antislop

Anti AI Slop: Design & Copy Rules. A rules file for AI coding agents. It stops them from generating generic “AI slop” UI and copy, without letting the result turn sterile. It is a filter, not a style guide: no prescribed colors, fonts, or layouts. It is not only for building pages: it also writes and audits copy, so AI text stops reading like AI. And it never beautifies on its own; DESIGN.md (yours) is where beauty and direction come from.

New here? Start with the guide. It explains what antislop is and how to install it, from zero.

What it does

• 38 mandatory rules (R-01 to R-38) in three tiers: Hard Gate (absolute), Purpose-Gate (technique allowed, reason required), Quality Locks (consistency)
• A Liveliness Toolkit with three dials (ENERGY / RHYTHM / MOTION) and a Design Read, so the result is alive and specific, not just “clean”
• A Delivery Gate: a mandatory PASS/FAIL report in four blocks, run before anything ships
• Additive skills, one per concern, so an agent only loads what a task needs

The core prevents slop but cannot invent direction. DESIGN.md (yours) supplies it; a sterile result means the direction was missing, not that the filter failed (R-37).

Install

antislop is a set of standard agent skills (one folder per skill, SKILL.md) you can install as a package. The core is always loaded; the skills load only for the task at hand. Pick one of these three paths.

1. The picker (recommended). One command, then choose. It shows the antislop banner, lists the skills with the core locked on, and asks for project or global:

npx antislop-ai

2. The skills directory. antislop is listed on skills.sh, the open directory for agent skills:

npx skills add miqdadbadjuber/anti-slop

Add --all for every skill, -g for a global install, or --skill for a single one. Run --list first to see what is available.

skills.sh reads the skill folders straight from this repository, so the listing appears as soon as the repo is live; there is no separate setup step.

3. The plugin (Claude Code). Add the marketplace once, then install the plugin:

/plugin marketplace add https://github.com/miqdadbadjuber/anti-slop
/plugin install antislop@anti-slop

Every skill is a folder of the open Agent Skills standard (/SKILL.md), so it drops into Claude Code (.claude/skills/), Codex (.codex/skills/), Antigravity (.agents/skills/), and any other agent that reads the standard. The picker (path 1) detects which of these agents exist in your project and installs into them; the skills directory (path 2) handles the same agents and more. The plugin (path 3) is the Claude Code door only.

Manual (single file, no packaging). The core antislop.md alone remains a complete filter you can paste into any chat window. Download it and tell your agent to read it; the First-Run wizard inside it installs skills the manual way:

curl -o antislop.md https://raw.githubusercontent.com/miqdadbadjuber/anti-slop/main/antislop.md

Skills

Pick what matches the work: UI work → antislop-ui, copy work → antislop-copywriting, people work → antislop-human, mobile layout work → antislop-layoutmobile, more than one → install several, or none (the core alone is a complete filter).

Usage Modes

antislop is used one of two ways, chosen at the start of a session:

• During guides the work while it is built, ending with the Delivery Gate. Use it when building new UI.
• After audits finished work: a numbered findings list, you approve which to fix, then a follow-up report. Use it to clean up existing output.

Roadmap

v3.0.0 shipped: antislop is packaged as installable skills. See ROADMAP.md. The skill plan that built toward it (one skill per version) is complete; antislop-docs and antislop-identity are candidates for after v3.

FAQ

Is antislop a style guide? No, a filter. It does not prescribe colors, fonts, or layouts. It rejects technique without purpose and requires liveliness; direction is yours.

Which agents does it work with? All of them, but the install paths differ:

• The picker and the skills directory support Claude Code, Codex, and Antigravity (the picker detects each agent’s skill folder; npx skills add handles the same agents and more). These are the recommended paths.
• The plugin is Claude Code only. It is the Claude-specific door.
• The single file (antislop.md) works with any agent that reads plain Markdown: Cursor, Gemini CLI, or a plain chat window.

The packaged skills use the open Agent Skills standard (folder per skill), so they drop into any tool that reads the standard.

What is a “skill”? A folder that goes deeper into one concern (UI, copywriting, accessibility, and so on), holding a SKILL.md with its rules. It references the core rules by number and never duplicates them, so adding a skill does not change the core.

What are DURING and AFTER? The two usage modes: DURING applies the rules while building, AFTER audits finished work. You pick one at the start of a session.

Contributing

Found a new AI slop pattern, a rule that missed something, or a bug in the installer? Open an issue. PRs are welcome for new AI slop patterns, clarifications, or checklist items out of sync with their rule.

License

MIT: LICENSE