Validates Finalization Phase completion before workflow concludes. Checks documentation updates, file registry, git commits, deployment readiness, and lessons learned contributions.
Validates finalization before workflow completion. Checks documentation, commits, deployment readiness, and lessons learned. Automatically blocks completion if single-source-of-truth violations or file size limits are exceeded.
/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 that all work is properly documented, committed, and ready for deployment/handoff.
When to Use: Final validation before marking workflow complete.
Executable Script: execute.sh
# Basic usage (no parameters required)
bash .claude/skills/phase-5-validator/execute.sh
# Show help
bash .claude/skills/phase-5-validator/execute.sh --help
Parameters:
Script validates:
Exit codes:
CRITICAL: This validator has BLOCKING AUTHORITY and can prevent workflow completion.
CRITICAL: This check runs FIRST with BLOCKING AUTHORITY. Any violations = immediate failure before scoring begins.
CRITICAL: This check runs SECOND with BLOCKING AUTHORITY. Files exceeding 1700 lines = immediate failure before scoring begins.
Use the phase-5-validator skill to check if work is ready to finalize
# Run finalization validation
bash .claude/skills/phase-5-validator.md
CRITICAL: Every file operation must be logged.
Solution:
# Update file registry
echo "| $(date +%Y-%m-%d) | /path/to/file | CREATED | Purpose | Task | ACTIVE | - |" >> docs/architecture/file-registry.md
Solution:
# Check status
git status
# Commit changes
git add .
git commit -m "feat: implement user management feature
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>"
Required documents:
Solution:
# Find and remove
find . -name "*.tmp" -delete
find . -name "*.bak" -delete
# Or move to session-work
mkdir -p session-work/$(date +%Y-%m-%d)
mv status.md session-work/$(date +%Y-%m-%d)/
Before marking workflow complete:
🚨 Single Source of Truth (BLOCKING - FIRST CHECK)
Git
Documentation
Lessons Learned
Quality
Cleanup
{
"phase": "finalization",
"status": "pass|fail",
"singleSourceOfTruth": {
"validated": true,
"skillsChecked": 13,
"violations": 0,
"blocking": false,
"note": "CRITICAL: This check runs FIRST. Any violations = immediate failure."
},
"score": 87,
"maxScore": 100,
"percentage": 87,
"requiredPercentage": 80,
"git": {
"uncommittedChanges": 0,
"commitMessage": "standards-compliant",
"upToDate": true,
"conflicts": false
},
"documentation": {
"fileRegistry": "updated",
"progress": "updated",
"featureDocs": "complete",
"claude": "not-needed"
},
"lessonsLearned": {
"newLessons": 2,
"formatCompliant": true,
"crossReferences": true
},
"deployment": {
"testsPass": true,
"blockingIssues": 0,
"notesPresent": true
},
"cleanup": {
"tempFiles": 0,
"sessionWork": "organized",
"orphanedFiles": 0
},
"readyToFinalize": true,
"nextSteps": [
"Deploy to staging (if approved)",
"Close workflow",
"Update project status"
]
}
Quality gate thresholds by work type:
Initial Context: Show quick status check (committed, documented, tested) On Request: Show full scoring breakdown On Failure: Show specific missing items with actionable fixes On Pass: Show next steps and finalization instructions
Remember: Finalization is about ensuring nothing is forgotten. Documentation, commits, and lessons learned ensure the work is sustainable and maintainable long-term.
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.