This commit adds the full UI/UX Pro Max skill to prevent "file not found" errors
when using the ui-ux-pro-max agent in Claude Code.
Added files:
- skills/ui-ux-pro-max/README.md - Complete skill documentation with:
* 50+ design styles (Glassmorphism, Neumorphism, Claymorphism, Bento Grid, etc.)
* 97 color palettes for different industries
* 57 font pairings (Elegant, Modern, Playful, Professional, Technical)
* WCAG 2.1 AA/AAA accessibility guidelines
* Stack-specific patterns (React, Next.js, Vue, Tailwind, shadcn/ui)
* Anti-patterns to avoid
* Pre-delivery checklist
- skills/ui-ux-pro-max/scripts/search.py - Design knowledge search tool with:
* DESIGN_KNOWLEDGE dictionary with 8 domains
* search_knowledge() function for searching domains
* format_results() function for output formatting
* main() function with argparse CLI interface
* Support for --domain and --stack filters
* Configurable max-results parameter
Tested scenarios:
✓ Product domain search (dashboard, saas, ecommerce, etc.)
✓ Style domain search (glassmorphism, minimalism, etc.)
✓ UX domain search (accessibility, animation, forms, etc.)
✓ Stack-specific search (react, nextjs, vue, tailwind, shadcn)
✓ Max results limiting
✓ No results handling
✓ Help documentation
The skill integrates with /tmp/claude-repo/agents/design/ui-ux-pro-max.md
and provides professional design intelligence for web and mobile interfaces.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Moved 3 scripts that are no longer recommended for installation:
- install-claude-customizations.sh (replaced by interactive installer)
- export-claude-customizations.sh (export utility, not needed for install)
- sync-agents.sh (sync utility, not needed for install)
Users should use interactive-install-claude.sh or MASTER-PROMPT.md instead.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add complete Docker testing infrastructure to validate all 3 installation methods
Features:
- Dockerfile: Ubuntu 22.04 with Node.js 20, Python 3, prerequisites
- docker-compose.yml: Orchestrate 3 test containers + verification
- Test suite with 5 scripts:
* common.sh: Shared utilities and verification functions
* test-interactive-install.sh: Test Option 2 (interactive installer)
* test-master-prompt-install.sh: Test Option 1 (master prompt)
* test-manual-install.sh: Test Option 3 (manual installation)
* verify-all-installations.sh: Master verification with report generation
- run-tests.sh: Quick start script for easy test execution
What Gets Tested:
✓ Prerequisites (Node.js, npm, Python, Git, jq)
✓ Claude Code installation and version
✓ Settings files (settings.json, settings.local.json)
✓ 38 agents across 8 departments
✓ MCP tools (@z_ai/mcp-server, @z_ai/coding-helper, llm-tldr)
✓ UI/UX Pro Max skill
✓ Ralph CLI (optional, can be enabled)
Test Results:
- Saved to docker/test-env/test-results/
- Detailed logs for each test method
- Component verification counts
- Comprehensive final report with pass/fail status
Usage:
cd docker/test-env
./run-tests.sh
Or manually:
docker-compose up verify-all
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Changes:
- Update "What's Included": Add Ralph CLI Integration (Advanced)
- Add comprehensive "Ralph CLI Integration" section:
* What Ralph CLI does
* How it works (background execution)
* Key features table
* Control modes (agents/always/off)
* Monitoring & control commands
* Real-life example workflow
* Ralph vs PROACTIVELY comparison table
* Installation instructions
* When to use Ralph CLI
- Update "Complete Source Guide": 6 → 7 major open-source projects
- Add Ralph CLI as 6th component in source guide
Total Ralph mentions: 0 → 37
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Changes:
- Add section #8: Ralph CLI Check (Advanced - Optional)
- Verify Ralph CLI installation and version
- Check Ralph auto-trigger hook existence and permissions
- Verify hooks.json Ralph configuration
- Check ralph-config.env environment file
- Update Summary section number from #8 to #9
The verification script now covers all 3 auto-triggering systems:
1. PROACTIVELY agents (built-in to agent definitions)
2. Ralph CLI (optional autonomous looping)
3. Hooks-based event triggers
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
New Step 6: Configure Ralph CLI Autonomous Looping (Advanced - Optional)
- Install Ralph CLI: npm install -g @iannuttall/ralph
- Create ralph-auto-trigger.sh hook script
- Configure hooks.json for auto-triggering
- Control modes: always/agents/off (default: agents)
