.
- One CTA — a single action (reply, click, try, share). Multiple CTAs split attention and lower every click.
- Sign-off — human, brief, optionally a P.S. (the P.S. is the second-most-read line — use it for the CTA or a hook to next issue).
Output template
Subject options:
1. <...>
2. <...>
3. <...>
Preview text: <...>
---
<Open — the hook>
<Body — the one idea, developed, scannable>
**<CTA line>** → [link/action]
<Sign-off>
P.S. <optional — CTA reinforcement or teaser>Rules
- One idea per issue. If the user dumps five topics, pick the strongest and offer the rest as future issues — don't cram.
- Write to one person, not "everyone". "You" singular.
- The open must not be a warm-up; delete any first line that could be cut without loss.
- One CTA. If the user insists on two, make one clearly primary and one a low-key P.S.
- Match the sender's voice if samples are given; otherwise default to plain, warm, direct.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

