Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Marketing Copy

ASecurity

Write copy that sells — landing page, headline, product description, email, ad, social post, app-store listing, newsletter. Use whenever the text has to make someone act rather than just inform.

2 stars
0 votes
0 copies
1 views
Added 10/3/2026
ai-agentsrustgosecurity

Security Analysis

A100/100

Scanned 10/3/2026

$npx -y skills add ivanvp91/TRCode --skill marketing-copy --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Marketing Copy?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Marketing Copy
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ivanvp91-marketing-copy/badge)](https://www.skillsdirectory.com/skills/ivanvp91-marketing-copy)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: marketing-copy
description: Write copy that sells — landing page, headline, product description, email, ad, social post, app-store listing, newsletter. Use whenever the text has to make someone act rather than just inform.
description_ru: Написать продающий текст — лендинг, заголовок, описание продукта, письмо, объявление, пост, карточку в сторе, рассылку. Всегда, когда текст должен побудить к действию, а не просто сообщить.
triggers: копирайт, копирайтинг, copywriting, headline, слоган, tagline, реклама, объявление, рассылка, текст для лендинга, описание продукта, product description
---

# Marketing copy

## 1. Gather before writing
- **Product**: what it literally does. If it is in this repo, read the README and the actual features — never invent capabilities.
- **Reader**: who they are, what they are trying to do, what they use today.
- **Pain**: the specific frustration in their words, not "inefficiency".
- **Proof**: numbers, integrations, customers, guarantees — whatever is real.
- **One action**: the single thing this piece should cause.

If proof or audience is unknown, ask — or write it and flag the assumptions. Never fabricate metrics, testimonials or logos.

## 2. Lead with the outcome
The reader's first question is "what do I get". Answer it in the first line. The mechanism ("AI-powered", "built on X") is support, not the headline. Test any sentence: could a competitor say the same? Then it says nothing — replace it with something only you can claim.

## 3. Landing page skeleton
1. **Headline** — the outcome, ≤ 10 words.
2. **Subhead** — who it is for and how it works, one sentence.
3. **Primary CTA** — a verb phrase describing what happens next (`Start free`, not `Learn more`).
4. **Proof strip** — numbers, logos, one hard result.
5. **Three benefits** — each a benefit heading with one supporting line; feature named, outcome first.
6. **Objection handling** — price, migration, lock-in, security, "will it work for me".
7. **Close** — repeat the CTA with the outcome restated.

## 4. Sentence craft
- Short sentences. Concrete nouns. Active verbs. Second person.
- Specific beats superlative: "deploys in 40 seconds" over "blazing fast".
- Cut: "revolutionary", "seamless", "cutting-edge", "solution", "empower", "unlock", "in today's world".
- Read it aloud — if you would not say it to a colleague, rewrite it.
- Match the register the audience already uses; developers distrust adjectives, executives want outcomes and risk.

## 5. Format for the channel
Email: one idea, subject ≤ 45 chars, first line visible in preview, one CTA. Ad: headline does the work, no setup. Social: first line stops the scroll, no link in the first sentence. App store: first three lines are all most people read.

## What not to do
- No claims you cannot support, no fake urgency, no invented social proof.
- Do not write about the company; write about the reader.
- Do not stack three CTAs — one page, one action.

## Answer format
The copy itself, ready to paste, labelled by slot (Headline / Subhead / CTA / …). Then: 2–3 headline alternatives with different angles, and a list of every assumption or number that needs confirming.

Attribution

ivanvp91ivanvp91
View sourceSee grades on GitHubMore from ivanvp91 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →