Copywriting
Write conversion-focused copy using proven frameworks (AIDA, PAS, BAB). Produces headlines, CTAs, landing page copy, email sequences, and micro-copy. Ensures copy matches brand voice and target audience.
Best use case
Copywriting is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Write conversion-focused copy using proven frameworks (AIDA, PAS, BAB). Produces headlines, CTAs, landing page copy, email sequences, and micro-copy. Ensures copy matches brand voice and target audience.
Teams using Copywriting should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/copywriting/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Copywriting Compares
| Feature / Agent | Copywriting | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Write conversion-focused copy using proven frameworks (AIDA, PAS, BAB). Produces headlines, CTAs, landing page copy, email sequences, and micro-copy. Ensures copy matches brand voice and target audience.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Skill: Copywriting
## Metadata
| Field | Value |
|-------|-------|
| **Skill ID** | SKL-0033 |
| **Version** | 1.0 |
| **Owner** | builder |
| **Inputs** | Target page, PRD.md, brand guidelines |
| **Outputs** | Copy in target files or docs/COPY.md, STATE.md updated |
| **Triggers** | `COPYWRITING_REQUESTED` |
---
## Purpose
Write copy that converts — not just fills space. Generic placeholder text ("Welcome to our app") kills conversion rates. This skill applies proven copywriting frameworks to produce headlines, CTAs, landing page sections, email sequences, and micro-copy that matches the product's value proposition and target audience.
---
## Procedure
### Step 1 — Understand the Context
Read:
1. `docs/PRD.md` — extract value proposition, target users, problem statement
2. Target page/component — understand what copy is needed and where
3. Any existing brand guidelines in `docs/`
4. `docs/PROBLEM_STRESS_TEST.md` (if exists) — the validated problem language
Identify the copy type needed:
- **Hero section** (headline + subhead + CTA)
- **Feature descriptions** (benefit-focused, not feature-focused)
- **Social proof** (testimonial framing, trust signals)
- **Email sequence** (welcome, onboarding, re-engagement)
- **Micro-copy** (button text, error messages, empty states, tooltips)
- **About page** (story, mission, team)
### Step 2 — Select Framework
| Framework | Best For | Structure |
|-----------|----------|-----------|
| **AIDA** | Landing pages, ads | Attention → Interest → Desire → Action |
| **PAS** | Problem-aware audiences | Problem → Agitate → Solution |
| **BAB** | Aspirational products | Before → After → Bridge |
| **4Ps** | Feature sections | Promise → Picture → Proof → Push |
| **StoryBrand** | Brand narrative | Character → Problem → Guide → Plan → Action → Success → Failure |
### Step 3 — Write Copy
**Headlines:**
- Lead with the benefit, not the feature
- Use the user's language (from PRD target users section)
- Test: "Would I click this?" If not, rewrite.
- Provide 3 headline options: safe, bold, and provocative
**CTAs:**
- Action verb + value ("Start saving time" not "Submit")
- One primary CTA per section — never compete with yourself
- Micro-copy under buttons reduces friction ("No credit card required", "Cancel anytime")
**Body copy:**
- Short paragraphs (2-3 sentences max)
- One idea per paragraph
- Conversational tone unless brand guidelines specify otherwise
- Features → Benefits: "AI-powered search" → "Find what you need in seconds"
**Micro-copy:**
- Error messages: Say what went wrong + how to fix it
- Empty states: Guide the user to their first action
- Loading states: Reassure ("Setting up your workspace...")
- Success states: Celebrate + suggest next step
### Step 4 — Voice Consistency Check
If brand guidelines exist, verify all copy matches:
- Tone (formal/casual/playful/authoritative)
- Vocabulary level (target 8th-grade reading level for public content per accessibility rules)
- Prohibited words or phrases
- Pronoun style (we/you/our)
### Step 5 — Write Output
- If copy is for specific pages/components: write directly to those files
- If copy is general (email sequences, ad variations): write to `docs/COPY.md`
- Always provide the framework used and rationale for key choices
### Step 6 — Update STATE.md
---
## Constraints
- Never writes generic placeholder text — every string should be intentional
- Always leads with benefits, not features
- Copy must be factual — no unsupported claims or fake testimonials
- Respects accessibility: plain language, clear CTAs, no "click here"
- Does not make promises the product can't keep
- Multiple options provided for headlines and CTAs — user chooses
---
## Primary Agent
builder
---
## Definition of Done
- [ ] Copy context understood (PRD, target users, problem statement)
- [ ] Framework selected and applied
- [ ] Headlines provided (3 options)
- [ ] CTAs are action-verb + value (not "Submit" or "Click here")
- [ ] Body copy follows short-paragraph, benefit-first pattern
- [ ] Micro-copy covers error, empty, loading, and success states
- [ ] Voice consistency verified against brand guidelines (if any)
- [ ] Copy written to target files or docs/COPY.md
- [ ] STATE.md updated
## Output Contract
| Field | Value |
|-------|-------|
| **Artifacts** | Copy in target files or `docs/COPY.md` |
| **State Update** | `.claude/project/STATE.md` — mark task complete, log files modified |
| **Handoff Event** | `TASK_COMPLETED` (copy written) |Related Skills
Supply Chain Audit
Audit the dependency supply chain for security risks beyond what `npm audit` or `pip audit` catches. Analyzes dependency health, maintainer trust signals, typosquatting risk, and transitive dependency exposure.
SEO Audit
Audit web pages for search engine optimization: meta tags, heading hierarchy, structured data, image optimization, mobile-friendliness, and content quality. Complements SKL-0013 (Growth & Distribution) by validating what was built.
Pitch Deck
Create a structured pitch deck outline for investors, stakeholders, or partners. Covers problem, solution, market, traction, team, and ask. Natural output after PRD + Problem Stress Test validation.
Launch Checklist
Pre-launch validation covering everything deployment (SKL-0021) doesn't: analytics, error tracking, social meta, legal pages, email setup, DNS, SSL, and go-live readiness. Produces a launch readiness report with pass/fail checklist. Use this skill before going live on any project.
Insecure Defaults Detection
Detect insecure default configurations, hardcoded credentials, fail-open security patterns, and dangerous default values in application code and configuration files. Complements SKL-0015 (Security Audit) by focusing on configuration-level vulnerabilities that dependency scanners miss.
Differential Security Review
Security-focused review of code changes using git diff analysis. Identifies security implications of recent modifications — new attack surfaces, removed protections, changed auth logic, and risky refactors. Complements SKL-0016 (Code Review) with a security lens on diffs.
Competitor Analysis
Structured competitor research: features, pricing, positioning, gaps, and differentiation strategy. Feeds into PRD Writing (SKL-0004) and Problem Stress Test (SKL-0027) with better market context.
UX Design
Design user experiences including wireframes, flows, and interaction patterns. Use this skill when UX design work is requested, including onboarding flows and interface layouts.
User Acceptance Testing
Structured QA testing with four modes: diff-aware (auto-scoped to branch changes), full (systematic exploration), quick (30-second smoke test), and regression (compare against baseline). Produces health score, structured reports, and actionable bug lists. Use this skill when UAT is requested or a feature is ready for acceptance testing.
Token Audit
Audit the current project for token waste patterns. Produces a Token Health Report with scored findings and actionable fixes. Use this skill when token usage feels high, sessions are hitting limits, or before optimizing costs.
Test Writing
Write automated tests for existing or new functionality. Use this skill when tests are requested, including unit tests, integration tests, and end-to-end tests.
Skill Creator
Turn a repetitive workflow into a reusable custom skill. Interviews the user, then produces a complete SKILL.md with frontmatter, procedure, constraints, definition of done, and output contract in custom-skills/. Use this skill when you find yourself repeating the same process and want to automate it.