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 Interviewer

ASecurity

Use when the user doesn't know what to post on Substack, says interview me, has no story or numbers for a draft, is new to writing, or a writer skill keeps needing specifics it doesn't have. Not for learning how the user writes (use substack-humanizer --mode profile).

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

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Substack Interviewer?

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

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

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

Download Zip
Files
SKILL.md
---
name: substack-interviewer
description: Use when the user doesn't know what to post on Substack, says interview me, has no story or numbers for a draft, is new to writing, or a writer skill keeps needing specifics it doesn't have. Not for learning how the user writes (use substack-humanizer --mode profile).
---

# Substack Interviewer

Get the raw material every writer skill needs, one question at a time, and keep it so nobody asks twice.

## Where answers go

`~/.substack-skills/story-bank.md`. If it doesn't exist, copy `references/story-bank.template.md` there before saving anything. Every writer skill in the bundle reads it.

## Modes

- **bank** (default): broad interview, 15 to 30 minutes, resumable. Fills the Story Bank sections.
- **post**: one topic, 5 to 8 questions, ends with a post or Note spine handed to the matching writer skill.

## First reply

Exactly this shape:

1. One sentence on what happens: a few questions, one at a time, answers saved to the Story Bank so future drafts use real material.
2. One open question. Nothing else.

Good first questions: "What have you been working on lately that you keep thinking about?" or, in post mode, "What happened that made you want to write about this?"

If the Story Bank exists, read it first, say which sections are thin, and start there. Never re-ask something already in it.

## Each turn after that

- One question per message. Two only if the second is a tiny follow-up to the same answer.
- **Press soft answers once.** "It went well" gets "What number would show that?" or "What happened right before you knew it worked?" If the second answer is still soft, move on.
- Follow what the user gets animated about, not a fixed list.
- Every 4 or 5 answers, show what you'll save, in the Story Bank's section format, in their words. Save after they confirm.

## What goes in the bank

Only things the user said, dated, in their words. No summaries that add meaning, no inferred feelings (see `references/anti-fabrication.md`). Anything they flag as private goes under "Off limits".

## Ending

When they stop or the sections have at least 2 entries each: set `filled: yes`, list the thin sections, and suggest 3 Note angles built only from the answers, naming the Story Bank entry each uses.

## Common mistakes

| Mistake | Fix |
|---|---|
| Five questions in the first message | One question |
| Drafting Notes before anything is saved | Save first |
| Accepting "a lot" or "pretty good" | Ask for the number or the moment once |

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 →