Anti-slop filter for AI coding agents: rules against generic AI-looking UI and copy
Load-always filter that rejects technique-without-purpose UI — 38 mandatory rules (hard gates, purpose gates, quality locks), two usage modes (during/after), plus install wizard and per-concern sub-skills
- What
- Load-always filter that rejects technique-without-purpose UI — 38 mandatory rules (hard gates, purpose gates, quality locks), two usage modes (during/after), plus install wizard and per-concern sub-skills
- Cost
- Free
- Needs
- an AI coding agent setup where you build UI, copy, or code comments — the skill is a rules filter the agent reads, not software to install
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @miqdadbadjuber's anti-slop filter for AI coding agents: a rules system loaded always to stop generic, recognizable AI-slop output before it ships. Part 1 is a diagnostic scan of the telltale patterns (generic blue-purple gradients, excessive glassmorphism, monotonous hero→CTAs→feature-grid layouts, em dashes, generic CTAs, AI buzzwords, fake statistics, fabricated trust claims, Lucide-icon-everywhere). Part 2 is the meat — 38 mandatory rules in three tiers: Hard Gate (absolute — no em dashes in agent copy, mobile must be perfect, no fabricated numbers or testimonials, no dead interactive elements, required empty/loading/error states, WCAG AA contrast, keyboard navigability, no building features via CSS-patch scripts, design direction required before building), Purpose-Gate (color, gradients, icons, typography, badges, glassmorphism, glow, animations, illustrations are allowed only with a stated purpose, written down, with dose caps), and Quality Locks (no template layouts, max 2-3 core colors plus 1 accent, every decision must have a one-line reason). Part 3 adds liveliness: three dials every design must set (ENERGY, RHYTHM, MOTION) and a Design Read declaration. Two usage modes — during (rules applied while building, ending in a Delivery Gate PASS/FAIL report) or after (numbered audit of an existing project, fix only approved findings). Ships with a first-run install wizard (pointer block in AGENTS.md/CLAUDE.md/GEMINI.md, per-concern sub-skills antislop-ui, antislop-copywriting, antislop-human, antislop-layoutmobile, antislop-code, user fetches the files, the agent never downloads them itself) and update instructions per agent platform. MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Anti-slop is a free Muse skill that filters AI coding output against generic, recognizable AI-looking UI and copy, loaded always so slop never ships. Part one is a diagnostic scan of telltale patterns, from generic blue-purple gradients and excessive glassmorphism to monotonous hero-to-feature-grid layouts, em dashes, generic calls to action, AI buzzwords, fake statistics and fabricated trust claims.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 388cbe3Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: an AI coding agent setup where you build UI, copy, or code comments — the skill is a rules filter the agent reads, not software to install Install "Anti-slop filter for AI coding agents: rules against generic AI-looking UI and copy" for me. It gives my agent @miqdadbadjuber's anti-slop system: a diagnostic scan of AI-slop patterns, 38 mandatory rules (hard gates like no fabricated claims and no dead interactive elements, purpose gates with written reasons and dose caps for gradients/icons/glassmorphism/animations, quality locks like no template layouts and a max-3-color palette), liveliness dials (ENERGY/RHYTHM/MOTION) plus a Design Read, and two usage modes — during (apply while building, end with a Delivery Gate PASS/FAIL report) or after (numbered audit, fix only approved findings). MIT-licensed. Repository: https://raw.githubusercontent.com/miqdadbadjuber/anti-slop/388cbe3b6c37d5175b9f460015bb092ef9e34894/skills/antislop/SKILL.md Pinned version: install the code at commit 388cbe3b6c37d5175b9f460015bb092ef9e34894 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). Review the files for suspicious commands or credential handling; stop on any red flag and never assume the repository is safe. Tell me if anything looks off. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "antislop". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. run the first-run wizard steps: pick sub-skills and the during/after mode; note the pointer block is appended to the agent's entry file — AGENTS.md, CLAUDE.md or GEMINI.md — at next session start). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 388cbe3 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.