去AI味 skill for Codex: a compact Chinese AI writing humanizer for AI味清理, template sentence shells, and fake engagement endings.

CLI for detecting slop smell

Design intelligence engine for AI coding tools (Claude Code, Cursor, Windsurf). Deterministic anti-AI-slop linter with 152 rules, 160 brand specs, a 7-axis synthesizer, an MCP server (18 tools), 25 commands, 17 IDEs. Offline, never calls an LLM. MIT.

PencilPlaybook is the UI Skills / Taste-Skill for Pencil.dev + Claude Code — a design playbook that gives Claude real perceptual psychology and senior-level guardrails so it stops producing averaged-out AI slop.

🚫 Stop AI slop in Chinese writing. 干掉中文 AI 味 — banned words, punctuation rules, structure constraints & 4-layer QA. Works with Claude Code, Cursor, Codex CLI.

50,000+ unique HTML presentation designs. Zero dependencies. Anti-AI-slop. A Claude Code skill.

Pravidla, díky kterým AI píše český text jako člověk a nikoliv jako AI generátor. Krátký prompt do AI chatu, plný průvodce a skill pro AI agenty (Claude Code, Codex, Cursor).

Universal AI writing skill — tech articles, marketing copy, research reports, Xiaohongshu notes, technical docs. Research-driven, full-pipeline, anti-AI-slop. Bilingual (EN/ZH).

A Claude Code skill that strips AI slop from text. 35 patterns detected. No mercy, no fluff.

Claude Code skill for designing landing pages and portfolios that look human-crafted — custom icons, 2D illustrations, shader effects, no AI slop.

🌸 AI 前端 UI 生图 Skill · 三位一体跨模态系统 (image-2 × MCP × prompt engineering) for Claude Code / Cursor / Windsurf

A site made to protect creative comunities from AI slop bros.

The Claude Code plugin for award-tier expressive web design. SvelteKit + Astro, anti-AI-slop, WCAG 2.1 AA. No shadcn. No Inter. No purple gradients.

A filter that strips AI fingerprints from your writing before you publish. Drop into any LLM workflow (Claude Code, Claude.ai, Gemini Gems, Codex, plain chat). 7 passes catch the tells.

Enforce human-like writing in AI output by blocking banned words, phrases, and patterns that trigger AI detectors

The taste layer for AI agents — a self-contained, source-cited design-system knowledge base + 5 skills that let any AI produce modern (2026), human-feeling, non-AI-slop frontend.

Detect and improve AI slop, generic-output, template-like, and AI-smell patterns across writing, UI, slides, visuals, code, reports, and other artifacts without making authorship claims.

A Claude skill for restrained, production-grade product UI (dashboards, SaaS, settings, tables, forms) that looks shipped, not AI slop — the counterpart to frontend-design.

A Paperclip template for running niche YouTube Shorts channels with anti-AI-slop features: voice rotation, archival image mix, human intro bumper, retention feedback loop

Remove AI patterns and robotic phrasing from your drafts to restore a natural human voice.