- State persistence in .claude/ralph-loop.local.md
- Cancel methods: /cancel-ralph, delete state file, set mode=off
Key Features:
- Autonomous looping until task completion
- Multi-iteration workflows
- State management across loops
- Integrates with PROACTIVELY agents in HYBRID mode
Updated Step 7: Verify Complete Installation
- Added Ralph CLI verification
- Added Ralph hook verification
- Marked Ralph as optional (⚠️)
Updated Summary:
- Changed 'Two Auto-Triggering Systems' to 'Three'
- Added Ralph CLI as third system
- Clarified PROACTIVELY vs Ralph CLI vs Hooks
HYBRID Approach:
- Users can choose patterns-only (simple)
- Or Ralph CLI (advanced autonomous)
- Or combine both for maximum power
- Default: PROACTIVELY patterns built-in
- Optional: Ralph CLI for complex workflows
Changes:
- Remove Ralph from list of installed components (it was misleading)
- Change component count from 7 to 6
- Add Agent Architecture Patterns section explaining:
- PROACTIVELY coordinators implement proven coordination patterns
- Patterns inspired by frameworks like Ralph
- Supervisor-agent delegation and shared context management
- Clarify Ralph is a conceptual reference, not an installed tool
This prevents confusion - Ralph CLI is not installed, only its
coordination patterns influenced the agent design.
MASTER-PROMPT.md restructure:
- Master prompt now in ONE continuous code block (bash blocks to plain text
- Added clear labels for code sections within the prompt
- Real-life examples now in proper markdown outside code block
- Configuration examples in separate code blocks after main prompt
- Quick reference section properly formatted
- All content preserved, just restructured for proper rendering
The master prompt can now be copied as a single block
without formatting breaking mid-copy.
Interactive installer (interactive-install-claude.sh):
- Add fetch_latest_agents() function to check GitHub for updates
- Clone latest agents from contains-studio/agents before installing
- Update local agents directory with upstream changes
- Gracefully fallback to local agents if GitHub fetch fails
- Call fetch_latest_agents() before install_agents() in main flow
Sync script (sync-agents.sh):
- Add REPO_AGENTS_DIR environment variable support
- Automatically update repository agents directory when syncing
- Keep installer agents in sync with Claude Code agents
This ensures users always get the latest agents from upstream GitHub
while maintaining customizations in the local repository.
- agent-updater.md: Special agent for syncing agents from GitHub
- sync-agents.sh: Automated script to update local agents from upstream
and push to Gitea for backup
- Add PROACTIVELY (uppercase) to test-writer-fixer description
- Ensures consistency with other 6 PROACTIVELY agents
- All 7 coordinators now use uppercase PROACTIVELY keyword
- Add MASTER-PROMPT.md.backup to .gitignore
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- workflow-example-pro.html: Modern timeline-based visualization with gradient timeline line, numbered steps, color-coded agent cards, celebratory result section
- coordination-system-pro.html: Updated coordination section with architecture overview, two pathways explanation, all 7 coordinators with proper styling
These HTML sections can be used in WordPress blogs, documentation, or landing pages to explain the agent coordination system visually.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Update PROACTIVELY agents from 5 to 7 (add studio-producer, project-shipper)
- Add clear architecture overview: 7 coordinators + 31 specialists
- Explain two pathways: automatic vs direct control
- Add real workflow example showing coordinator orchestration
- Clarify how coordinators call specialists automatically
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Replace HTML div tags with proper markdown formatting
- Use box-drawing characters for visual separation
- Add clear section headers with emoji indicators
- Use code blocks with language tags (diff for ❌ examples)
- Add proper spacing and horizontal rules
- Ensure GitHub renders all formatting correctly
- Make examples section clearly distinct from main content
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Create prominent boxed section with gradient background
- Add clear warning box explaining these are illustrative examples only
- Use color-coded boxes: yellow (❌ WITHOUT) vs green (✅ WITH)
- Add proper visual separation from main installation content
- Include border styling and padding for clear visual hierarchy
