newsletter
Skill1 starsChanged 2 months agoMITView on GitHub
Full-stack newsletter system. Generates branded HTML newsletters (reusing digest CSS components), sends via the connected-workspace MCP (Gmail), deploys to example.com/newsletters/ via FTP, and tracks opens/clicks via a PHP pixel. Subscriber engagement is stored in SQLite to power a funnel pipeline.
- Reads credentials
23 other projects use a version of this.
Adopted by
Most recently taken up by
- oivanfelipe/claude-skillstheir own version, first seen Nov 8, 2026
- nisarth/claude-skills-storetheir own version, first seen Nov 8, 2026
- Insightful-Pipe/email-marketing-skillstheir own version, first seen Nov 8, 2026
- MoizIbnYousaf/marketing-clitheir own version, first seen Nov 1, 2026
- Anglesite/anglesite-skillstheir own version, first seen Oct 27, 2026
- guiloureiromkt/ultra-skillstheir own version, first seen Oct 21, 2026
Used with
Projects with it also use lead-magnet, brand-voice and 4 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
robertbstillwellSkilllead-magnet
Create lead magnets and gated content to capture email subscribers and leads. Use when asked to design checklists, templates, calculators, mini-courses, whitepapers, or other downloadable content offers. Trigger phrases: "lead magnet", "gated content", "email capture", "content offer", "free download", "checklist", "template", "whitepaper", "swipe file", "content upgrade", "opt-in offer".
Also in 4 projects that use this
Dokkabei97Skillbrand-voice
Defines and enforces brand voice guidelines for startups. Creates tone, style, messaging frameworks and provides consistency checks across all content. Ensures every piece of communication sounds like it comes from the same brand.
Also in 4 projects that use this
silvainfmSkillreferral-program
When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' or 'partner program.' This skill covers program design, incentive structure, and growth optimization.
Also in 3 projects that use this
silvainfmSkilllaunch-strategy
When the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature release,' 'announcement,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' or 'product update.' This skill covers phased launches, channel strategy, and ongoing launch momentum.
Also in 3 projects that use this
indranilbanerjeeSkillkeyword-research
Research keywords via the connected data source: intent, gaps. Grouping → keyword-cluster. \"what keywords should we target\"
Also in 3 projects that use this
- +1 more from silvainfm
Other versions23 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 23
- masamasa59/ai-agent-papers★ 1.7ksame name
- OpenClaudia/openclaudia-skills★ 731same name
- getnao/sylph★ 195same name
- AlemTuzlak/skills★ 45same name
- MoizIbnYousaf/marketing-cli★ 33same name
- sanky369/vibe-building-skills★ 30same name
- coopersimson96/ai-content-system★ 17same name
- Anglesite/anglesite-skills★ 15same name
- jsath/claude-skills★ 14same name
- calven-ai/marketing-as-code★ 10same name
13 more not listed
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 repository10 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- ai-digestSkill
- daily-digestSkill
- humanizeSkill
- linkedinSkill
- meSkill
- pixelSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 1 is distinctive, and 7 are very specific to this project.
0
Common
Most of the 22 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
Create this checklist first.
- Very specific: line 43
Load your profile & memory: Read config.profile (name, role, voice, brand, content pillars), the voice samples in content.md when tone …
- Distinctive: line 44
Ask if anything is missing: If a required input is unknown, stop and ask a specific question.
- Very specific: line 46
Validate, output & record: Check the result against this skill's rules, return it, then append any new durable fact to memory.md and any …
- Very specific: line 51
Run scripts/db.py --stats and display:
- Very specific: line 64
Read config.digest.sources for source URLs
- Very specific: line 66
Read config.profile for author voice and brand
- Very specific: line 67
Read config.newsletter.settings for title, CTA, sections
“Common” is measured: kept by at least 6 in 10 of the 22 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.
Files
Newsletter Skill — /newsletter
Role
You are the user's newsletter producer. You generate branded HTML newsletters, deploy them, and track engagement.
Context to load
Load and honor these before acting:
config.profile— identity, role, voice, brand, content pillars (personalize everything)content.md— voice samples and prompt guidance (when tone matters)memory.md/notes.md— learned preferences and open follow-upsconfig.newsletter.settingsandconfig.newsletter.subscribers
Workflow
Step 0: TodoWrite Checklist
Create this checklist first; mark one task in_progress, finish it, then move to the next.
TodoWrite([
{ content: "Gather inputs; load config.profile, content.md, memory.md & notes.md", status: "in_progress" },
{ content: "Ask for any missing inputs — never assume or hallucinate", status: "pending" },
{ content: "Generate, deploy, or report on the newsletter as requested", status: "pending" },
{ content: "Validate output; record new facts to memory.md / follow-ups to notes.md", status: "pending" }
])Steps
- Gather inputs. Parse the request /
$ARGUMENTSand list what this skill needs. - Load your profile & memory. Read
config.profile(name, role, voice, brand, content pillars), the voice samples incontent.mdwhen tone matters, and the sharedmemory.md/notes.mdfor learned preferences and open follow-ups. - Ask if anything is missing. If a required input is unknown, stop and ask a specific question. Never assume, guess, or invent facts, numbers, names, or sources.
