moai-adk 0.4.0__py3-none-any.whl → 0.4.1__py3-none-any.whl

moai_adk/templates/.claude/skills/moai-domain-cli-tool/SKILL.md

@@ -1,23 +1,32 @@
 ---
+
 name: moai-domain-cli-tool
-description: CLI tool development with argument parsing, POSIX compliance, and user-friendly
-  help messages
+description: CLI tool development with argument parsing, POSIX compliance, and user-friendly help messages. Use when working on command-line tooling scenarios.
 allowed-tools:
-- Read
-- Bash
+  - Read
+  - Bash
 ---
 
 # CLI Tool Expert
 
+## Skill Metadata
+| Field | Value |
+| ----- | ----- |
+| Allowed tools | Read (read_file), Bash (terminal) |
+| Auto-load | On demand for CLI design requests |
+| Trigger cues | Command-line UX, packaging, distribution, and automation workflows. |
+| Tier | 4 |
+
 ## What it does
 
 Provides expertise in developing command-line interface tools with proper argument parsing, POSIX compliance, intuitive help messages, and standard exit codes.
 
 ## When to use
 
-- "CLI 도구 개발", "명령줄 파싱", "POSIX 호환성"
+- Engages when building or enhancing command-line tools.
+- “CLI tool development”, “command line parsing”, “POSIX compatibility”
 - Automatically invoked when working with CLI projects
-- CLI tool SPEC implementation (`/alfred:2-build`)
+- CLI tool SPEC implementation (`/alfred:2-run`)
 
 ## How it works
 
@@ -48,17 +57,39 @@ Provides expertise in developing command-line interface tools with proper argume
 - **Precedence**: CLI args > env vars > config file > defaults
 
 ## Examples
+```bash
+$ tool --help
+$ tool run --config config.yml
+```
+
+## Inputs
+- Domain-specific design documents and user requirements.
+- Project technology stack and operational constraints.
+
+## Outputs
+- Domain-specific architecture or implementation guidelines.
+- Recommended list of associated sub-agents/skills.
 
-### Example 1: CLI tool with subcommands
-User: "/alfred:2-build CLI-001"
-Claude: (creates RED CLI test, GREEN implementation with click, REFACTOR)
+## Failure Modes
+- When the domain document does not exist or is ambiguous.
+- When the project strategy is unconfirmed and cannot be specified.
 
-### Example 2: POSIX compliance check
-User: "POSIX 호환성 확인"
-Claude: (validates exit codes, option formats, stderr usage)
+## Dependencies
+- `.moai/project/` document and latest technical briefing are required.
+
+## References
+- Microsoft. "Command Line Interface Guidelines." https://learn.microsoft.com/windows/console/ (accessed 2025-03-29).
+- Python Packaging Authority. "Command-line Interface Guidelines." https://packaging.python.org/en/latest/guides/distributing-packages-using-setuptools/#entry-points (accessed 2025-03-29).
+
+## Changelog
+- 2025-03-29: Codified input/output and failure responses for domain skills.
 
 ## Works well with
 
 - alfred-trust-validation (CLI testing)
 - shell-expert (shell integration)
 - python-expert/typescript-expert (implementation)
+
+## Best Practices
+- Record supporting documentation (version/link) for each domain decision.
+- Review performance, security, and operational requirements simultaneously at an early stage.

moai_adk/templates/.claude/skills/moai-domain-data-science/SKILL.md

@@ -1,23 +1,32 @@
 ---
+
 name: moai-domain-data-science
-description: Data analysis, visualization, statistical modeling, and reproducible
-  research workflows
+description: Data analysis, visualization, statistical modeling, and reproducible research workflows. Use when working on data science workflows scenarios.
 allowed-tools:
-- Read
-- Bash
+  - Read
+  - Bash
 ---
 
 # Data Science Expert
 
+## Skill Metadata
+| Field | Value |
+| ----- | ----- |
+| Allowed tools | Read (read_file), Bash (terminal) |
+| Auto-load | On demand for analytics and DS work |
+| Trigger cues | Notebook workflows, data pipelines, feature engineering, experimentation plans. |
+| Tier | 4 |
+
 ## What it does
 
 Provides expertise in data analysis workflows, statistical modeling, data visualization, and reproducible research practices using Python (pandas, scikit-learn) or R (tidyverse).
 
