newsletter-growth
Skill0 starsChanged 4 months agoMITView on GitHub
Plan, audit, design, or improve newsletters for audience growth, engagement, retention, and monetization. Use when user asks to start or grow a newsletter, create a dashboard or metric digest, improve issue format, subject lines, calls to action, cadence, segmentation, referrals, reader feedback, distribution, or newsletter business model.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- clear-explanationSkill
- creative-writingSkill
- dataset-triageSkill
- excalidraw-system-sketchSkill
- figma-to-uiSkill
- frontend-designSkill
- mermaid-architecture-mapSkill
- no-ai-slopSkill
- outreach-emailSkill
- presentation-builderSkill
- resume-helperSkill
- skill-authoringSkill
- stanford-researchSkill
- technical-writingSkill
- verification-loopSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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
- Very specific: line 11
Use for recurring newsletters and owned email audiences.
- Distinctive: line 22
When user provides a preferred prior issue or reference issue, preserve its section order, density, CTA weight, and visual rhythm unless …
- Distinctive: line 37
If audience vague, infer one reader from existing channel or product.
- Distinctive: line 97
Test one variable at time.
- Distinctive: line 99
Use enough sends or audience volume for meaningful read.
- Distinctive: line 101
Stop tactic that raises metric while hurting trust or promise.
- Distinctive: line 109
No analytics: audit promise, format, consistency, and qualitative reader evidence.
- Distinctive: line 129
Use direct simple sentences.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Build repeatable newsletter system around one reader promise and measurable feedback.
Scope
Use for recurring newsletters and owned email audiences. Use no-ai-slop for AI-pattern detection or voice-preserving polish of existing issue copy. Use outreach-email for one-to-one prospect, colleague, or client messages. Do not promise growth, open, click, or revenue outcomes.
Inputs
- Reader, topic boundary, and newsletter goal.
- Existing issues, list size, acquisition sources, and cadence.
- Available analytics, segments, platform features, and production capacity.
- Business model, voice, constraints, and current offers.
User owns audience facts, analytics, and business constraints. Cite current source for benchmark claims. Treat platform metrics as diagnostic, not universal truth.
When user provides a preferred prior issue or reference issue, preserve its section order, density, CTA weight, and visual rhythm unless they explicitly ask to redesign it.
Workflow
Step 1: Pin Reader And Promise
Name:
- Reader: specific person, role, context, and media habit.
- Job: why reader opens instead of scrolling, searching, or reading another source.
- Promise: one-sentence outcome plus topic boundary.
- Exclusions: topics and offers newsletter will reject.
If audience vague, infer one reader from existing channel or product. State assumption.
Step 2: Pick One Lane
Choose primary format:
- Curated briefing for fast-moving topic.
- Expert essay for author-led trust.
- Framework digest for repeatable advice.
- Community signal for reader-generated insight.
- Product education for use cases and objections.
- Metric dashboard for recurring KPI, status, or briefing data.
Blend only when each lane owns distinct recurring section.
Step 3: Build Repeatable Issue
Every issue needs:
- Hook: reason to read now.
- Core value: curation, analysis, tutorial, or decision support.
- One reader action: reply, click, save, share, vote, or try.
- Close: next issue, reflection, or specific call to action.
Reject format requiring full reinvention each send.
Step 4: Design Dashboard Issues When Needed
For metric dashboard lane, load dashboard email reference. Build issue around:
- Header: newsletter name, date, one-line summary.
- Lead: most important takeaway and primary metric.
- Cards: related metrics grouped by reader decision.
- Exceptions: material changes, risks, or urgent callouts.
- One primary CTA: live dashboard or next action.
Dashboard means skimmable hierarchy, not bland styling. Preserve existing newsletter personality, including brand colors, emoji section cues, playful labels, and high-energy CTA treatment when the audience expects it. Use restrained styling only when the newsletter is operational, regulated, or executive-facing.
Dashboard must remain useful with images blocked and columns stacked. Do not turn every newsletter into dashboard.
Step 5: Set Sustainable Cadence
Match frequency to reader need and production capacity. Name owner, production steps, send window, and fallback issue format. Avoid cadence supported only during launch effort.
Step 6: Build Growth And Retention Loops
- Acquisition: existing channels, partnerships, search, referrals, events, or product.
- Activation: welcome sequence and first useful issue.
- Retention: consistent promise, recognizable format, reader feedback, and clear value.
- Referral: reason, mechanism, and reward aligned with audience trust.
- Segmentation: interest, source, behavior, customer stage, or paid/free status only when treatment differs.
Step 7: Measure And Test
Track only metrics tied to decision: delivery, opens where reliable, clicks, replies, unsubscribes, referrals, conversion, and paid retention when relevant.
- Test one variable at time.
- Define expected decision before test.
- Use enough sends or audience volume for meaningful read.
- Combine quantitative signal with replies, polls, and interviews.
- Stop tactic that raises metric while hurting trust or promise.
Step 8: Monetize After Product Fit
Choose model matching reader intent: sponsorship, paid subscription, product/service, or transparent affiliate offer. Define value, placement, frequency, and conflict rules. Delay monetization when promise, cadence, or reader value remains unstable.
Fallbacks
- No analytics: audit promise, format, consistency, and qualitative reader evidence.
- Small list: use replies/interviews before A/B tests.
- Low production capacity: reduce cadence or use lighter recurring format.
- Mixed audience: choose primary reader or create explicit segments.
- Limited email editor: use single-column text-first dashboard and link to live dashboard.
Verify
- Reader and promise specific.
- Format repeatable.
- Dashboard hierarchy works with images off and on mobile when used.
- Cadence resourced.
- One primary action per issue.
- Growth loop names channel and mechanism.
- Metrics map to decisions.
- Monetization fits trust and reader intent.
- Benchmarks sourced or omitted.
Writing
Use direct simple sentences. Skip rhetorical flourishes. Avoid X-not-Y contrasts, self-answering rhetorical questions, em dashes, alliterative three-part phrases, vague inspirational pivots, unsourced claims, and unverified quotes.
Output
Return promise, reader, lane, issue format, cadence, first five issue ideas, subject/CTA patterns, growth loop, measurement plan, and monetization path when relevant. For dashboard lane, include hierarchy, card plan, mobile stack, image fallbacks, and client-test plan. State assumptions and missing data.
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
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.