- Do the work following the sections below.
- Validate, output & record. Check the result against this skill's rules, return it, then append any new durable fact to
memory.mdand any follow-up tonotes.mdviapython .agents/scripts/memory.py.
Commands
/newsletter — Dashboard
Run scripts/db.py --stats and display:
- Total subscribers (active / churned)
- Newsletters sent (last 5)
- Pipeline summary: count per funnel stage
- Last newsletter date and open rate
/newsletter create [date] — Generate newsletter HTML
Date format: YYYY-MM-DD (defaults to today). Slug = {date}.
Content generation process:
- Read
config.digest.sourcesfor source URLs - Research the latest AI news using WebSearch for each section (same as digest)
- Read
config.profilefor author voice and brand - Read
config.newsletter.settingsfor title, CTA, sections - Build the newsletter HTML using the newsletter template (see HTML Design below)
- Write to
output/newsletter/newsletter-{slug}.html - Register in SQLite via
scripts/db.py --register --slug {slug} --subject "{subject}" --date {date} - Report: file path, web URL (before deploy), item count per section
Sections to include (same content categories as digest):
- Top Stories (3–5 items): breaking_news + models_apis
- Research Highlights (2–3 items): research_papers
- Tools & Repos (4–6 items): github_repos + products_tools
- Agents & Automation (2–4 items): agents_automation
- Industry Pulse (2–3 items): industry_analysis
- Worth Reading (3–5 links): tutorials_learning + linkedin_insights
/newsletter preview [date] — Open in browser
Run: python -m http.server 8899 --directory output/newsletter/
Then print: http://localhost:8899/newsletter-{slug}.html
/newsletter send [date] [--dry-run] — Send via the Gmail MCP tool
Sending uses the connected-workspace MCP server (gmail_send_message), not a local script.
- List active subscribers:
python .agents/scripts/newsletter/db.py --list - For each subscriber, inject the per-recipient tracking pixel with
python .agents/scripts/newsletter/template.py inject --slug {date} --email-hash <hash> ... --dry-run: show the subject, preview, and full recipient list — do NOT send.- Without
--dry-run: call the MCPgmail_send_messagetool once per recipient, then log each send to SQLite viadb.py. Confirm before sending to a real list.
/newsletter deploy [date] — Upload to FTP
Run scripts/ftp_deploy.py --slug {date}
- Uploads
newsletter-{slug}.htmlto FTPpublic_html/newsletters/ - Uploads
scripts/tracker.phpastrack.php(only if not already on server) - Prints web URL:
https://example.com/newsletters/newsletter-{slug}.html - Updates
ftp_urlin SQLite
/newsletter subscribers [subcommand] — Manage list
list→ runscripts/db.py --subscribers(table: email, name, stage, opens, last seen)add [email] [name]→ runscripts/db.py --add-subscriber --email X --name Yremove [email]→ runscripts/db.py --remove-subscriber --email Ximport→ re-import fromconfig.newsletter.subscribersinto SQLiteexport→ export SQLite subscribers back toconfig.newsletter.subscribers
/newsletter pipeline — Funnel view
Run scripts/db.py --pipeline and display:
Funnel Stage Count Avg Opens Last Activity
────────────────────────────────────────────────
cold 12 0.0 2026-02-20
warm 8 1.5 2026-02-27
hot 4 4.2 2026-02-26
engaged 3 8.1 2026-02-27
converted 1 12.0 2026-02-24
churned 2 — 2026-02-15/newsletter setup — Configuration guide
Sending is handled by the connected-workspace MCP server (Gmail OAuth lives there, not in
this repo). For deploy + tracking you only need FTP credentials in .env:
- Register the
connected-workspaceMCP server and authorize Google (forgmail_send_message). - FTP credentials — set
FTP_HOST,FTP_USER,FTP_PASSWORD,NEWSLETTER_BASE_URLin.env. python .agents/scripts/newsletter/ftp_deploy.py --slug {date} --check— verify FTP connection.
HTML Design
Reuse the exact design system from output/ai-digest/digest-2026-02-26.html:
Same CSS variables (:root), same components:
.header— gradient hero block with title, date range, author.editor-note— left-bordered intro block.section+.section-header+.section-dot— section containers.card+.card-title+.card-body+.card-why+.card-meta— content cards.badge+.source-link— item metadata.footer— author attribution- Light/dark mode via
@media (prefers-color-scheme: light)
Newsletter-specific additions:
- Photo signature: Author photo in footer (
photos/author.png) - CTA block: Prominent "Subscribe on LinkedIn" button from
settings.json - Web archive link: "Read in browser: {ftp_url}" banner at top of email
- Unsubscribe: Footer link
mailto:{reply_to}?subject={unsubscribe_subject} - Tracking pixel: 1×1 GIF at end of body (injected per-subscriber at send time)
Output
- Web HTML:
output/newsletter/newsletter-{slug}.html - Sent log:
output/newsletter/newsletter.db(events table) - FTP URL:
https://example.com/newsletters/newsletter-{slug}.html
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.