 ## When to use
 
-- "데이터 분석", "시각화", "통계 모델링", "재현 가능한 연구"
+- Engages when analytics, experimentation, or data science implementation is requested.
+- “Data analysis”, “Visualization”, “Statistical modeling”, “Reproducible research”
 - Automatically invoked when working with data science projects
-- Data science SPEC implementation (`/alfred:2-build`)
+- Data science SPEC implementation (`/alfred:2-run`)
 
 ## How it works
 
@@ -51,17 +60,39 @@ Provides expertise in data analysis workflows, statistical modeling, data visual
 - **Environment management**: conda, renv
 
 ## Examples
+```markdown
+- Orchestrate data prep → training → evaluation steps.
+- Export metrics (precision/recall) to the Quality Report.
+```
+
+## Inputs
+- Domain-specific design documents and user requirements.
+- Project technology stack and operational constraints.
+
+## Outputs
+- Domain-specific architecture or implementation guidelines.
+- Recommended list of associated sub-agents/skills.
 
-### Example 1: Exploratory data analysis
-User: "/alfred:2-build ANALYSIS-001"
-Claude: (creates RED analysis test, GREEN pandas implementation, REFACTOR with visualizations)
+## Failure Modes
+- When the domain document does not exist or is ambiguous.
+- When the project strategy is unconfirmed and cannot be specified.
 
-### Example 2: Statistical modeling
-User: "회귀 분석 모델 구축"
-Claude: (implements linear regression with hypothesis testing)
+## Dependencies
+- `.moai/project/` document and latest technical briefing are required.
+
+## References
+- Google. "Rules of Machine Learning." https://developers.google.com/machine-learning/guides/rules-of-ml (accessed 2025-03-29).
+- Netflix. "Metaflow: Human-Centric Framework for Data Science." https://metaflow.org/ (accessed 2025-03-29).
+
+## Changelog
+- 2025-03-29: Codified input/output and failure responses for domain skills.
 
 ## Works well with
 
 - alfred-trust-validation (analysis testing)
 - python-expert/r-expert (implementation)
 - ml-expert (advanced modeling)
+
+## Best Practices
+- Record supporting documentation (version/link) for each domain decision.
+- Review performance, security, and operational requirements simultaneously at an early stage.

moai_adk/templates/.claude/skills/moai-domain-database/SKILL.md

@@ -1,23 +1,32 @@
 ---
+
 name: moai-domain-database
-description: Database design, schema optimization, indexing strategies, and migration
-  management
+description: Database design, schema optimization, indexing strategies, and migration management. Use when working on database integration tasks scenarios.
 allowed-tools:
-- Read
-- Bash
+  - Read
+  - Bash
 ---
 
 # Database Expert
 
+## Skill Metadata
+| Field | Value |
+| ----- | ----- |
+| Allowed tools | Read (read_file), Bash (terminal) |
+| Auto-load | On demand for data layer design |
+| Trigger cues | Schema modeling, migration planning, query optimization, indexing strategy. |
+| Tier | 4 |
+
 ## What it does
 
 Provides expertise in database design, schema normalization, indexing strategies, query optimization, and safe migration management for SQL and NoSQL databases.
 
 ## When to use
 
-- "데이터베이스 설계", "스키마 최적화", "인덱스 전략", "마이그레이션"
+- Engages when the conversation focuses on database design or tuning.
+- “Database design”, “Schema optimization”, “Index strategy”, “Migration”
 - Automatically invoked when working with database projects
-- Database SPEC implementation (`/alfred:2-build`)
+- Database SPEC implementation (`/alfred:2-run`)
 
 ## How it works
 
@@ -53,17 +62,39 @@ Provides expertise in database design, schema normalization, indexing strategies
 - **NewSQL**: CockroachDB, Vitess
 
 ## Examples
+```bash
+$ alembic upgrade head
+$ psql -f audits/verify_constraints.sql
+```
+
+## Inputs
+- Domain-specific design documents and user requirements.
+- Project technology stack and operational constraints.
+
+## Outputs
+- Domain-specific architecture or implementation guidelines.
+- Recommended list of associated sub-agents/skills.
 
-### Example 1: Schema design with normalization
-User: "/alfred:2-build DB-SCHEMA-001"
-Claude: (creates RED schema test, GREEN implementation with constraints, REFACTOR with indices)
+## Failure Modes
+- When the domain document does not exist or is ambiguous.
+- When the project strategy is unconfirmed and cannot be specified.
 
