Anti Pattern logo

Anti Pattern

Community
Omar-Obando
anti-pattern

Anti-pattern detection and prevention skill. Catches hardcoded data, non-functional UI elements, placeholder code, N+1 queries, and other common development anti-patterns before they ship.

Overview

PublisherOmar-Obando
Repositoryqwen-orchestrator
Skill nameanti-pattern
Stars
53
Forks
13
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Omar-Obando on GitHub. Read the source before you install it.

Installation

Install the Anti Pattern AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Omar-Obando/qwen-orchestrator/tree/main/skills/anti-pattern
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Omar-Obando/qwen-orchestrator.git /tmp/qwen-orchestrator
mkdir -p .claude/skills
cp -r /tmp/qwen-orchestrator/skills/anti-pattern .claude/skills/anti-pattern
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Anti Pattern in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Anti Pattern on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Anti Pattern is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Anti-Pattern Skill — Ship Real Code, Not Decorations

This skill detects and prevents the most common anti-patterns that make software look unfinished or unprofessional.

Banned Anti-Patterns (ZERO TOLERANCE)

UI/UX Anti-Patterns

❌ BANNED:
- "Coming Soon" sections or labels
- Non-functional buttons (must work or be removed)
- Forms that don't submit anywhere
- Hardcoded fake data in production components
- Static tables pretending to be dynamic
- Links that go nowhere (href="#")
- "Under Construction" banners
- Feature flags permanently set to false
- Disabled inputs without clear explanation
- Empty states without helpful messaging
- Pagination that doesn't actually paginate
- Search bars that don't actually search
- Filters that return the same results
- SINGLE LANDING PAGE when user asks for "a website" (MUST be multi-page)
- No color palette defined before writing CSS
- Random hex colors without a documented design system
- Inconsistent colors across pages (different blues, different spacing)
- EMOJIS anywhere in the website (use SVG icons from Lucide/Heroicons/Phosphor)
- Sections touching each other (no spacing between content blocks)
- Footer stuck directly to the section above (no breathing room)
- Navigation with more than 7 top-level items (cluttered, overwhelming)
- Service pages without individual detail pages (/services only, no /services/web-design)
- Product pages without individual detail pages (/products only, no /products/[slug])
- Generic service descriptions (2-3 lines per service is NOT enough)

✅ REQUIRED:
- Every visible button triggers a real handler or is removed
- Every form has a real onSubmit connected to an API call
- Every list loads from a real data source with loading states
- Every link navigates to a real destination
- Empty states explain why and suggest next actions
- Error states show real error messages from the server
- Loading states appear during real async operations
- Multi-page website with separate routes (Home, About, Services, Contact, Products)
- Professional 6-color palette (--color-primary, secondary, accent, bg, surface, text)
- Consistent design system across ALL pages
- ZERO emojis — use SVG icons (Lucide, Heroicons, Phosphor)
- Section spacing: minimum 80px padding between sections
- Footer: minimum 128px top padding (never touching content above)
- Navigation: max 7 items, dropdowns for groups, secondary links in footer
- Services: listing page + individual detail pages per service
- Products: listing page + individual detail pages per product
- Each service detail: description, process, deliverables, pricing, FAQ, CTA
- Each product detail: gallery, specs, pricing, reviews, related products

Website Architecture Anti-Patterns

❌ BANNED (when user says "build a website"):
- Creating index.html as the ONLY file
- Putting all content in one scrollable page
- Using anchor links (#about, #services) instead of separate pages
- Calling it a "website" when it's just a landing page
- No navigation menu between sections/pages
- No shared header/footer across pages
- No unique meta title/description per page

✅ REQUIRED:
- Separate route/page for each section (e.g., /about, /services, /contact)
- Navigation menu linking all pages
- Shared header + footer components
- Each page has unique <title> and <meta description>
- Consistent color palette and typography across ALL pages
- Minimum 5 pages for any "website" request (Home, About, Services, Products/Portfolio, Contact)

Code Anti-Patterns

❌ BANNED:
- return []; // TODO: implement
- throw new Error('Not implemented');
- // placeholder
- Hardcoded arrays pretending to be API responses
- Functions with empty bodies
- Catch blocks that silently swallow errors
- Commented-out code in production
- Magic numbers without named constants
- Copy-pasted code (DRY violation)
- God functions (>100 lines)
- Deeply nested callbacks (>3 levels)
- N+1 database queries in loops

