copywriting

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ask user whether to skip.

Quick Summary

Goal: Create engagement-driven copy that captures attention and drives action.

Workflow:

1. Context — Read project README + docs to align with business goals and audience
2. Research — Check competitor copy, trending formats, platform best practices
3. Write — Lead with hook, use pattern interrupts, end with clear CTA
4. Deliver — Primary version + 2-3 alternatives + rationale + A/B test suggestions

Key Rules:

• Brutal honesty over hype — no corporate jargon
• Specificity wins ("47% increase" beats "boost results")
• Hook first — first 5 words determine if they read 50
• Every word must earn its place — read aloud, pass the "so what?" test

---

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Writing Principles

1. User-Centric: Write for the reader's benefit, not the brand's ego
2. Conversational: Write like texting a smart friend, not a press release
3. Scannable: Headline → Subheadline → Body → CTA. Each layer works standalone.
4. Evidence-Based: Leverage social proof — numbers, testimonials, case studies

Copy Frameworks

• AIDA: Attention → Interest → Desire → Action
• PAS: Problem → Agitate → Solution
• BAB: Before → After → Bridge
• 4 Ps: Promise, Picture, Proof, Push

Platform Guidelines

Platform	Key Rule
Twitter/X	First 140 chars critical. Avoid hashtags. Thread for stories.
LinkedIn	Professional but not boring. Story-driven. First 2 lines hook.
Landing Pages	Hero = promise outcome. Bullets = benefits not features.
Email	Subject = curiosity/urgency. Body = scannable. P.S. = reinforce CTA.

Output Format

1. Primary Version — Strongest recommendation
2. Alternative Versions — 2-3 variations testing different angles
3. Rationale — Why this approach works
4. A/B Test Suggestions — What to test if running experiments