Agent skill

Copywriting

by seb1n in seb1n/awesome-ai-agent-skills

Write compelling, persuasive marketing and sales copy using proven frameworks like AIDA, PAS, BAB, and 4Ps, with tone and voice customization, CTA optimization, and A/B variant generation.

MITAuto-check passedWriting & Content

Install Copywriting

skills CLI
$ npx skills add seb1n/awesome-ai-agent-skills --skill copywriting -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install seb1n/awesome-ai-agent-skills copywriting --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/seb1n/awesome-ai-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/writing-and-content/copywriting .claude/skills/copywriting && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
copywriting
GitHub stars
206
Token cost
~1.9k tokens
SKILL.md length
1,008 words
Files
1
Skills in repo
101
Repo updated
First seen
Licence
MIT

At a glance

Write compelling, persuasive marketing and sales copy using proven frameworks like AIDA, PAS, BAB, and 4Ps, with tone and voice customization, CTA optimization, and A/B variant generation.

  • Works in 6 steps: Define the Objective and Audience → Select a Copywriting Framework → Establish Tone and Voice → …
  • The user requests copywriting
  • SKILL.md covers Workflow, Usage, Examples and Best Practices, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Copywriting is an agent skill from seb1n/awesome-ai-agent-skills. Write compelling, persuasive marketing and sales copy using proven frameworks like AIDA, PAS, BAB, and 4Ps, with tone and voice customization, CTA optimization, and A/B variant generation. Use when the user requests copywriting or provides relevant inputs for this workflow.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Copywriting. The repository describes itself as: 103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf, and other Agent Skills-compatible tools. Complete SKILL.md… The licence is MIT.

When your agent uses it

  • The user requests copywriting
  • Provides relevant inputs for this workflow

Example prompts

  • “/copywriting”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Define the Objective and Audience
  2. Select a Copywriting Framework
  3. Establish Tone and Voice
  4. Draft the Copy
  5. Optimize the CTA
  6. Generate A/B Variants

What it can do on your machine

Read from SKILL.md and the folder at commit 75865a5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Copywriting loads about 1.9k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 1,008 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from seb1n/awesome-ai-agent-skills at commit 75865a5, republished under its MIT licence (© seb1n). 1,008 words, ~1,922 tokens.

Download SKILL.mdSave it as .claude/skills/copywriting/SKILL.md (or your agent's skills folder).
name
copywriting
description
Write compelling, persuasive marketing and sales copy using proven frameworks like AIDA, PAS, BAB, and 4Ps, with tone and voice customization, CTA optimization, and A/B variant generation. Use when the user requests copywriting or provides relevant inputs for this workflow.
license
MIT
metadata.author
awesome-ai-agent-skills
metadata.version
1.0.0

Copywriting

This skill enables an AI agent to write persuasive marketing and sales copy that drives action. The agent applies proven copywriting frameworks — AIDA (Attention, Interest, Desire, Action), PAS (Problem, Agitation, Solution), BAB (Before, After, Bridge), and 4Ps (Promise, Picture, Proof, Push) — and adapts tone, voice, and structure to the brand, audience, and channel. It supports landing pages, email campaigns, social media ads, product descriptions, and more.

Workflow

  1. Define the Objective and Audience Clarify the primary goal: drive conversions, generate leads, increase brand awareness, or nurture existing customers. Identify the target audience — their pain points, desires, language patterns, and stage in the buyer's journey (awareness, consideration, decision). This determines which framework and emotional levers to use.

  2. Select a Copywriting Framework Choose the framework that best fits the objective. Use AIDA for landing pages and ads that guide readers from attention to action. Use PAS when the audience has a strong, identifiable pain point. Use BAB for case studies and transformation stories. Use 4Ps when you have strong social proof. State which framework is being applied and why.

  3. Establish Tone and Voice Define the brand voice (authoritative, friendly, playful, luxurious, bold) and the specific tone for this piece (urgent, empathetic, excited, reassuring). If brand guidelines are provided, follow them precisely. If not, infer an appropriate voice from the product category and audience.

  4. Draft the Copy Write the copy following the chosen framework's structure. Open with a strong hook. Build emotional engagement through the body — agitate the pain, paint the transformation, or stack the benefits. Close with a clear, specific CTA. Every sentence should earn its place; cut anything that does not move the reader toward the CTA.

  5. Optimize the CTA Replace generic phrases like "Submit" or "Click Here" with benefit-driven language like "Start Your Free Trial." Consider the commitment level — a free trial CTA differs from a $5,000 enterprise demo request. Use urgency elements only when they are truthful.

  6. Generate A/B Variants Produce at least two distinct versions of the key elements — headline, subheadline, and CTA — for testing. Variants should differ meaningfully (different angles or emotional hooks), not just in word choice. Label each variant and note the hypothesis behind it.

Usage

Provide the agent with:

  • Product or service — what you are selling or promoting
  • Objective — conversions, signups, traffic, awareness, retention
  • Target audience — demographics, psychographics, buyer journey stage
  • Channel — landing page, email, Facebook ad, Google ad, product page
  • Brand voice — or a link to brand guidelines
  • Constraints — character limits, required disclaimers, mandatory phrases

Example prompt: "Write a landing page hero section for our project management tool aimed at remote teams. Use PAS. Tone: confident but friendly. Include two headline variants."

Examples

Example 1: Landing Page Hero Section (PAS Framework)

Input: "SaaS product: CloudSync — automated file backup for freelancers. Audience: freelancers who have lost files before. Goal: free trial signups."

Output:

Variant A (Fear-driven):

Headline: One Crashed Hard Drive Away from Losing Everything? Subheadline: Freelancers lose an average of 4.7 hours of work per data loss incident. Body: You have spent months building your portfolio and client deliverables. One spilled coffee, one ransomware email, and it can all vanish. CloudSync backs up every file change automatically to encrypted cloud storage. If disaster strikes, restore everything in minutes. CTA: Start Your Free 14-Day Backup — No Credit Card Needed

Variant B (Aspiration-driven):

Headline: Work Fearlessly. Every File, Backed Up Automatically. Subheadline: Enterprise-grade backup for freelancers — without the enterprise price. Body: CloudSync watches your folders and syncs every change in real time. Version history, AES-256 encryption, and setup in under two minutes. CTA: Protect Your Work Free for 14 Days

A/B Hypothesis: Variant A tests loss aversion; Variant B tests aspirational confidence. Compare signup rates to determine which emotional angle resonates.

Show full SKILL.md (386 more words)Show less
Example 2: Email Marketing Sequence (AIDA Framework)

Input: "Product: FitTrack smart fitness watch. Audience: health-conscious professionals, 30-45. Goal: convert leads who have a discount code."

Output:

Email 1 — Attention + Interest (Day 0) Subject: Your 20% off code is inside (expires in 48 hours) Body: Hi {first_name}, here is your code: FIT20. FitTrack tracks heart rate, sleep, and activity, then gives you a single weekly health score — no complicated dashboards. [Shop FitTrack — 20% Off]

Email 2 — Desire (Day 1) Subject: "I finally sleep through the night" — here is what changed Body: Sarah, a marketing director, was averaging 5.2 hours of broken sleep. Two weeks with FitTrack revealed the culprit: late-evening screen time. One habit change, and her sleep score jumped 34%. That is why 92% of users feel healthier after 30 days. Code FIT20 still active. [Get Your FitTrack Now]

Email 3 — Action (Day 2) Subject: Last call — your 20% code expires tonight Body: Your code FIT20 expires at midnight. Free shipping. 30-day money-back guarantee. [Claim Your Discount Before Midnight]