✅ REQUIRED:
- Every function has real, working implementation
- Every error is properly handled with user feedback
- Constants are named and documented
- Code is DRY — extract shared logic
- Functions are focused and under 40 lines

N+1 Query Detection

❌ BANNED (N+1):
// This fires 1 query per user = N+1 problem
for (const user of users) {
  const orders = await db.query('SELECT * FROM orders WHERE user_id = ?', [user.id]);
}

✅ REQUIRED (Batch):
// This fires 1 query total
const userIds = users.map(u => u.id);
const orders = await db.query(
  'SELECT * FROM orders WHERE user_id IN (?)',
  [userIds]
);
// Then group in memory
const ordersByUser = groupBy(orders, 'user_id');

SQL Anti-Patterns

❌ BANNED:
SELECT * FROM users                    -- No SELECT *
WHERE name LIKE '%" + input + "%'     -- SQL injection
ORDER BY RAND()                        -- Performance killer
HAVING COUNT(*) > 0                    -- Use WHERE instead
WHERE YEAR(created_at) = 2024          -- Breaks index usage

✅ REQUIRED:
SELECT id, name, email FROM users      -- Explicit columns
WHERE name LIKE ?                      -- Parameterized
ORDER BY id DESC LIMIT 20              -- Deterministic sort
WHERE created_at >= '2024-01-01'       -- Index-friendly
  AND created_at < '2025-01-01'

Verification Checklist

Before ANY deliverable is marked complete:

General

  • No "coming soon" or "under construction" anywhere
  • All buttons are functional or removed
  • All forms submit to real endpoints
  • All lists load from real data sources
  • No hardcoded demo data in production paths
  • No N+1 queries (check every loop with a query)
  • No TODO comments without issue references
  • Error states handle real errors
  • Loading states show during real operations

Design & UI Anti-Patterns

  • Zero emojis anywhere in the website (use SVG icons only)
  • Sections have minimum 80px padding between them (no touching)
  • Footer has minimum 128px top padding (not stuck to content)
  • Main navigation has max 7 top-level items
  • Secondary links in footer, not main nav
  • Services have individual detail pages (not just a listing page)
  • Products have individual detail pages (not just a listing page)
  • Each service detail has: description, process, deliverables, CTA
  • Each product detail has: gallery, specs, pricing, reviews
  • Alternating section backgrounds for visual separation

SEO Anti-Patterns (for website projects)

  • No page without a unique <title> and <meta name="description">
  • No page without Open Graph tags (og:title, og:description, og:image)
  • No page without JSON-LD structured data (<script type="application/ld+json">)
  • No non-home page without BreadcrumbList schema
  • No duplicate JSON-LD blocks (use @id references instead)
  • No missing robots.txt or sitemap.xml
  • No images without alt text
  • no page without canonical URL
  • No missing <html lang="xx"> attribute
  • No page with more than one <h1>

When NOT to Use

Do NOT use this skill when:

  • Performing general code quality reviews (use code-review skill for broader analysis)
  • Designing database schemas (use database-design skill for schema planning)
  • Writing application business logic (use domain-driven skill for complete modules)
  • Reviewing API endpoint implementations (use api-design skill for endpoint patterns)
  • Performing security audits (use security-auditor skill for vulnerability analysis)
  • Analyzing deployment configurations (use deployment skill for CI/CD pipelines)
  • Reviewing git workflows or version control (use git-workflow skill for branching/commits)
  • Writing SQL queries (use sql-best-practices skill for query optimization)
  • Designing multi-page website layouts (use design-system skill for professional UI/UX)
  • Reviewing existing code for refactoring needs (use refactoring skill for safe transformations)

Frequently asked questions

What does the Anti Pattern AI skill do?

Anti-pattern detection and prevention skill. Catches hardcoded data, non-functional UI elements, placeholder code, N+1 queries, and other common development anti-patterns before they ship.

Why use Anti Pattern on TypingMind?

Because you install it once and use it with any model. Anti Pattern is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Anti Pattern in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Omar-Obando/qwen-orchestrator/tree/main/skills/anti-pattern. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Anti Pattern?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Anti Pattern?

As many as you like. As long as a model supports skills, you can use Anti Pattern with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Anti Pattern AI skill free?

Yes. It is published on GitHub by Omar-Obando under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