# Copywriting Frameworks

> Direct-response copywriting workflow for drafting, rewriting, critiquing, and explaining persuasive copy. Use when Claude needs to work on headlines, hooks, ads, landing pages, emails, sales pages, CTAs, founder stories, lead magnets, social or video scripts, offer pages, copy critiques, copywork, swipe-file analysis, AIDA, curiosity gaps, open loops, objection handling, proof-first ads, or story…

- **Type:** Skill
- **Install:** `agentstack add skill-raintree-technology-agent-starter-copywriting-frameworks`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [raintree-technology](https://agentstack.voostack.com/s/raintree-technology)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [raintree-technology](https://github.com/raintree-technology)
- **Source:** https://github.com/raintree-technology/agent-starter/tree/main/templates/.claude/skills/copywriting-frameworks
- **Website:** https://claude.raintree.technology

## Install

```sh
agentstack add skill-raintree-technology-agent-starter-copywriting-frameworks
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Copywriting Frameworks

## Overview

Use this skill to turn generic messaging into specific persuasive copy. Anchor the work on one reader, one desired action, believable proof, and the next sentence.

## Fast Workflow

1. Identify the audience, offer, desired action, channel, funnel stage, brand voice, proof constraints, and forbidden claims. If details are missing and the task can still proceed, state assumptions briefly.
2. Choose the dominant job:
   - Hook/headline: select one reader, open a curiosity loop, and use a concrete image or identity target.
   - Long-form copy: use AIDA and story; make the customer the hero and the product the guide.
   - Ad or video script: start with a pattern interrupt, build belief before naming the product, then make the CTA feel earned.
   - Critique: diagnose attention, specificity, proof, desire, objections, and CTA friction.
   - Copywork: build a repeatable swipe-study routine from strong examples in the same medium.
3. Draft in passes: first make it specific, then make it credible, then cut.
4. Mark unverifiable claims as `needs proof` instead of inventing data, testimonials, endorsements, or scientific support.

## Required Checks

- Make the first line earn the second line.
- Make the headline select or repel a specific audience.
- Add proof, a concrete demonstration, or an explicit proof placeholder.
- Create tension and change; do not merely list events.
- Handle likely objections before the CTA.
- Keep sentences simple and varied; prefer one point per sentence.
- Let copy be long only while tension, proof, or desire is still building.
- Match the brand's permission for humor, edge, and directness.

## Output Shape

For creative requests, provide several variants grouped by angle. For critique requests, lead with the highest-leverage fixes, then give a revised version. For strategic requests, show the selected framework and the reason it fits the audience, channel, and funnel stage.

## Resource

Read `references/direct-response-patterns.md` when selecting patterns, rewriting weak copy, planning copywork, or applying the critique rubric.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [raintree-technology](https://github.com/raintree-technology)
- **Source:** [raintree-technology/agent-starter](https://github.com/raintree-technology/agent-starter)
- **License:** MIT
- **Homepage:** https://claude.raintree.technology

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-raintree-technology-agent-starter-copywriting-frameworks
- Seller: https://agentstack.voostack.com/s/raintree-technology
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.