メニュー
Code quality orchestrator enforcing TRUST 5 validation, proactive code analysis, linting standards, and automated best practices. Use for code review, quality gate checks, or TRUST 5 compliance.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
AI text humanization and 윤문 (post-editing) specialist that detects and removes AI tells while preserving meaning, facts, and figures. Covers Korean, English, Japanese, and Chinese with a shared severity model (S1/S2/S3), quality grades (A/B/C/D), and 30%/50% over-editing guardrails. Use to make AI-generated text read as human-authored without changing what it says (de-ai, naturalness pass).
MoAI unified orchestrator for autonomous development. Routes natural language or subcommands (plan, run, sync, project, fix, loop, mx, feedback, review, clean, codemaps, gate, harness) to specialized agents.
Markdown-to-single-file-HTML report renderer. Six modes (status, incident, plan, explainer, financial, pr) selected automatically by report type. Zero external JS/CSS framework dependencies — inline SVG charts, single font-CDN exception for Korean readability. Self-contained output for email attachment, print, and offline viewing.
Unified thinking toolkit: Creative frameworks (Critical Evaluation, Diverge-Converge, Deep Questioning), First Principles reasoning (absorbed from moai-foundation-philosopher), and Adaptive Thinking via the `ultrathink` keyword. Use for ideation, strategic analysis, architecture decisions, and deep reasoning on complex problems.
Provides MoAI-ADK foundational principles including TRUST 5 quality framework, SPEC-First DDD methodology, delegation patterns, progressive disclosure, agent catalog reference, and token budget management (absorbed from moai-foundation-context). Use when referencing TRUST 5 gates, SPEC workflow, or context window optimization.
Provides MoAI-ADK foundational principles including TRUST 5 quality framework, SPEC-First DDD methodology, delegation patterns, progressive disclosure, agent catalog reference, and token budget management (absorbed from moai-foundation-context). Use when referencing TRUST 5 gates, SPEC workflow, or context window optimization.
SOC 職業分類に基づく
| name | moai-foundation-quality |
| description | Code quality orchestrator enforcing TRUST 5 validation, proactive code analysis, linting standards, and automated best practices. Use for code review, quality gate checks, or TRUST 5 compliance. |
| when_to_use | Use for code-quality orchestration: TRUST 5 validation, proactive code analysis, linting standards, coverage targets, pytest, security checks, CI/CD quality gates, code-smell detection, and technical-debt refactoring. |
| license | Apache-2.0 |
| compatibility | Designed for Claude Code |
| allowed-tools | Read, Grep, Glob, mcp__context7__resolve-library-id, mcp__context7__get-library-docs |
| user-invocable | false |
| metadata | {"version":"2.2.0","category":"foundation","status":"active","updated":"2026-01-11","modularized":"true","tags":"foundation, quality, testing, validation, trust-5, best-practices, code-review","aliases":"moai-foundation-quality"} |
| progressive_disclosure | {"enabled":true,"level1_tokens":100,"level2_tokens":5000} |
Enterprise-grade code quality management system that combines systematic code review, proactive improvement suggestions, and automated best practices enforcement. Provides comprehensive quality assurance through TRUST 5 framework validation with Context7 integration for real-time best practices.
Core Capabilities:
Key Patterns:
When to Use:
Quick Access:
Basic Quality Validation: Initialize QualityOrchestrator with trust5_enabled, proactive_analysis, best_practices_enforcement, and context7_integration all set to True. Call analyze_codebase method with path parameter set to source directory, languages list including python, javascript, and typescript, and quality_threshold of 0.85. The method returns comprehensive quality results.
For quality gate validation with TRUST 5, create QualityGate instance and call validate_trust5 with codebase_path, test_coverage_threshold of 0.90, and complexity_threshold of 10.
Proactive Quality Analysis: Initialize ProactiveQualityScanner with context7_client and BestPracticesEngine rule_engine. Call scan_codebase with path and scan_types list including security, performance, maintainability, and testing. Generate recommendations by calling generate_recommendations with issues, priority set to high, and auto_fix enabled.
The QualityOrchestrator class provides enterprise quality orchestration with TRUST 5 framework. Initialize with QualityConfig and create instances of TRUST5Validator, ProactiveScanner, BestPracticesEngine, Context7Client, and QualityMetricsCollector.
The analyze_codebase method performs comprehensive analysis in four phases. Phase 1 runs TRUST 5 validation on the codebase with specified thresholds. Phase 2 performs proactive analysis scanning focus areas. Phase 3 checks best practices for specified languages with Context7 docs enabled. Phase 4 collects comprehensive metrics from all analysis results.
