Newsletter digest

Skill markhamsquareventures/learn-ai-with-nick-plugins/learn-ai-with-nick/skills/newsletter-digest

Fetch newsletters from Gmail and compile a digest with themes, highlights, and action items. Use when asked to "digest newsletters", "check newsletters", "what landed in my inbox", or "newsletter summary".From its SKILL.md

Install

npx -y skills add markhamsquareventures/learn-ai-with-nick-plugins --skill newsletter-digest

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.3 KB, 453 tokens by cl100k_base, as published. Nobody here has run it

Newsletter Digest

You fetch recent newsletters from Gmail and output a structured digest. All output goes to the conversation — do not write any files.

STEP 1: Search Gmail for Newsletters

Use gmail_search_messages to find newsletters from the last 24 hours.
- Try this query first: category:promotions newer_than:1d
- Then also search: label:newsletters newer_than:1d (if the user has a newsletters label)
Deduplicate results by message ID.
If no messages are found, tell the user there are no new newsletters and stop.

STEP 2: Read Each Newsletter

For each message found, use gmail_read_message to get the full content.
Extract: sender name, subject line, and body text.
Skip messages that are clearly not newsletter content — receipts, password resets, order confirmations, marketing promos for a single product. You want editorial content: curated links, essays, roundups, industry news.
If a message is truncated or you need the full thread, use gmail_read_thread.

STEP 3: Compile the Digest

Analyze all newsletters and output the digest using this structure:

# Newsletter Digest — YYYY-MM-DD

## Top Themes
1. **Theme title** — 1-sentence explanation of why this matters
2. ...
(3-5 themes that appear across multiple newsletters)

## Newsletter Highlights

### [Newsletter Name] — [Subject Line]
- Key takeaway 1
- Key takeaway 2
- Key takeaway 3

### [Newsletter Name] — [Subject Line]
- ...

(repeat for each newsletter)

## Action Items
- [ ] Things worth doing based on what you read

## Links Worth Reading
- [Article title](URL) — why it's worth your time
- ...

Keep it concise. The goal is to save the user from reading 10+ newsletters — give them the signal, skip the noise.

STEP 4: Summary

End with a short summary: how many newsletters were processed and the single most interesting finding across all of them.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most marketing audience skills give in 453 tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

Apply Poppins font to headingsin 41 of 690, across 6 files
Apply Lora font to body textin 41 of 690, across 6 files
Use Arial fallback for headingsin 39 of 690, across 4 files
Use Georgia fallback for body textin 39 of 690, across 4 files
Maintain text hierarchy and formattingin 39 of 690, across 4 files
Use accent colors for non-text shapesin 38 of 690, across 3 files
Use RGB values for precise color matchingin 38 of 690, across 3 files
Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
Use active voice instead of passive voicein 26 of 690, across 10 files
Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

search Gmail for recent newsletters
deduplicate search results by message ID
read each newsletter's full content
skip non-editorial messages
identify three to five top themes
list three key takeaways per newsletter

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.