- Make it immediately clear this is a separate reference section
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Create dedicated 'How Auto-Triggering Works: Practical Examples' section
- Add clear NOTE explaining these are illustrative examples
- Consolidate 5 examples showing WITHOUT vs WITH scenarios
- Add visual separation with headers and dividers
- Include summary table comparing without vs with auto-triggering
- Remove duplicate examples scattered throughout document
- Make it immediately clear these are workflow examples
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Added tip at top of README with invite code R0K78RJKNW
- Links to Z.AI GLM Plan subscription with discount
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Added ui-ux-pro-max agent installation to design section
- Includes fallback download from repository
- Completes synchronization across all installation methods
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Create RALPH-INTEGRATION.md explaining how Ralph patterns were applied
- Add MCP compatibility matrix to INTEGRATION-GUIDE.md
* All 29 MCP tools work with both Anthropic and Z.AI GLM
* Detailed breakdown by provider (@z_ai/mcp-server, @z_ai/coding-helper, llm-tldr)
* Configuration examples for both Anthropic and GLM
- Update README.md to link to RALPH-INTEGRATION.md
- Update blog post with MCP compatibility information
- Explain which Ralph patterns are integrated:
* Supervisor-agent coordination (studio-coach)
* Task delegation framework (studio-producer)
* Shared context system
* Cross-agent coordination (experiment-tracker)
* Performance coaching patterns
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Add llm-tldr (95% token reduction) to all installation methods
- Update MASTER-PROMPT.md with all 6 sources and real-life examples
- Update README.md with comprehensive source guide
- Update automation script with TLDR installation and MCP config
- Update INTEGRATION-GUIDE.md to clarify Z.AI MCP tools work with GLM
- Add MCP explanation and link to modelcontextprotocol.io
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
BREAKING CHANGES to workflow:
- Add 'BEFORE YOU BEGIN' section to MASTER-PROMPT.md
- GLM users MUST configure GLM FIRST before using Claude Code
- Add clear GLM pre-configuration steps at top of file
- Add clear copy boundaries (✂️ COPY FROM HERE / ✂️ COPY ENDS HERE)
- Add visual separator lines for copy-paste section
README.md updates:
- Add prominent GLM warning at top of Installation Options
- Add quick GLM setup commands
- Clarify Master Prompt workflow with step-by-step
- Emphasize GLM pre-configuration requirement
This fixes the issue where GLM users couldn't use Claude Code
to paste the master prompt without first configuring GLM.
- Add GLM model mappings (glm-4.5-air, glm-4.7) to settings.json
- Update both new and existing file creation paths
- Add version verification guidance (2.0.14+ recommended)
- Reference official Z.AI documentation (https://docs.z.ai/devpack/tool/claude)
- Add troubleshooting steps from official docs
- Add /status command verification instructions
- Display GLM configuration summary after setup
- Update API help text to include official docs link
- Add Claude Code installation prerequisite (npm install)
- Update GLM configuration with official model mappings (glm-4.5-air, glm-4.7)
- Add version verification (recommended 2.0.14+)
- Include troubleshooting steps from Z.AI docs
- Add /status command verification
- Reference official Z.AI documentation: https://docs.z.ai/devpack/tool/claude
- Update README with proper GLM model configuration
- Users can now copy-paste a master prompt into Claude Code
- Includes all source repository references
- Step-by-step guided installation
- Alternative to running bash scripts
- Updated README with 3 installation options
- Agent integration architecture (file-based system)
- MCP tools integration (STDIO/JSON-RPC protocol)
- Ralph framework integration (multi-agent coordination)
- Auto-triggering system (hooks-based automation)
- Multi-model support (Anthropic + Z.AI)
- Benefits and use cases for each integration
- Complete integration stack diagram
- How Ralph patterns benefit Claude Code
- Step-by-step instructions for Anthropic Claude setup
- Step-by-step instructions for Z.AI/GLM Plan setup
- Complete copy-paste commands for both options
- MCP tools installation instructions
- Verification and testing steps
- Advanced configuration examples
- All commands ready to copy and execute