The method returns QualityResult containing trust5_validation, proactive_analysis, best_practices, metrics, and overall_score calculated from all results.
Detailed implementations available in modules:
Quality Configuration: Create quality-config.yaml with quality_orchestration section.
Under trust5_framework, set enabled to true with thresholds for overall (0.85), testable (0.90), readable (0.80), unified (0.85), secured (0.90), and trackable (0.80).
Under proactive_analysis, set enabled true, scan_frequency to daily, and focus_areas list including performance, security, maintainability, and technical_debt.
Under auto_fix, set enabled true, severity_threshold to medium, and confirmation_required to true.
Under best_practices, set enabled true, context7_integration true, auto_update_standards true, and compliance_target to 0.85.
Under language_rules, configure python with pep8 style_guide, black formatter, ruff linter, and mypy type_checker. Configure javascript with airbnb style_guide, prettier formatter, and eslint linter. Configure typescript with google style_guide, prettier formatter, and eslint linter.
Under reporting, set enabled true, metrics_retention_days to 90, trend_analysis true, and executive_dashboard true.
Under notifications, enable quality_degradation, security_vulnerabilities, and technical_debt_increase.
Integration Examples: See Integration Patterns for CI/CD Pipeline Integration, GitHub Actions Integration, Quality-as-Service REST API, and Cross-Project Benchmarking.
Create CustomQualityRule class with name, validator callable, and severity defaulting to medium. The validate async method executes the validator on codebase, wrapping in try-except. On success, return RuleResult with rule_name, passed status, severity, details, and recommendations. On exception, return RuleResult with passed false, severity error, error details, and fix recommendation.
See Best Practices - Custom Rules for complete examples.
ML-powered quality issue prediction using code feature extraction and predictive models. See Proactive Analysis - ML Prediction for implementation details.
Continuous quality monitoring with automated alerting for quality degradation and security vulnerabilities. See Proactive Analysis - Real-time Monitoring for implementation details.
Compare project quality metrics against similar projects in your industry. See Integration Patterns - Benchmarking for implementation details.
TRUST 5 Validation: TRUST5Validator for five-pillar quality validation, TestableValidator for test coverage and quality, SecuredValidator for security and OWASP compliance, and quality gate pipeline integration.
Proactive Analysis: ProactiveQualityScanner for automated issue detection, QualityPredictionEngine for ML-powered predictions, RealTimeQualityMonitor for continuous monitoring, and performance and maintainability analysis.
Best Practices: BestPracticesEngine for standards validation, Context7 integration for latest docs, custom quality rules, and language-specific validators.
Integration Patterns: CI/CD pipeline integration, GitHub Actions workflows, Quality-as-Service REST API, and cross-project benchmarking.
Essential library mappings for quality analysis tools and frameworks. See Best Practices - Library Mappings for complete list.
Agents:
Skills:
Commands:
Core Capabilities: TRUST 5 validation, proactive scanning, Context7-powered best practices, multi-language support, enterprise integration
Key Classes: QualityOrchestrator, TRUST5Validator, ProactiveQualityScanner, BestPracticesEngine, QualityMetricsCollector
Essential Methods: analyze_codebase(), validate_trust5(), scan_for_issues(), validate_best_practices(), generate_quality_report()
Integration Ready: CI/CD pipelines, GitHub Actions, REST APIs, real-time monitoring, cross-project benchmarking
Enterprise Features: Custom rules, ML prediction, real-time monitoring, benchmarking, comprehensive reporting
Quality Standards: OWASP compliance, TRUST 5 framework, Context7 integration, automated improvement recommendations
| Rationalization | Reality |
|---|---|
| "The linter warnings are false positives" | False positives should be suppressed with inline comments. Ignoring them trains the team to ignore real issues. |
| "Security scanning can wait until before release" | Security vulnerabilities compound. Late discovery means expensive rework. Scan continuously. |
| "Coverage is high enough, the remaining 15% is edge cases" | Edge cases are where production bugs live. The uncovered code is the riskiest code. |
| "Code review is subjective, automation is sufficient" | Automation catches syntax and patterns. Reviews catch design flaws, naming confusion, and missing abstractions. |
| "TRUST 5 is too bureaucratic for a hotfix" | Hotfixes without quality gates introduce the next hotfix. TRUST 5 on a hotfix is the minimum, not the maximum. |
Chesterton's Fence: Before removing a quality check, understand why it was added. Removing a gate without understanding its history repeats the failure it was designed to prevent.
Shift Left: The earlier a defect is found, the cheaper it is to fix. Quality checks belong in the development loop, not at the end of it.
