This skill provides centralized quality gate definitions for all workflows. Instead of hardcoding thresholds like "80% coverage" or "100% test pass rate" throughout the codebase, agents and skills reference this single source of truth.
/plugin marketplace add marcel-Ngan/ai-dev-team/plugin install marcel-ngan-ai-dev-team@marcel-Ngan/ai-dev-teamThis skill inherits all available tools. When active, it can use any tool Claude has access to.
gates.jsonThis skill provides centralized quality gate definitions for all workflows. Instead of hardcoding thresholds like "80% coverage" or "100% test pass rate" throughout the codebase, agents and skills reference this single source of truth.
skills/quality/gate-definitions/gates.json
Global thresholds referenced by gates:
{
"thresholds": {
"test_pass_rate": { "value": 100, "unit": "%" },
"code_coverage": { "value": 80, "unit": "%" },
"max_review_iterations": { "value": 3, "unit": "iterations" }
}
}
Each gate defines:
Each requirement can be:
Metric-based (has a numeric threshold):
{
"id": "coverage_met",
"metric": "code_coverage",
"operator": "gte",
"threshold": "{{thresholds.code_coverage.value}}",
"unit": "%"
}
Check-based (boolean pass/fail):
{
"id": "tdd_compliance",
"check": "tdd_compliance",
"required": true
}
| Gate ID | Name | Workflow | Enforced By |
|---|---|---|---|
code-review-gate | Code Review Gate | development | Senior Developer |
qa-gate | QA Gate | development | QA Engineer |
deployment-gate | Deployment Gate | development | DevOps Engineer |
bug-fix-review-gate | Bug Fix Code Review Gate | bug-hotfix | Senior Developer |
bug-fix-qa-gate | Bug Fix QA Gate | bug-hotfix | QA Engineer |
When checking a gate, reference the definition:
**Gate:** `qa-gate` (from `skills/quality/gate-definitions/gates.json`)
**Requirements:**
- Unit tests: {{unit_test_pass_rate}}% (threshold: {{gates.qa-gate.requirements.unit_tests_pass.threshold}}%)
- Integration tests: {{integration_test_pass_rate}}% (threshold: {{gates.qa-gate.requirements.integration_tests_pass.threshold}}%)
- Coverage: {{code_coverage}}% (threshold: {{gates.qa-gate.requirements.coverage_met.threshold}}%)
Include gate reference in QA sign-off:
### Gate Evaluation
**Gate:** QA Gate (`qa-gate`)
**Thresholds from:** `skills/quality/gate-definitions/gates.json`
| Requirement | Threshold | Actual | Status |
|-------------|-----------|--------|--------|
| Unit Test Pass Rate | 100% | 100% | ✅ |
| Integration Test Pass Rate | 100% | 100% | ✅ |
| E2E Test Pass Rate | 100% | 100% | ✅ |
| Code Coverage | ≥80% | 84% | ✅ |
| Exploratory Testing | Required | Done | ✅ |
| No Critical Bugs | Required | None | ✅ |
| Acceptance Criteria | Required | Verified | ✅ |
**Result:** ✅ GATE PASSED
Workflows reference gates by ID:
### Step 5: QA Verification
**Gate:** `qa-gate`
QA Engineer evaluates requirements defined in `skills/quality/gate-definitions/gates.json`.
See gate definition for current thresholds.
To change a threshold (e.g., increase coverage to 85%):
Edit gates.json:
"code_coverage": { "value": 85, "unit": "%" }
All gates referencing this threshold automatically use the new value
Document the change in the commit message
The gate definitions include metrics to track:
These feed into the Retrospective Gate Report (see workflows/retrospective.md).
skills/testing/test-verification/ - Uses gate definitions for QA sign-offskills/observability/workflow-trace/ - Tracks gate outcomesqa-gate, bug-fix-qa-gatecode-review-gate, bug-fix-review-gatedeployment-gateThis 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 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 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.