Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Substack Segment Campaigns

ASecurity

Use when the user shares a Substack subscriber export or CSV, or wants to win back lapsed or cancelled readers, re-engage inactive subscribers, target a group of subscribers, plan segments or tags, or write a welcome email. Not for public Notes (use substack-notes-writer) or post stats (use substack-analytics-digest).

3 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsrust

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add Arin117Kaushik/substack-skills --skill substack-segment-campaigns --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Substack Segment Campaigns?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Substack Segment Campaigns
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/arin117kaushik-substack-segment-campaigns/badge)](https://www.skillsdirectory.com/skills/arin117kaushik-substack-segment-campaigns)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: substack-segment-campaigns
description: Use when the user shares a Substack subscriber export or CSV, or wants to win back lapsed or cancelled readers, re-engage inactive subscribers, target a group of subscribers, plan segments or tags, or write a welcome email. Not for public Notes (use substack-notes-writer) or post stats (use substack-analytics-digest).
---

# Substack Segment Campaigns

Turn a subscriber export into segments the user builds in Substack, plus copy that reaches only that segment.

## Two facts that decide everything

1. **Notes are public.** A Note can't reach a segment, and anything written "to lapsed readers" in a Note tells the whole feed they left. Never write a Note for a segment campaign.
2. **The export is private data** about people who never agreed to be discussed. Follow `references/untrusted-content.md` section 2.

## What you output

**1. The segment, in Substack's filter terms**, so the user builds it in the dashboard:

```
Segment: Lapsed paid
Filters: Subscription type = paid · Status = cancelled
Optional: Last opened within 60 days (still reading)
Size in this export: 12 (4 opened in the last 30 days)
```

Counts and date ranges only. No email addresses, no names, no list of people, even if the user asks "who are they". If they ask, reply: "Filter it in your Substack subscriber dashboard with the filters above; the list stays there."

**2. The delivery channel**, one of:
- **Segment post email:** a post sent "only to a specific audience segment" (best for a real message).
- **Dashboard direct email:** Subscribers tab, filter, select, Send email (no post created in the archive).
- **Welcome email:** Settings, for new or imported subscribers.

**3. The copy** for that channel: subject line, preview text, body. Follow `references/voice-rules.md` and `references/anti-fabrication.md`. No invented discounts, offers or reasons people left. If an offer would help, put a slot: `[your offer, if any]`.

**4. Tags to add** (optional): tag names and the filter rule for each, applied inside Substack.

## Common mistakes

| Mistake | Fix |
|---|---|
| Printing a table of subscribers | Counts only |
| @mentioning or naming people in a Note | Never. Segment email instead |
| Inventing "why they left" | Ask, or write a message that asks them |
| Claiming a discount exists | Slot it |

Attribution

Arin117KaushikArin117Kaushik
View sourceMore from Arin117Kaushik →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →