Validates Design Phase completion before advancing to Implementation Phase. Checks functional specifications, database design, and UI/UX design for completeness and technical feasibility.
Validates design phase completion before implementation by checking functional specs, database design, and UI/UX for completeness. Triggered when orchestrator needs to verify designs are ready, enforcing quality gates (90% for features) and detecting architectural violations.
/plugin marketplace add DarkMonkDev/WitchCityRope/plugin install darkmonkdev-witchcityrope-agents@DarkMonkDev/WitchCityRopeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Purpose: Automate validation of Design Phase completion before advancing to Implementation Phase.
When to Use: When orchestrator or agents need to verify design documents are ready for implementation.
Executable Script: execute.sh
# Basic usage with new-work directory path
bash .claude/skills/phase-2-validator/execute.sh <new-work-directory>
# With work type specification
bash .claude/skills/phase-2-validator/execute.sh <new-work-dir> <work-type>
# With custom quality gate threshold
bash .claude/skills/phase-2-validator/execute.sh <new-work-dir> Feature 90
# Examples:
bash .claude/skills/phase-2-validator/execute.sh docs/functional-areas/events/new-work/2025-11-03-feature
bash .claude/skills/phase-2-validator/execute.sh docs/functional-areas/checkin/new-work/2025-11-03-bug Bug 70
Parameters:
new-work-directory: Path to new-work folder containing design documentswork-type: (optional) Feature|Bug|Hotfix|Docs|Refactor (default: Feature)required-percentage: (optional) Override quality gate thresholdScript validates:
Exit codes:
See: The validation logic is now in execute.sh - this maintains single source of truth for the automation.
Use the phase-2-validator skill to check if design is ready for implementation
# Find new-work directory
NEW_WORK_DIR=$(find docs/functional-areas -type d -path "*/new-work/*-*-*" | sort | tail -1)
# Run validation
bash .claude/skills/phase-2-validator.md "$NEW_WORK_DIR"
Solution: Functional spec must explicitly document:
Solution: All database designs must use PostgreSQL syntax:
UUID not UNIQUEIDENTIFIERVARCHAR not NVARCHARTIMESTAMP not DATETIME2Solution: UI design must specify Mantine components:
Button, TextInput, Select, Modal, etc.Critical violations that fail validation:
{
"phase": "design",
"status": "pass|fail",
"score": 32,
"maxScore": 35,
"percentage": 91,
"requiredPercentage": 90,
"documents": {
"functionalSpec": "present",
"databaseDesign": "present",
"uiUxDesign": "present"
},
"missingItems": [
"Accessibility requirements not addressed",
"Mobile wireframes not provided"
],
"architecturalViolations": [],
"readyForNextPhase": true
}
This skill enforces the quality gate thresholds by work type:
Initial Context: Show quick document checklist On Request: Show full validation script with scoring On Failure: Show specific missing items and architectural violations On Pass: Show concise summary with score
Remember: This skill automates design validation but doesn't replace agent judgment. If validation fails, orchestrator should loop back to functional-spec, database-designer, or ui-designer agents.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.