Validates Testing Phase completion before advancing to Finalization Phase. Checks test execution results, coverage targets, test quality, and environment health. Ensures 100% test pass rate required by quality gates.
Validates Testing Phase completion by checking 100% test pass rate, coverage targets, and environment health. Triggers when orchestrator needs to verify all tests pass before advancing to Finalization Phase.
/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 Testing Phase before advancing to Finalization Phase.
When to Use: When orchestrator needs to verify all tests are passing and ready for deployment.
ALL work types (Feature/Bug/Hotfix/Docs/Refactor) require 100% test pass rate.
No exceptions. One failing test = Phase 4 fails.
Executable Script: execute.sh
# Basic usage (no parameters required)
bash .claude/skills/phase-4-validator/execute.sh
# Show help
bash .claude/skills/phase-4-validator/execute.sh --help
Parameters:
Script validates:
Exit codes:
CRITICAL: This validator BLOCKS workflow if ANY test fails. 100% pass rate is mandatory.
Use the phase-4-validator skill to verify all tests are passing
# Run complete validation
bash .claude/skills/phase-4-validator.md
Solution: Run environment checks first
./dev.sh
# Wait for all containers to be healthy
docker ps
Solution: Phase 4 CANNOT advance with failing tests
Warning but not blocker: Coverage below targets is a warning but doesn't block if all tests pass.
However: Should document in testing-notes.md as known limitation.
Solution: Flaky tests = unreliable validation
Testing Phase has ZERO TOLERANCE for failing tests.
Even a single failing test means:
Why: Deploying with failing tests risks production issues.
{
"phase": "testing",
"status": "pass|fail",
"score": 95,
"maxScore": 100,
"percentage": 95,
"testResults": {
"unit": {
"total": 45,
"passed": 45,
"failed": 0,
"passRate": 100
},
"integration": {
"total": 12,
"passed": 12,
"failed": 0,
"passRate": 100
},
"e2e": {
"total": 8,
"passed": 8,
"failed": 0,
"passRate": 100
}
},
"coverage": {
"api": 85,
"web": 72
},
"environment": {
"docker": "healthy",
"database": "healthy",
"api": "responding",
"web": "responding"
},
"quality": {
"flakyTests": 0,
"executionTime": 125.3,
"independent": true,
"cleanupWorking": true
},
"readyForNextPhase": true
}
ALL work types require 100% test pass rate:
Initial Context: Show pass/fail status only On Request: Show detailed test results and coverage On Failure: Show specific failing tests with logs On Pass: Show concise summary + quality metrics
Remember: Phase 4 is the quality gate. If tests aren't 100% passing, nothing advances. This protects production from bugs.
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.