-### Example 2: Query optimization
-User: "쿼리 성능 개선"
-Claude: (analyzes EXPLAIN output and suggests index creation)
+## Dependencies
+- `.moai/project/` document and latest technical briefing are required.
+
+## References
+- Fowler, Martin. "Evolutionary Database Design." https://martinfowler.com/articles/evodb.html (accessed 2025-03-29).
+- AWS. "Database Tuning Best Practices." https://aws.amazon.com/blogs/database/ (accessed 2025-03-29).
+
+## Changelog
+- 2025-03-29: Codified input/output and failure responses for domain skills.
 
 ## Works well with
 
 - alfred-trust-validation (migration testing)
 - sql-expert (SQL implementation)
 - backend-expert (ORM integration)
+
+## Best Practices
+- Record supporting documentation (version/link) for each domain decision.
+- Review performance, security, and operational requirements simultaneously at an early stage.

moai_adk/templates/.claude/skills/moai-domain-devops/SKILL.md

@@ -1,23 +1,32 @@
 ---
+
 name: moai-domain-devops
-description: CI/CD pipelines, Docker containerization, Kubernetes orchestration, and
-  infrastructure as code
+description: CI/CD pipelines, Docker containerization, Kubernetes orchestration, and infrastructure as code. Use when working on DevOps automation scenarios.
 allowed-tools:
-- Read
-- Bash
+  - Read
+  - Bash
 ---
 
 # DevOps Expert
 
+## Skill Metadata
+| Field | Value |
+| ----- | ----- |
+| Allowed tools | Read (read_file), Bash (terminal) |
+| Auto-load | On demand for platform and CI/CD topics |
+| Trigger cues | Infrastructure as code, pipeline design, release automation, observability setup. |
+| Tier | 4 |
+
 ## What it does
 
 Provides expertise in continuous integration/deployment (CI/CD), Docker containerization, Kubernetes orchestration, and infrastructure as code (IaC) for automated deployment workflows.
 
 ## When to use
 
-- "CI/CD 파이프라인", "Docker 컨테이너화", "Kubernetes 배포", "인프라 코드"
+- Engages when DevOps, CI/CD, or infrastructure automation is required.
+- “CI/CD pipeline”, “Docker containerization”, “Kubernetes deployment”, “infrastructure code”
 - Automatically invoked when working with DevOps projects
-- DevOps SPEC implementation (`/alfred:2-build`)
+- DevOps SPEC implementation (`/alfred:2-run`)
 
 ## How it works
 
@@ -53,17 +62,39 @@ Provides expertise in continuous integration/deployment (CI/CD), Docker containe
 - **ELK Stack**: Logging (Elasticsearch, Logstash, Kibana)
 
 ## Examples
+```bash
+$ terraform fmt && terraform validate
+$ ansible-playbook deploy.yml --check
+```
+
+## Inputs
+- Domain-specific design documents and user requirements.
+- Project technology stack and operational constraints.
+
+## Outputs
+- Domain-specific architecture or implementation guidelines.
+- Recommended list of associated sub-agents/skills.
 
-### Example 1: GitHub Actions CI/CD
-User: "/alfred:2-build CICD-001"
-Claude: (creates RED workflow test, GREEN GitHub Actions workflow, REFACTOR)
+## Failure Modes
+- When the domain document does not exist or is ambiguous.
+- When the project strategy is unconfirmed and cannot be specified.
 
-### Example 2: Kubernetes deployment
-User: "Kubernetes 배포 설정"
-Claude: (creates deployment.yaml, service.yaml, ingress.yaml)
+## Dependencies
+- `.moai/project/` document and latest technical briefing are required.
+
+## References
+- Google SRE. "Site Reliability Engineering." https://sre.google/books/ (accessed 2025-03-29).
+- HashiCorp. "Terraform Best Practices." https://developer.hashicorp.com/terraform/intro (accessed 2025-03-29).
+
+## Changelog
+- 2025-03-29: Codified input/output and failure responses for domain skills.
 
 ## Works well with
 
 - alfred-trust-validation (deployment validation)
 - shell-expert (shell scripting for automation)
 - security-expert (secure deployments)
+
+## Best Practices
+- Record supporting documentation (version/link) for each domain decision.
+- Review performance, security, and operational requirements simultaneously at an early stage.

moai_adk/templates/.claude/skills/moai-domain-frontend/SKILL.md

@@ -1,23 +1,32 @@
 ---
+
 name: moai-domain-frontend
-description: React/Vue/Angular development with state management, performance optimization,
-  and accessibility
+description: React/Vue/Angular development with state management, performance optimization, and accessibility. Use when working on frontend interfaces scenarios.
 allowed-tools:
-- Read
-- Bash
+  - Read
+  - Bash
 ---
 
 # Frontend Expert
 
+## Skill Metadata
+| Field | Value |
+| ----- | ----- |
+| Allowed tools | Read (read_file), Bash (terminal) |
+| Auto-load | On demand for frontend delivery |
+| Trigger cues | Component architecture, design systems, accessibility, performance budgets. |
+| Tier | 4 |
+
 ## What it does
 
 Provides expertise in modern frontend development using React, Vue, or Angular, including state management patterns, performance optimization techniques, and accessibility (a11y) best practices.
 
