wpgaurav/claude-code-skills

Opinionated Claude Code Agent Skills for fighting AI slop in design, code, and copy. stop-slop, red-pen, clarify, distill, quieter, polish, harden.

3Stars on the repository
8Mods indexed here, across every type
13d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

clarify

01

wpgaurav/claude-code-skills

Skill Claude CodeCodex

Improve unclear UX copy, error messages, microcopy, labels, and instructions. Makes interfaces easier to understand and use.

3 13d ago A 27 tokens copy · 86% MIT

distill

02

wpgaurav/claude-code-skills

Skill Claude CodeCodex

Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean.

3 13d ago A 23 tokens copy · 89% MIT

harden

03

wpgaurav/claude-code-skills

Skill Claude CodeCodex

Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready.

3 13d ago A 32 tokens copy · 94% MIT

polish

04

wpgaurav/claude-code-skills

Skill Claude CodeCodex

Final quality pass before shipping. Fixes alignment, spacing, consistency, and detail issues that separate good from great.

3 13d ago A 26 tokens copy · 89% MIT

quieter

05

wpgaurav/claude-code-skills

Skill Claude CodeCodex

Tone down overly bold or visually aggressive designs. Reduces intensity while maintaining design quality and impact.

3 13d ago A 22 tokens copy · 89% MIT

red-pen

06

wpgaurav/claude-code-skills

Skill Claude CodeCodex

A strict editorial reviewer that checks writing principles inspired by George Orwell's "Politics and the English Language" rules and Matthew Butterick's Practical Typography. Use this skill whenever the user says "red pen", "check my prose", "edit this for clarity", "typography check", "tighten this up", "review this…

3 13d ago A 147 tokens original MIT

slop-detector

07

wpgaurav/claude-code-skills

Skill Claude CodeCodex

Score a draft, page, or caption set for AI slop with a four-tier severity model instead of a flat banned-words list. Exact production narration fails outright, rhetorical scaffolds warn only when repeated, lexical tells become review prompts, and document-level patterns are diagnosed. Use when the user asks to score…

3 13d ago A 96 tokens original MIT

stop-slop

08

wpgaurav/claude-code-skills

Skill Claude CodeCodex

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

3 13d ago A 26 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: