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 Post Writer

ASecurity

Use when the user wants a Substack newsletter post or long-form issue drafted from an idea or outline, or an existing draft packaged for publishing with title, subtitle, SEO title and description, slug, tags, section, and paywall placement. Not for short Notes (use substack-notes-writer) or reviewing tone (use substack-humanizer).

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

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add Arin117Kaushik/substack-skills --skill substack-post-writer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Substack Post Writer?

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

Security grade badge for Substack Post Writer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/arin117kaushik-substack-post-writer/badge)](https://www.skillsdirectory.com/skills/arin117kaushik-substack-post-writer)

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

Download Zip
Files
SKILL.md
---
name: substack-post-writer
description: Use when the user wants a Substack newsletter post or long-form issue drafted from an idea or outline, or an existing draft packaged for publishing with title, subtitle, SEO title and description, slug, tags, section, and paywall placement. Not for short Notes (use substack-notes-writer) or reviewing tone (use substack-humanizer).
---

# Substack Post Writer

Draft a post from what the user actually has, then package every field Substack needs.

## Before drafting

1. Read `references/voice-rules.md`, `references/anti-fabrication.md`, `references/platform-limits.md`.
2. Read `~/.substack-skills/voice-profile.md` and `~/.substack-skills/story-bank.md` if they exist.

## Draft

- Build each section from the user's outline, message, Story Bank, or files. Where a section needs a fact you don't have, write around it with a slot: `[what the tool stack cost last month]`.
- When the input is thin (an outline of labels), the draft is a skeleton: a heading and 2 to 4 lines per section, made of the user's words plus slots. Still a draft, never a refusal.
- Working length 1,000 to 2,500 words unless the user sets one.
- **Clipping check:** Gmail clips emails over 102KB. If the user's target or past style is over about 6,000 words, or image-heavy, say so before drafting and offer: split into a series, cut, or accept that email readers see "View entire message".

`--mode package` skips drafting and packages an existing draft.

## Reply shape (always, in this order)

1. Clipping warning, if it applies.
2. The draft or skeleton.
3. The package block below, every field filled. Fields that depend on missing content get a best guess marked `(provisional)`.
4. Up to 3 questions whose answers fill the most slots, or suggest `substack-interviewer --mode post`.

## Package

```
Title: <60 characters or fewer, says what the reader gets>
Subtitle: <one sentence, adds what the title doesn't>
SEO title: <keyword-first version of the title, 60 characters or fewer>
SEO description: <150 to 160 characters, plain language, includes the main keyword>
Slug: <3 to 6 lowercase words joined by hyphens>
Tags: <2 to 4 existing or new topic tags>
Section: <section name from the voice profile, or "main">
Audience: <everyone | only_paid | founding | only_free>
Paywall: <none | after the paragraph starting "...", with one line on why>
Email subscribers: <yes | no | ask the user>
Words: <count> · Clipping risk: <yes | no>
Slots to fill: <list or "none">
```

Mark the paywall in the draft with `<!-- paywall -->` on its own line if there is one.

## Publishing

Hand the draft and package to `substack-publisher` when the user wants it live. This skill doesn't publish.

## Common mistakes

| Mistake | Fix |
|---|---|
| Replying with only questions | Skeleton, package, then questions |
| Leaving out SEO, slug or tags because the user didn't ask | The package is always complete |
| Ignoring a 9,000 word target | Warn about clipping first |
| Inventing the cost, date or result in a section | 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 →