 ## When to use
 
-- "프론트엔드 개발", "React 컴포넌트", "상태 관리", "성능 최적화"
+- Engages when building or reviewing UI/front-end experiences.
+- “Front-end development”, “React components”, “state management”, “performance optimization”
 - Automatically invoked when working with frontend projects
-- Frontend SPEC implementation (`/alfred:2-build`)
+- Frontend SPEC implementation (`/alfred:2-run`)
 
 ## How it works
 
@@ -52,17 +61,39 @@ Provides expertise in modern frontend development using React, Vue, or Angular,
 - **Screen reader support**: Alt text, aria-live
 
 ## Examples
+```bash
+$ npm run lint && npm run test
+$ npm run build -- --profiling
+```
+
+## Inputs
+- Domain-specific design documents and user requirements.
+- Project technology stack and operational constraints.
+
+## Outputs
+- Domain-specific architecture or implementation guidelines.
+- Recommended list of associated sub-agents/skills.
 
-### Example 1: React component with performance optimization
-User: "/alfred:2-build UI-001"
-Claude: (creates RED component test, GREEN implementation with React.memo, REFACTOR)
+## Failure Modes
+- When the domain document does not exist or is ambiguous.
+- When the project strategy is unconfirmed and cannot be specified.
 
-### Example 2: Accessibility audit
-User: "접근성 검사"
-Claude: (runs axe-core or Lighthouse and reports issues)
+## Dependencies
+- `.moai/project/` document and latest technical briefing are required.
+
+## References
+- Google. "Web.dev Performance Guidelines." https://web.dev/fast/ (accessed 2025-03-29).
+- W3C. "Web Content Accessibility Guidelines (WCAG) 2.2." https://www.w3.org/TR/WCAG22/ (accessed 2025-03-29).
+
+## Changelog
+- 2025-03-29: Codified input/output and failure responses for domain skills.
 
 ## Works well with
 
 - alfred-trust-validation (frontend testing)
 - typescript-expert (type-safe React/Vue)
 - alfred-performance-optimizer (performance profiling)
+
+## Best Practices
+- Record supporting documentation (version/link) for each domain decision.
+- Review performance, security, and operational requirements simultaneously at an early stage.

moai_adk/templates/.claude/skills/moai-domain-ml/SKILL.md

@@ -1,22 +1,32 @@
 ---
+
 name: moai-domain-ml
-description: Machine learning model training, evaluation, deployment, and MLOps workflows
+description: Machine learning model training, evaluation, deployment, and MLOps workflows. Use when working on machine learning pipelines scenarios.
 allowed-tools:
-- Read
-- Bash
+  - Read
+  - Bash
 ---
 
 # ML Expert
 
+## Skill Metadata
+| Field | Value |
+| ----- | ----- |
+| Allowed tools | Read (read_file), Bash (terminal) |
+| Auto-load | On demand for ML lifecycle |
+| Trigger cues | Model training, evaluation, deployment, MLOps guardrails. |
+| Tier | 4 |
+
 ## What it does
 
 Provides expertise in machine learning model development, training, evaluation, hyperparameter tuning, deployment, and MLOps workflows for production ML systems.
 
 ## When to use
 
-- "머신러닝 모델 개발", "모델 학습", "모델 배포", "MLOps"
+- Engages when machine learning workflows or model operations are discussed.
+- “Machine learning model development”, “model training”, “model deployment”, “MLOps”
 - Automatically invoked when working with ML projects
-- ML SPEC implementation (`/alfred:2-build`)
+- ML SPEC implementation (`/alfred:2-run`)
 
 ## How it works
 
@@ -51,17 +61,39 @@ Provides expertise in machine learning model development, training, evaluation,
 - **Monitoring**: Data drift detection, model performance
 
 ## Examples
+```markdown
+- Trigger model training pipeline (e.g., `dvc repro`).
+- Register artifact path in Completion Report.
+```
+
+## Inputs
+- Domain-specific design documents and user requirements.
+- Project technology stack and operational constraints.
+
+## Outputs
+- Domain-specific architecture or implementation guidelines.
+- Recommended list of associated sub-agents/skills.
 
