Rules for an AI coding agent to filter out generic AI-generated UI designs, text, and code.
# Add to your Claude Code skills
git clone https://github.com/miqdadbadjuber/anti-slopLast scanned: 9/22/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-09-22T09:02:28.306Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how anti-slop compares with popular alternatives.
anti-slop is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by miqdadbadjuber. Rules for an AI coding agent to filter out generic AI-generated UI designs, text, and code. It has 5,813 GitHub stars.
Yes. anti-slop passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/miqdadbadjuber/anti-slop" and add it to your Claude Code skills directory (see the Installation section above).
anti-slop is primarily written in JavaScript. It is open-source under miqdadbadjuber on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh anti-slop against similar tools.
No comments yet. Be the first to share your thoughts!
Based on votes and bookmarks from developers who liked this skill
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
See comparison
The same brief, built four ways. antislop filters and DESIGN.md supplies direction. They are different jobs, and these are the four results.
| Nothing at all | antislop alone | DESIGN.md alone |
|---|---|---|
| Where most AI output starts: a sparkle logo, a beta pill, and a fake terminal. | Honest, because the filter removed the invented numbers. Plain, because beauty is not its job. | The direction lands, but the slop stays, because DESIGN.md directs and does not filter. |
The fourth is the only one of the four that is clean and directed at the same time:
antislop + DESIGN.md |
|---|
Honest numbers and a real direction in the same build. The filter removes what should not be there; DESIGN.md fills the space that leaves, which is the one thing neither manages alone. |
One prompt, run twice.
| Before | After |
|---|---|
One file, run twice.
| Before | After |
|---|---|
Every image here opens full size if you click it.
antislop ships as standard agent skills: one folder per skill, holding a SKILL.md. Installation differs per agent, so pick the section for the one you use. Each route is walked through from zero, with update and removal, in GUIDE.md.
One command, then answer the prompts. It asks which skills you want, where to install them (this project or everywhere), and which agents you use, then copies the folders and writes the pointer that reloads antislop every session.
npx antislop-ai
antislop is listed on skills.sh, the open directory for agent skills. This copies the same folders as the installer and nothing else, so antislop reloads by description alone.
npx skills add miqdadbadjuber/anti-slop
/plugin marketplace add https://github.com/miqdadbadjuber/anti-slop
/plugin install antislop@anti-slop
agy plugin install https://github.com/miqdadbadjuber/anti-slop
codex plugin marketplace add miqdadbadjuber/anti-slop
codex plugin add antislop@anti-slop
agent plugin marketplace add https://github.com/miqdadbadjuber/anti-slop
Then open Customize, find antislop, and select Install.
/plugins install https://github.com/miqdadbadjuber/anti-slop
cline plugin install https://github.com/miqdadbadjuber/anti-slop.git
This door covers the Cline CLI. For the VS Code or JetBrains extension, use the installer.
omp plugin marketplace add miqdadbadjuber/anti-slop
omp plugin install antislop@anti-slop
pi install git:github.com/miqdadbadjuber/anti-slop
antislop.md on its own is a complete filter you can paste into any chat window, with no packaging and no folders.
curl -o antislop.md https://raw.githubusercontent.com/miqdadbadjuber/anti-slop/main/antislop.md
The core prevents slop but cannot invent direction. DESIGN.md (yours) supplies it, and a sterile result means the direction was missing, not that the filter failed (R-37). antislop never beautifies on its own.
| Skill | Covers | Pick it for |
|---|---|---|
| antislop | The core filter: rules, tiers, the Delivery Gate, liveliness | Everything. Always loaded |
| antislop-ui | Layout, color, components, decoration, motion, structure | UI and visual work |
| antislop-copywriting | Headlines, CTAs, tone, fake stats, anti-AI writing, markdown hygiene | Copy and text |
| antislop-human | Contrast, keyboard, focus, states | Accessibility |
| antislop-layoutmobile | Reflow across screen widths, breakpoints, grids, overflow, tap targets | Responsive work |
| antislop-code | AI-slop comments: which to remove, which to keep | Comment cleanup |
Install one, several, or the core alone.
antislop runs one of two ways, and by default the agent asks which at the start of every session. Both end with a report you can check; they differ in when the rules apply.
Saving a preference is opt-in. With no settings file, antislop keeps asking in every new session exactly as it does today. Save your preferred mode once to skip that question:
npx antislop-ai --mode during
Use after instead for audits, ask to restore the question in every session, or --mode alone to view the setting. The file is shared, so one command covers every agent and every project: ~/.config/antislop/settings.json on Linux and macOS, %APPDATA%\antislop\settings.json on Windows.
A mode you ask for in the current chat always wins for that session and never changes what is saved. When a saved preference applies, the skill says so once: "antislop active: during (global preference)." Older installs still carry the unconditional question, so run the update below to pick this up.
antislop does not update itself. If you installed through the installer, one command replaces what is already there, in this project and under your home directory, and prints the release it replaced:
npx antislop-ai --update
A plugin keeps its own copy under the agent that installed it, so it updates through its own command, and the Pi package updates through Pi. Every route is listed in GUIDE.md. Skills load when a session starts, so start a new one afterwards.
Is antislop a style guide? No, a filter. It rejects technique without purpose and requires liveliness. Direction is yours.
Which agents does it work with? Claude Code, Codex, Antigravity, OpenCode, Cursor, Cline, Amp, Gemini CLI, Hermes, GitHub Copilot, Kimi Code, Pi, and Oh My Pi. The installer covers twelve of them and detects which ones you have, and the plugin doors install from this same repository. GUIDE.md lists the folder each agent reads.
What is a skill?
A folder that goes deeper into one concern, holding a SKILL.md with its rules. Skills reference the core rules by number and never duplicate them, so adding one does not change the core.
v3.2.20