Best Practices

  • Lead with the benefit, not the feature. "Save 3 hours every week" beats "Automated scheduling engine." Translate every feature into the outcome it creates.
  • Write for scanners. Use short paragraphs, bold key phrases, and subheadings. Put the most important message in the first line.
  • Use specific numbers. "Join 14,327 freelancers" is more credible than "Join thousands." Specificity builds trust.
  • Match the CTA to the commitment level. Low-commitment offers (free trial) earn bolder CTAs than high-commitment asks (enterprise demo). Reduce friction with "No credit card required."
  • Create honest urgency. Real deadlines and genuine scarcity drive action. Fake urgency erodes trust.
  • Test one variable at a time. In A/B variants, change only the headline or only the CTA — not both — so results are actionable.

Edge Cases

  • Regulated industries: Financial, healthcare, and legal copy may require disclaimers or pre-approval. Flag when the product category likely triggers compliance requirements.
  • No brand guidelines provided: Default to clear, confident, benefit-focused copy. Avoid slang and hype words unless explicitly requested.
  • Extremely short formats: For Google Ads (30-character headlines) or SMS (160 characters), prioritize the single strongest benefit and the CTA.
  • Multi-language campaigns: Avoid idioms, puns, and cultural references that do not translate. Write for translatability.
  • Sensitive topics: When writing about health, finances, or personal struggles, use empathetic language and avoid exploitative fear-mongering.

© seb1n, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in writing-and-content/copywriting of seb1n/awesome-ai-agent-skills.

Open the folder on GitHubat commit 75865a5

Compare with similar skills

Copywriting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Copywriting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Copywriting this skillseb1n/awesome-ai-agent-skills206—~1.9kAutomated safety check: PassMIT
Asd Ste100danyuchn/asd-ste100-skill4.2k—~4.1kAutomated safety check: PassMIT
AI Copywritermikiarlo3/ai-copywriter1.2k—~12kAutomated safety check: PassMIT
Brand Voice Guideluongnv89/claude-howto42k—~609Automated safety check: PassMIT
Ralph Copywritermuratcankoylan/ralph-wiggum-marketer777—~2.4kAutomated safety check: PassNone
Humanities Writing Companiontizzy916/humanities-writing-companion435—~3.4kAutomated safety check: PassCC-BY-NC-4.0

Similar skills

  • Asd Ste100

    danyuchn/asd-ste100-skill

    A skill your agent uses when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and…

    4.2k GitHub stars~4.1k tokensUpdated 5 days ago
    Writing & ContentAuto-check passed
  • AI Copywriter

    mikiarlo3/ai-copywriter

    Write copy that converts and doesn't sound like a robot. An agent skill from mikiarlo3/ai-copywriter.

    1.2k GitHub stars~12k tokensUpdated 2 mo ago
    Writing & ContentAuto-check passed
  • Brand Voice Guide

    luongnv89/claude-howto

    Ensure all communication matches brand voice and tone guidelines. Use when creating marketing copy, customer communications, public-facing content, or when…

    42k GitHub stars~609 tokensUpdated 9 days ago
    Writing & ContentAuto-check passed
  • Ralph Copywriter

    muratcankoylan/ralph-wiggum-marketer

    A skill your agent uses when the user asks to "analyze my content", "learn my writing style", "research competitors", "find content angles", "improve my blog", "write like me", "embody my brand…

    777 GitHub stars~2.4k tokensUpdated 6 mo ago
    Writing & ContentAuto-check passed
  • Humanities Writing Companion

    tizzy916/humanities-writing-companion

    Help with humanities scholarly writing: sharpen research questions, map supplied readings, plan and draft arguments, review chapters, preserve authorial voice, and respond to reviewers.

    435 GitHub stars~3.4k tokensUpdated 17 days ago
    Writing & ContentAuto-check passed
  • Xiaoma Durex Copywriter

    crawfordxx/xiaoma-durex-copywriter

    用杜蕾斯黄金期(2011-2017 环时互动)那套「双层语义 + 留白」的方法产出文案与海报。先识别用户意图并给 3-5 个方案供选,再出短文案(长文案可选)+ 五种比例配图。适用于借势热点、节日节气、产品卖点、课程/知识付费推广、自媒体标题与封面、品牌人格化运营。当用户说「写个文案」「借势热点」「节日海报」「想句…

    582 GitHub stars~1.8k tokensUpdated 2 mo ago
    Writing & ContentAuto-check passed

More from seb1n/awesome-ai-agent-skills

All 101 skills in this repo
  • Agent Red Teaming

    seb1n/awesome-ai-agent-skills

    Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings.

    206 GitHub stars~2.8k tokensUpdated 2 mo ago
    Auto-check passed
  • Eu AI Act Readiness

    seb1n/awesome-ai-agent-skills

    Build a preliminary, evidence-based EU AI Act readiness assessment across AI-system inventory, territorial scope, operator roles, prohibited-practice screening, risk classification, transparency…

    206 GitHub stars~3.3k tokensUpdated 2 mo ago
    Auto-check passed
  • Human In The Loop

    seb1n/awesome-ai-agent-skills

    Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows.

    206 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • MCP Server Building

    seb1n/awesome-ai-agent-skills

    Design, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege authorization, safe transports, structured errors, and interoperability tests.

    206 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • PDF Processing

    seb1n/awesome-ai-agent-skills

    Inspect, extract, OCR, create, merge, split, reorder, rotate, annotate, fill, redact, compress, secure, and verify PDF documents while preserving source files and visual fidelity.

    206 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Skill Supply Chain Audit

    seb1n/awesome-ai-agent-skills

    Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk.

    206 GitHub stars~2.4k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Copywriting

What does Copywriting do?

Write compelling, persuasive marketing and sales copy using proven frameworks like AIDA, PAS, BAB, and 4Ps, with tone and voice customization, CTA optimization, and A/B variant generation. Copywriting is an agent skill from seb1n/awesome-ai-agent-skills. Write compelling, persuasive marketing and sales copy using proven frameworks like AIDA, PAS, BAB, and 4Ps, with tone and voice customization, CTA optimization, and A/B variant generation.

When should I use Copywriting?

Copywriting fits situations like: the user requests copywriting; provides relevant inputs for this workflow.

How do I install Copywriting in Claude Code?

Run `npx skills add seb1n/awesome-ai-agent-skills --skill copywriting -a claude-code`. Or copy the skill folder (writing-and-content/copywriting in seb1n/awesome-ai-agent-skills) into .claude/skills/copywriting in your project. Claude Code loads it when a task matches its description.

How do I install Copywriting in Codex?

Run `npx skills add seb1n/awesome-ai-agent-skills --skill copywriting -a codex`. Or copy the skill folder (writing-and-content/copywriting in seb1n/awesome-ai-agent-skills) into .agents/skills/copywriting in your project. Codex loads it when a task matches its description.

Can I use Copywriting in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add seb1n/awesome-ai-agent-skills --skill copywriting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/copywriting, .gemini/skills/copywriting, .github/skills/copywriting and .opencode/skills/copywriting in your project.

What does Copywriting need to run?

SKILL.md names no scripts, command-line tools or credentials: Copywriting is instructions for the agent only.

Does Copywriting access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Copywriting safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Copywriting use?

Copywriting is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Copywriting use?

About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Copywriting?

Skills that share tags, products or a category with Copywriting: Asd Ste100 (danyuchn/asd-ste100-skill, 4.2k stars), AI Copywriter (mikiarlo3/ai-copywriter, 1.2k stars), Brand Voice Guide (luongnv89/claude-howto, 42k stars) and Ralph Copywriter (muratcankoylan/ralph-wiggum-marketer, 777 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Copywriting?

seb1n (a GitHub user) maintains it in seb1n/awesome-ai-agent-skills, which has 206 GitHub stars. The repository holds 101 skills in this directory. The repository was last updated on August 9, 2026.

Source: seb1n/awesome-ai-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.