Writing Hooks — Development skill for Claude Code

writing-hooks

A Claude Code / Claude Cowork skill that generates scroll-stopping opening lines for any piece of content.

Why this exists

Most content dies at line one. Not because the idea is weak, because the opener asks the reader to care before giving them a reason to.

This skill treats the hook as its own job:

• 5 hooks per run, across at least 3 different mechanisms so you are choosing between real alternatives, not five phrasings of one idea
• Each labelled by type and by the awareness stage it targets - a cold-audience hook and a most-aware hook are different tools
• Brand-aware - it writes to the audience in your config, not to a generic reader
• Called by other writing skills before they draft the body, so the opener is chosen deliberately rather than backfilled

It does not write body copy, CTAs or full drafts. It writes the first line, which is the one that decides whether the rest gets read.

First run

The skill ships with **zero identity in it**. It does not know your brand, your audience or your CTAs, and it will not guess.

On first use it runs a setup wizard (`SETUP.md`) that asks about your brands, who reads them, their pains in their own words, your voice cues and the CTAs you actually use. It writes the answers to `config/brand-profile.md`.

`config/` is gitignored. Your answers never get committed, and never leave your machine.

How it pairs with the family

Skill	What it does
voice-analyser	Extract: builds tone-of-voice.md from 3 real writing samples
voice-humaniser	Rewrite: strips AI-writing tells and rewrites in the documented voice
voice-scoring-expert	Score: validates voice fit before shipping
linkedin-post-analyser	Score: LinkedIn platform fi