Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/vedangvatsa-antislop-ui-81d68e
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
antislop-ui- Description
- UI and visual skill for antislop. Use when building or editing any interface: color, layout, components, motion. Load with the core.
- License
- MIT
- Allowed tools
- Read, Write, Edit, Glob, Grep
- Instructions
- 293 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
--- name: antislop-ui description: "UI and visual skill for antislop. Use when building or editing any interface: color, layout, components, motion. Load with the core." allowed-tools: Read Write Edit Glob Grep --- # antislop-ui > Anti Slop: Rules for AI Coding Agents. UI & Visual skill > Part of the antislop system. Read together with `antislop.md` (the core). This skill deep-dives the UI/visual concern: color, layout, components, decoration, structural flow, and motion. It references core rules by number and never duplicates or renumbers them. Load it when the task builds or edits a website, web app, or any interface. ## How to use this skill - Load together with `antislop.md` whenever the task is UI or visual work. The core holds the mechanism (the purpose test, the three tiers, the Delivery Gate); this skill holds UI-specific depth. - Every entry has the same shape: **Tell** (the pattern), **Why** (why it reads as slop), **Fix** (what to do instead), with the governing core rule cited as R-XX. - The Delivery Gate in the core remains the gate. The "UI Skill Checklist" at the end of this file is the UI-specific supplement to run alongside it. ## Visual & Color ### Generic Blue-Purple Gradient - **Tell:** blue-to-purple, blue-to-cyan, or purple-to-pink gradients used as the primary color treatment, or a full-page colored glow. - **Why:** the most over-represented color treatment in training data. It signals "no brand identity", not "our palette", and marks the design as AI-generated at a glance. - **Fix:** pull the palette from `DESIGN.md` or the product's own identity. Keep a gradient only as a hierarchy function with the reason written down (R-01). A gradient separating one level from another is craft; the same gradient on every section is a default. - **The same default family:** harsh or rainbow gradients, purple-and-black schemes, neon or pastel palettes, and blurred radial orbs behind the hero. They are the same tell wearing different clothes: color from the model's default, not from the brand. All of them are FORBIDDEN as defaults without purpose (R-01). ### Excessive Glassmorphism - **Tell:** blur/backdrop-filter on the navbar, cards, modals, and sidebar at the same time. - **Why:** blur removes texture and sits every surface in the same frosted layer, flattening hierarchy. When every surface is glass, nothing is foreground. - **Fix:** treat glass as an accent, not a character trait. Dose cap: at most 1-2 elements (R-10). The surface that needs the attention gets the glass; everything else stays solid. ### Excessive Border Radius - **Tell:** every element is pill-shaped: buttons, inputs, cards, badges, modals. - **Why:** uniform pill shapes erase the visual language of "this is an input, this is a card". Radius becomes decoration instead of a hierarchy tool. - **Fix:** set a small set of radii in the design system and apply them deliberately (R-11). One generous radius on the primary CTA reads as intentional; the same radius on every element reads as a default. ### Overly Soft Shadows - **Tell:** every component carries a large shadow, so the whole page feels like it is floating. - **Why:** when everything is elevated, elevation communicates nothing. The page loses its ground plane and becomes generic softness. - **Fix:** use shadow as an elevation marker only, and write the elevation reason down (R-12). Most elements should sit flat; the one or two that need to lift above the page carry the shadow. ### Glow Everywhere - **Tell:** glow on cards, buttons, icons, badges, backgrounds, and borders simultaneously. - **Why:** glow is an attention amplifier. Applied everywhere it amplifies nothing, and it is one of the fastest ways to look "made by AI". - **Fix:** reserve glow for a maximum of 1-2 important elements as a focus accent (R-13). Everything else stays matte. ### Background Grid - **Tell:** grid squares, blueprint lines, graph paper, dot grids, or thin repeating lines behind content. - **Why:** it is a default way to make a flat page feel "technical" without doing any real work. It reads as texture without intent. - **Fix:** use texture or pattern only when it genuinely supports the product's identity, with the reason written down (R-07). A real identity motif (core Part 3) beats a stock grid every time. ### Dark Mode Default for No Reason - **Tell:** the whole page is dark simply because it looks "tech", with no branding consideration. - **Why:** dark is a decision, not a default. Forcing it reads as following a trend, not serving the product. - **Fix:** choose the theme from brand identity, product type, and audience (R-21). Developer and creative tools have legitimate reasons for dark; a content-first product usually does not. If there is no strong reason for a fixed theme, build a working light/dark toggle. ### Too Many Colors in the Palette - **Tell:** 5-7 different colors on one page with no clear design system. - **Why:** a scattered palette has no hierarchy. When every element can be any color, nothing is distinguished. - **Fix:** cap the active palette at 2-3 core colors + 1 accent (R-29), and let one of the cores be the neutral base. Restraint is what makes