-### Example 1: Model training with scikit-learn
-User: "/alfred:2-build ML-001"
-Claude: (creates RED model test, GREEN training pipeline, REFACTOR with cross-validation)
+## Failure Modes
+- When the domain document does not exist or is ambiguous.
+- When the project strategy is unconfirmed and cannot be specified.
 
-### Example 2: Model deployment
-User: "모델 API 배포"
-Claude: (creates FastAPI endpoint with model serving)
+## Dependencies
+- `.moai/project/` document and latest technical briefing are required.
+
+## References
+- Google Cloud. "MLOps Continuous Delivery." https://cloud.google.com/architecture/mlops-continuous-delivery-and-automation-pipelines (accessed 2025-03-29).
+- NVIDIA. "MLOps Best Practices." https://developer.nvidia.com/blog/category/ai/ (accessed 2025-03-29).
+
+## Changelog
+- 2025-03-29: Codified input/output and failure responses for domain skills.
 
 ## Works well with
 
 - alfred-trust-validation (model testing)
 - python-expert (ML implementation)
 - data-science-expert (data preparation)
+
+## Best Practices
+- Record supporting documentation (version/link) for each domain decision.
+- Review performance, security, and operational requirements simultaneously at an early stage.

moai_adk/templates/.claude/skills/moai-domain-mobile-app/SKILL.md

@@ -1,23 +1,32 @@
 ---
+
 name: moai-domain-mobile-app
-description: Mobile app development with Flutter and React Native, state management,
-  and native integration
+description: Mobile app development with Flutter and React Native, state management, and native integration. Use when working on mobile application flows scenarios.
 allowed-tools:
-- Read
-- Bash
+  - Read
+  - Bash
 ---
 
 # Mobile App Expert
 
+## Skill Metadata
+| Field | Value |
+| ----- | ----- |
+| Allowed tools | Read (read_file), Bash (terminal) |
+| Auto-load | On demand for mobile flows |
+| Trigger cues | iOS/Android releases, cross-platform tooling, app store compliance, mobile UX. |
+| Tier | 4 |
+
 ## What it does
 
 Provides expertise in cross-platform mobile app development using Flutter (Dart) and React Native (TypeScript), including state management patterns and native module integration.
 
 ## When to use
 
-- "모바일 앱 개발", "Flutter 위젯", "React Native 컴포넌트", "상태 관리"
+- Engages when mobile application development or release pipelines are in scope.
+- “Mobile app development”, “Flutter widgets”, “React Native components”, “state management”
 - Automatically invoked when working with mobile app projects
-- Mobile app SPEC implementation (`/alfred:2-build`)
+- Mobile app SPEC implementation (`/alfred:2-run`)
 
 ## How it works
 
@@ -46,17 +55,39 @@ Provides expertise in cross-platform mobile app development using Flutter (Dart)
 - **Push notifications**: FCM, APNs
 
 ## Examples
+```markdown
+- Generate platform-specific builds (`flutter build`, `xcodebuild`).
+- Capture store submission checklist as Todo items.
+```
+
+## Inputs
+- Domain-specific design documents and user requirements.
+- Project technology stack and operational constraints.
+
+## Outputs
+- Domain-specific architecture or implementation guidelines.
+- Recommended list of associated sub-agents/skills.
 
-### Example 1: Flutter app with BLoC
-User: "/alfred:2-build MOBILE-001"
-Claude: (creates RED widget test, GREEN implementation with BLoC, REFACTOR)
+## Failure Modes
+- When the domain document does not exist or is ambiguous.
+- When the project strategy is unconfirmed and cannot be specified.
 
-### Example 2: React Native state management
-User: "React Native Redux 설정"
-Claude: (sets up Redux with TypeScript and async actions)
+## Dependencies
+- `.moai/project/` document and latest technical briefing are required.
+
+## References
+- Apple. "Human Interface Guidelines." https://developer.apple.com/design/human-interface-guidelines/ (accessed 2025-03-29).
+- Google. "Material Design." https://m3.material.io/ (accessed 2025-03-29).
+
+## Changelog
+- 2025-03-29: Codified input/output and failure responses for domain skills.
 
 ## Works well with
 
 - alfred-trust-validation (mobile testing)
 - dart-expert (Flutter development)
 - typescript-expert (React Native development)
+
+## Best Practices
+- Record supporting documentation (version/link) for each domain decision.
+- Review performance, security, and operational requirements simultaneously at an early stage.