Skip to content
cui-marketplace-architecture logo

CUI Marketplace Architecture Skill

cui-marketplace-architecture

Architecture rules and validation patterns for Claude Code marketplace components ensuring self-contained skills, proper skill usage, and clean reference patterns

SKILL.md

Full skill instructions

CUI Marketplace Architecture Skill

Standards for marketplace component architecture ensuring self-contained skills, proper skill usage in agents/​commands, clean reference patterns, and bundle organization principles.

Workflow

Step 1: Load Architecture Standards

CRITICAL: Load all architecture standards based on validation context.

  1. Always load core architecture rules:

    Read: standards/​architecture-rules.md
    Read: standards/​reference-patterns.md
    

    These provide fundamental marketplace architecture principles always needed.

  2. Conditional loading based on context:

    • If validating skills for self-containment:

      Read: standards/​self-containment-validation.md
      
    • If validating agents/​commands for skill usage:

      Read: standards/​skill-usage-patterns.md
      
    • If calculating compliance scores:

      Read: standards/​scoring-criteria.md
      

Step 2: Apply Architecture Rules

When to Execute: During component creation or validation

What to Validate:

  1. Skill Self-Containment:

    • All standards content in skill's standards/ directory
    • No external file references (../​../​../​../)
    • No absolute paths (~/​git/​cui-llm-rules/)
    • Only external URLs and skill references allowed
  2. Agent/​Command Skill Usage:

    • Agents using standards must invoke Skills
    • Skill tool in tools list if invoking skills
    • No direct standards file references
    • Proper skill invocation pattern in workflow
  3. Reference Pattern Compliance:

    • Categorize all references (internal/​external/​skill)
    • Validate allowed patterns only
    • Report prohibited patterns with fixes
  4. Bundle Architecture Compliance:

    • All bundle skills self-contained
    • All bundle agents use skills properly
    • Bundle follows cohesion principles
    • Components properly organized

Step 3: Calculate Compliance Scores

When to Execute: After validation

Scoring Logic:

  1. Skill Self-Containment Score (0-100):

    • Base: 100 points
    • Deduct 20 points per external file reference
    • Deduct 10 points per documentation-only external ref
    • Minimum: 0
  2. Agent Skill Usage Score (0-100):

    • Only if agent uses standards
    • Base: 100 points
    • Deduct 30 points if missing Skill in tools
    • Deduct 30 points if no Skill: invocations
    • Deduct 20 points per direct file reference
  3. Bundle Architecture Score:

    • Weighted average: Skills 60%, Agents 30%, Commands 10%

Step 4: Generate Fix Recommendations

When to Execute: After detecting violations

Fix Strategies:

  1. Internalize External Content:

    • Copy external files to skill/​standards/
    • Convert .adoc to .md if needed
    • Update references to internal paths
  2. Convert to Skill Usage:

    • Add Skill to agent tools list
    • Replace direct refs with Skill: invocations
    • Remove obsolete Read: statements
  3. Remove Documentation Links:

    • If reference only in ## References section
    • If not actually loaded in workflow
    • Replace with external URL if available

Common Validation Patterns

Pattern 1: Validate Skill Self-Containment

# Scan for external references
grep -E "(\.\.){3,}|~/​git/​cui-llm-rules" skill/​SKILL.md

# Should return nothing for compliant skill

Pattern 2: Check Agent Skill Usage

# If agent uses standards
grep -i "standard\|pattern" agent.md

# Then verify uses Skill
grep "Skill:" agent.md
grep "tools:.*Skill" agent.md

Pattern 3: Categorize References

In ## References section:
✅ https://external-url.com (allowed)
✅ Skill: cui-other-skill (allowed)
✅ standards/​internal.md (allowed)
❌ ../​../​../​../​standards/​external.adoc (prohibited)

Quality Verification

All marketplace components must pass:

  • Skills are self-contained (no external refs)
  • Agents use Skills (not direct refs)
  • Only allowed reference patterns used
  • Bundle architecture follows design principles
  • All standards content internalized

References

  • Claude Code Plugin System: https://docs.claude.com/en/docs/claude-code/plugins
  • Architecture rules: standards/​architecture-rules.md
  • Reference patterns: standards/​reference-patterns.md
  • Self-containment validation: standards/​self-containment-validation.md
  • Skill usage patterns: standards/​skill-usage-patterns.md
  • Scoring criteria: standards/​scoring-criteria.md

More Productivity & Planning skills

brainstorming logo
Productivity & Planning

brainstorming

Structured design dialogue that validates ideas before implementation begins.

295.4K 385.7K
View
ui-ux-pro-max logo
Productivity & Planning

ui-ux-pro-max

Comprehensive design intelligence for web and mobile UI/UX across 10 technology stacks.

133.1K 383.9K
View
writing-plans logo
Productivity & Planning

writing-plans

Comprehensive implementation plans for multi-step tasks, breaking down specs into bite-sized, testable steps.

295.4K 268K
View
using-superpowers logo
Productivity & Planning

using-superpowers

Introduction to the obra skills system with mandatory skill invocation rules and best practices.

295.4K 259.8K
View
executing-plans logo
Productivity & Planning

executing-plans

Execute a written implementation plan with critical review and task checkpoints.

295.4K 229.1K
View
dispatching-parallel-agents logo
Productivity & Planning

dispatching-parallel-agents

Delegate independent tasks to specialized agents working concurrently with isolated context.

295.4K 206.3K
View
using-git-worktrees logo
Productivity & Planning

using-git-worktrees

Isolated git worktrees with smart directory selection and safety verification.

295.4K 205.2K
View
webapp-testing logo
Productivity & Planning

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

179.7K 170.6K
View
content-strategy logo
Productivity & Planning

content-strategy

Plan searchable and shareable content that drives traffic, builds authority, and generates leads.

53.3K 150.9K
View
repo-intake-and-plan logo
Productivity & Planning

repo-intake-and-plan

README-first repository scanner that extracts commands and classifies reproduction candidates without executing them.

497 139.6K
View
marketing-ideas logo
Productivity & Planning

marketing-ideas

Brainstorm and prioritize marketing strategies tailored to your SaaS stage, budget, and goals.

53.3K 137.2K
View
site-architecture logo
Productivity & Planning

site-architecture

Plan and optimize your website's page hierarchy, navigation, URL structure, and internal linking.

53.3K 112.8K
View

Productivity AI tools

Vimcal logo
Productivity

Vimcal

The world's fastest calendar for remote work

Free
View
SaveDay logo
Productivity

SaveDay

Capture, organize, and utilize your knowledge effortlessly.

Free
View
Any Summary logo
Productivity

Any Summary

Instant Summaries of Audio & Video Interviews with AnySummary

Freemium
View
M
Productivity

Map This

Transform PDFs into engaging mind maps.

Freemium
View
ChatPDF logo
Productivity

ChatPDF

Chat with any PDF instantly

Free
View
I
Productivity

intellisay

Create an optimal daily plan using your voice

Paid
View
A
Productivity

Aurora AI

A productivity platform to centralize organizational knowledge and workflows with contextual AI assistance.

Paid
View
AskYourPDF logo
Productivity

AskYourPDF

AskYourPDF Pricing Plans: Tailored to Your Needs

Free
View