the accent land. ### Excessive Accent Color - **Tell:** one accent color on buttons, icons, badges, links, lines, backgrounds, and glows at once. - **Why:** the accent stops being an accent the moment it is everywhere. It becomes just another color, and the design loses its focal point. - **Fix:** the accent belongs at the key moment only (one deliberate accent, core Part 3). Zero accents is sterile; an accent everywhere is slop. Choose the one or two places it matters. ### Sterile Default - **Tell:** flat white or near-white, thin grey borders, small radius, no texture, generic font, no identity. - **Why:** this is the "safe" result of over-filtering without direction. It is not slop, but it is not design either: it is a void where a design should be. - **Fix:** this is a direction problem, not a filter problem. Add `DESIGN.md` or resolve the Design Read (core Part 3), then raise the liveliness dials. The fix is never more bans; it is state the purpose and add energy. ## Layout & Components ### Monotonous Template Layout - **Tell:** hero, subtitle, 2 CTAs, screenshot, feature grid, testimonials, FAQ, CTA, footer, in that order, every time. - **Why:** the order is the training-data default, not the product's narrative. Sections appear because the template has them, not because the content needs them. - **Fix:** build the structure around actual content needs (R-05, C-3). If the product has no testimonials, there is no testimonials section. Section order follows the product's story. Match the RHYTHM dial: if it is 3, sections visibly vary. ### Copy-Paste Feature Cards - **Tell:** identical size, height, icon, layout, and padding across all feature cards. - **Why:** uniform cards flatten the content. When every feature is a card with an icon, the features with real weight and the ones without look the same. - **Fix:** create variation that reflects content hierarchy, with the reason written down (R-14). Not every feature needs to be a card. The flagship feature may deserve a full-width treatment, the supporting ones a list. ### Bento Grid - **Tell:** a section made of a mosaic of differently-sized cards, some spanning two columns or two rows, filling the space like a tiled dashboard. - **Why:** it is the default "app-like" landing layout of the last few years, so it signals nothing about the product. When every section could be a bento, the layout is a template, not a decision. - **Fix:** use a bento grid only when the content genuinely has elements of different sizes to show (R-05). If every cell is roughly the same, a simple grid or list is more honest. The RHYTHM dial decides whether sections vary at all. ### Uniform Spacing - **Tell:** padding, margin, and gaps are identical across every section. - **Why:** rhythm is a tool, and a single spacing value removes it. Sections stop relating to each other; the page reads as one flat strip. - **Fix:** use whitespace as structure (core Part 3) and vary it with the RHYTHM dial. Establish a spacing scale, then use different levels to separate and connect. Uniform rhythm is a deliberate choice only when the dial says so (R-05). ### "How It Works" Always 3 Steps - **Tell:** round icon + number 1, 2, 3 + short text, always three steps, always the same shape. - **Why:** the product's real process is rarely a tidy three-step list. The template forces the process into its shape, not the other way around. - **Fix:** present the process as it actually is (R-05). Three steps with round icons is fine if that is genuinely the process; otherwise use whatever shape the real workflow takes, including two steps or five. ### "Trusted By" Logo Bar - **Tell:** a row of generic company logos directly below the hero. - **Why:** it is a trust claim with no evidence: generic logos, no real customers named, no proof of use. - **Fix:** only show real, verifiable logos (R-18, R-36, C-5). If the product has no such customers yet, do not fabricate a logo bar. Real social proof beats a generic one every time. ### "Most Popular" Pricing Card
From vedangvatsa/Web3-Jobs, MIT.
More from vedangvatsa/Web3-Jobs
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 4, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/vedangvatsa/Web3-Jobs
- Website
- web3-jobs-seven.vercel.app
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.582score
antislop-ui
SeriousJul
UI and visual skill for antislop.
SkillAFreshness: A★ 1Claude Code +9 - 0.339score
antislop-ui
Hadi-Akram-Ramadhan
UI and visual skill for antislop.
SkillAFreshness: AClaude Code +9 - 0.339score
antislop-ui
Hadi-Akram-Ramadhan
UI and visual skill for antislop.
SkillAFreshness: AClaude Code +9 - 0.339score
antislop-ui
terenceooi99
UI and visual skill for antislop.
SkillAFreshness: AClaude Code +9 - 0.315score
antislop-ui
vedangvatsa
UI and visual skill for antislop.
SkillBFreshness: BClaude Code +9 - 0.315score
antislop-ui
vedangvatsa
UI and visual skill for antislop.
SkillBFreshness: BClaude Code +9
More from vedangvatsa
- 0.557score
veda-research-hub
vedangvatsa
Search 50+ long-form essays, 100+ AI and Web3 glossary definitions, and 233,000+ academic papers via OpenAlex from veda.ng.
SkillAFreshness: AClaude Code +9 - 0.521score
antislop-layoutmobile
vedangvatsa
Mobile layout skill for antislop.
SkillBFreshness: BClaude Code +9 - 0.513score
veda-research-hub
vedangvatsa
Search Vedang Vatsa's essays, AI and Web3 glossary definitions, and OpenAlex-backed academic research via veda.ng.
SkillBFreshness: BClaude Code +9
Cite this page
antislop-ui skill. Agent Mart. https://agentmart.dev/skills/vedangvatsa-antislop-ui-81d68e (last updated 2026-10-24)