substack-notes

---
name: substack-notes
description: |
  Write Substack Notes that work as genuine fragments with an actual idea inside them, not
  miniaturized newsletters. Use for Substack Notes and similar short posts. Enforces the EW
  anti-AI rules and the writer's voice profile.
license: MIT
metadata:
  version: "0.3.0"
---

# EW Skill — Substack Notes

**Dependency chain. Read these in order before writing anything:**

1. `core/runtime-contract.md` (short operating contract; does not replace the full rules)
2. `core/obsidian-workspace.md` (resolve storage and persistence rules)
3. `core/anti-ai-rules.md` (full standard)
4. `core/ai_slop_commandments.md` (mechanism reference and diagnostic checklist)
5. `core/voice-profile.md` (voice resolver; require the resolved profile's `Completed:` field to be exactly `Yes`, otherwise stop and run onboarding)
6. Any `.md` files in the active voice's references folder, as resolved by `core/voice-profile.md`

This chain applies on direct invocation (`/ew:substack-notes`) exactly as it does on dispatch through `/ew`. Direct invocation skips routing, not constraints.

---

## WHAT THIS SKILL IS FOR

Substack Notes is a discovery layer, not a second newsletter. It lives between X and a full post — longer than a tweet, shorter than an issue, more conversational than either.

Notes that work are fragments with actual ideas inside them. A thought that didn't make it into the newsletter but is too good to waste. A reaction to something you read. A question you're genuinely sitting with. An observation from the week that deserves to exist independently.

Notes that don't work are newsletters cut into smaller pieces, or promotional announcements dressed as thoughts.

---

## THE DISTINCTION FROM FULL POSTS

A Note is not a miniaturized newsletter issue. The registers are different.

**A newsletter issue:** formal argument, built out, earned over the full length, structured for sustained attention.

**A Note:** fragment, opinion, question, or observation — valuable precisely because it's incomplete enough to invite a response. The incompleteness is not a failure; it's the feature.

Think of Notes as the margin notes of your writing life. The thoughts you'd share with someone smart over coffee that don't need a 1,500-word essay to justify existing.

---

## WHAT NOTES ARE FOR

**Thinking out loud on something you haven't resolved yet.**
Not a conclusion — a genuine question you're working through. The reader should feel like they caught you mid-thought, not like they're reading a prepared statement.

**Link commentary with actual perspective.**
Not "Great piece by [Name]" — that's noise. "This essay by [Name] on [topic] is right about X but completely misses Y, which is the part that actually matters for [specific reason]." The link is the citation; your perspective is the Note.

**An observation that doesn't need development.**
Something you noticed that's complete in one or two paragraphs. Sharp, specific, standalone. If it needs more than 3 paragraphs to make sense, it's a newsletter issue in disguise — let it grow into one.

**A question that invites actual conversation.**
Specific enough that readers have a concrete answer to give. "What do you think about AI?" is not a conversation-starter. "What's the one use of AI that's actually improved your writing process, not just your output?" is.

---

## FORMAT AND LENGTH

Notes live in a scrolling feed. They compete with everything. The rules:

**Open with the idea, not the context.**
❌ "I was reading something earlier this week that got me thinking about how we approach..."
✅ "The most-retweeted writing advice I've seen this year is also the most useless."

**Short paragraphs, real line breaks.**
Notes are read on mobile. White space is not a formatting choice — it's a readability requirement.

**Length:** Most Notes should land between 100–400 words. Shorter is better if the idea is complete. Longer is fine if each paragraph earns it. Never pad a Note to look substantive — it reads as insecurity.

**No bold-first bullets.** If you need bullets in a Note, collapse them into a sentence.

---

## THE DISCOVERY FUNCTION

Notes serve your newsletter's growth because they reach readers who haven't found your main publication yet. Every Note is a sample of your thinking. It should represent the quality of the newsletter, not the scraps left over from it.

**The best Notes create a natural pull toward the newsletter:**
Not by saying "subscribe to my newsletter" (which is a waste of a Note) — but by demonstrating a quality of thinking that makes the reader want more. The advertisement is the work itself.

**What to link, when:**
Link to a full issue when the Note expands on something the issue covers — not as self-promotion, as a genuine pointer to more depth. If the link feels forced, skip it. Notes stand alone.

---

## VOICE ON NOTES

Notes are where your voice can be most unguarded. Use that. The newsletters get polished; the Notes get to be immediate.

That said — unguarded doesn't mean unthought. The best Notes feel spontaneous but aren't careless. The thought behind them is real; the presentation is just relaxed.

The writers who build audiences on Notes are the ones who show up with genuine curiosity and a distinct perspective, consistently, over months. Not the ones who have the best individual Note.

---

## POST-GENERATION REVIEW

After producing any draft, stop. Re-read `core/anti-ai-rules.md` Sections 1–7 with the draft in front of you. Go line by line through the pre-publish checklist in Section 7. Fix every failure before presenting the output.

Notes are short — which means every word is load-bearing and AI patterns have nowhere to hide. The review pass is fast here. Do it.

## PRE-POST CHECKLIST

- [ ] Is this a genuine fragment of thought or a newsletter issue squeezed small?
- [ ] Does it open with the idea, not the context?
- [ ] Is it short enough — does every paragraph earn its place?
- [ ] If it links to something: is there an actual perspective, not just a pointer?
- [ ] Does it represent the quality of your newsletter, or the leftovers?
- [ ] Have you run the relevant items from Sections 1–7 of `core/anti-ai-rules.md`?
- [ ] No "subscribe to my newsletter" CTA dressed as a thought?