Skip to content
SkillModel-led3,440 tokens in use

copywriting

Writes and rewrites homepage, landing, pricing and feature copy. It diagnoses the input first, keeps claims supportable and screens out AI-sounding lines.

61,711 stars on the repository MIT Licensecoreyhaines31/marketingskills · skills/copywriting
npx skills add coreyhaines31/marketingskills --skill copywriting
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing copywriting costs

123tokens idle
3,440tokens in use
13,358tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure19/25
  • Examples6/15
  • Output10/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

copywriting guides an agent through conversion copy for homepage, landing, pricing, feature and about pages. Before drafting it decides whether it faces a blank brief, a draft with a real voice, or a point edit, and changes only what that situation allows.

Each unit of the page (headline, subhead, CTA, sections) is drafted in candidates, run through a three-question gate and locked. Claims the source material cannot support are declined with the evidence that would unlock them.

What You Get

  • Page copy organized by section with headline, subhead, CTAs and body
  • Annotations that explain the choice and the principle behind it
  • Two or three alternatives for headlines and CTAs, each with a rationale
  • Meta title and description when relevant
  • Declined claims listed with the closest supportable version and the evidence needed to unlock them

Common Use Cases

  • Writing a homepage hero from a product brief
  • Rewriting a pricing page so visitors can pick a plan
  • Matching a landing page headline to an ad’s promise
  • Fixing a single headline or paragraph without touching the rest

What Makes It Unique

The diagnosis step sets how much the agent may change. A draft with a real voice keeps its vocabulary and angle, and a point edit returns only the changed lines. Every line passes a three-question gate (can the reader picture it, can it be proven true or false, could a competitor write it) and a leave-it-alone test reverts changes that are only different.

Under The Hood

The SKILL.md and its reference files are loaded as context. It ships no scripts and runs no commands. It reads the product marketing context file in your project when present, and returns copy in chat or into the file you name. A [NEED: ...] marker replaces any fact the brief does not supply.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers