Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Humblytics/humblytics-marketing-skills --skill copywritinggit clone --depth 1 https://github.com/Humblytics/humblytics-marketing-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/humblytics/humblytics-marketing-skills/copywriting)<a href="https://agentmods.dev/skills/humblytics/humblytics-marketing-skills/copywriting"><img src="https://agentmods.dev/badge/skills/humblytics/humblytics-marketing-skills/copywriting/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/humblytics/humblytics-marketing-skills/copywriting"><img src="https://agentmods.dev/badge/skills/humblytics/humblytics-marketing-skills/copywriting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.02817 |
| Opus 5.5 | $0.00036 | $0.01127 |
| Sonnet 5.5 | $0.00018 | $0.00563 |
| Haiku 4.5 | $0.00009 | $0.00282 |
Grade A, and why
copywriting scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copywriting
Purpose
Write conversion-focused copy for any marketing context — landing pages, email sequences, advertisements, CTAs, product descriptions, sales pages, and more. Every piece of copy exists to drive a specific action. This skill produces clear, compelling, benefit-driven copy that respects the reader's intelligence while motivating them to act.
When to Use
- Writing or rewriting landing page copy (hero, features, CTAs, testimonials)
- Crafting email subject lines and body copy
- Creating ad copy for any platform
- Writing headlines and subheadlines
- Developing product descriptions
- Creating CTAs and button text
- Writing sales page long-form copy
- Taglines and brand messaging
- Signup flow microcopy
Before You Start
- Understand the product — What does it do? What is the core value? What makes it different?
- Know the audience — Who is reading this? What do they care about? What language do they use?
- Define the action — What is the one thing you want the reader to do after reading?
- Awareness level — How aware is the audience? (Unaware → Problem Aware → Solution Aware → Product Aware → Most Aware)
- Tone and voice — Professional? Casual? Technical? Warm? Check brand guidelines.
- Context — Where will this copy appear? What precedes and follows it?
- Look for context — Check project docs, AGENTS.md, existing copy, and brand voice documentation
Core Copywriting Principles
1. Clarity Over Cleverness
The reader should never have to re-read a sentence. If a line is clever but unclear, rewrite it clearly. The best copy is invisible — the reader feels the message without noticing the writing.
Bad: "Unlock the paradigm of data-driven growth synergies" Good: "See exactly where you're losing customers — and fix it"
2. Benefits Over Features
Features describe what the product does. Benefits describe what the customer gets. Always lead with benefits.
Feature: "Real-time analytics dashboard" Benefit: "Know what's working on your site right now — not yesterday"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 278 lines · 89 tokens per session scan A 910fe757afea
copywriting is a skill published in the GitHub repository Humblytics/humblytics-marketing-skills (85 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 2,817 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
copywriting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| copywritingHumblytics/humblytics-marketing-skills | Skill | 85 | 1mo ago | MIT | A | 89 | Claude Code, Codex |
| ab-test-generatorAffitor/affiliate-skills | Skill | 767 | 18d ago | MIT | A | 87 | Claude Code |
| authoring-ci-workflowsPostHog/posthog | Skill | 41k | yesterday | none | A | 200 | Claude Code, Codex |
| isolating-product-facade-contractsPostHog/posthog | Skill | 41k | yesterday | none | A | 76 | Claude Code, Codex |
| triaging-merge-queue-failuresPostHog/posthog | Skill | 41k | yesterday | none | A | 180 | Claude Code, Codex |
| creating-online-evaluationsPostHog/posthog | Skill | 41k | yesterday | none | A | 203 | Claude Code, Codex |
| debugging-mcp-analyticsPostHog/posthog | Skill | 41k | yesterday | none | A | 211 | Claude Code, Codex |