ProSkillsLibraryFreePassScan
Viral Hooks

Viral Hooks · agent skill

Hook Lab

Five hooks per post, each a different pattern.

Scan 100/100Grade A~971 tokens on trigger1 file

What it does

Five hooks per post, each a different pattern.

Your agent loads it when the user writes the first line of a post. It carries 3 rules and reads a profile.md with your details before it starts, so the output matches your brand and project.

SKILL.md, first 40 lines

---
name: hook-lab
description: "Use when the user writes or rewrites the first line of a post, tweet, LinkedIn update, caption or video opener, or says \"I need a hook\", \"first line\", \"this post is not landing\". Writes five hooks per post, each a different pattern, each under twelve words and a specific claim. Reads profile.md for brand, audience and platforms."
---

# Hook Lab

The first line decides whether the rest is read. A hook works when it makes one specific claim the audience can picture. A teaser such as "You won't believe what happened" promises something and says nothing, so it fails. This skill produces five hooks in five different patterns so the user can choose by pattern, not by luck.

## Before you start

Read `profile.md` in this folder:

| profile.md line | Use |
|---|---|
| **Brand** | Voice and product names; never mention a competitor. |
| **Audience** | The person the claim is for. Use their vocabulary and their problem. |
| **Platforms** | Where it will run. Adjust length and tone per platform (see rules). |

If a line says "not set", ask the user once, write the answer into profile.md, then continue.

## Workflow

1. Get the post's single point and its proof (a number, a result, a story, a before and after). If there is no proof, ask for one. Never invent a statistic, client or result.
2. Write one hook for each of five different patterns from the list below. Choose the five that fit the point best; never two of the same pattern.
3. Count words. Cut each hook to eleven words or fewer.
4. Test each: does it contain a specific noun, number or outcome? Could another post by anyone use it unchanged? If yes, rewrite.
5. Mark the strongest one and say why in one line. State which platform each suits.

## Patterns

| Pattern | Shape |
|---|---|
| Result | The outcome, with the number: "Cut onboarding from 9 steps to 3." |
| Contrarian | A claim against the common belief, with the reason. |
| Mistake | What you did wrong and what it cost, in the first person. |
| Process | "How X does Y in N steps", with the real N. |
| Before and after | Two states, one line. |
| Named enemy | A specific thing the audience hates, called out. |
| Quote | A line someone actually said, with who. |

Install

One command, in your project folder. It detects your agent; add --agent all for every agent.

npx proskills-cli add hook-lab

Or copy the skill folder (the one holding SKILL.md) into the directory your agent reads, then restart it or start a new session.

AgentThis projectEvery project
Claude Code.claude/skills/~/.claude/skills/
Cursor.agents/skills/ (or .cursor/skills/)~/.cursor/skills/
Codex.agents/skills/~/.agents/skills/
Gemini CLI.agents/skills/ (or .gemini/skills/)~/.gemini/skills/

More from Viral Hooks

The scan checks spec compliance, token cost, clarity and security patterns. A clean scan is not a guarantee: static scanners can be evaded. Scan any skill yourself.