antislop-copywriting

Rewrites marketing and product copy to remove AI-writing patterns and fabricated claims.

Updated Jul 2, 2026
One-click install
npx skills add https://github.com/daxrpm/epn-tracker --skill antislop-copywriting-daxrpm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: antislop-copywriting
Source: https://github.com/daxrpm/epn-tracker/tree/main/.claude/skills/antislop-copywriting
Command: npx skills add https://github.com/daxrpm/epn-tracker --skill antislop-copywriting-daxrpm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated prose is easy to spot: buzzwords, forced rule-of-three lists, em dashes, fabricated statistics, and generic upbeat endings. This Skill audits and rewrites copy so it reads like a person wrote it, without inventing facts or stripping the author's voice. ## Core Features & Use Cases - Pattern Detection and Fixes: Identifies and rewrites dozens of AI tells including empty vocabulary, significance inflation, weasel attributions, staccato drama, false ranges, and chatbot closers, each with before/after examples. - Honesty Enforcement: Blocks fabricated numbers, testimonials, names, and speculative gap-filling; every claim must come from the source text or the user. - Voice Calibration: Matches a user-supplied writing sample's sentence length, punctuation, and quirks instead of applying sterile defaults. - Use Case: Paste a landing page draft full of phrases like "unlock seamless collaboration" and "trusted by thousands of teams" and receive a rewrite with specific, evidenced language plus a completed copy checklist. ## Quick Start Rewrite this landing page copy using the antislop-copywriting skill and flag any claims that lack a real source.

Frequently Asked Questions about antislop-copywriting

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make AI-generated copy sound human?▼

Run the draft through the pattern list: replace buzzwords with specific language, remove em dashes, cut forced rule-of-three lists, and name the actor in every sentence. Then read it aloud and check that no fact, number, or quote was invented.

What are the most common signs of AI-written text?▼

Common tells include empty vocabulary like "unlock" and "seamless", significance inflation like "a new era of", fabricated statistics, em dashes, negative parallelism, and generic upbeat conclusions. A single tell means little; clusters of them indicate machine writing.

Can I keep my own writing style when editing AI copy?▼

Yes. Provide a sample of your writing and the skill matches its sentence lengths, vocabulary, and punctuation habits, including em dash frequency. The sample's voice overrides the default style rules.

When should I not flag something as AI writing?▼

Do not flag perfect grammar, formal vocabulary, single em dashes, one short emphatic sentence, or unsourced claims in isolation. These appear in legitimate human writing; only clusters of patterns are reliable evidence.

Does this skill work for non-marketing prose?▼

It targets any prose meant for people to read, including product copy, landing pages, and articles. It is loaded together with the antislop core file, which holds the shared rules and delivery gate it references.