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

moai_adk/templates/.claude/skills/moai-alfred-code-reviewer/SKILL.md

@@ -0,0 +1,112 @@
+---
+
+name: moai-alfred-code-reviewer
+description: Automated code review with language-specific best practices, SOLID principles, and actionable improvement suggestions. Use when reviewing code changes for issues and strengths.
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - TodoWrite
+---
+
+# Alfred Code Reviewer
+
+## Skill Metadata
+| Field | Value |
+| ----- | ----- |
+| Allowed tools | Read (read_file), Write (write_file), Edit (edit_file), Bash (terminal), TodoWrite (todo_write) |
+| Auto-load | /alfred:3-sync review phase |
+| Trigger cues | Alfred-driven review summaries, diff inspection, merge gate decisions. |
+
+## What it does
+
+Automated code review with language-specific best practices, SOLID principles verification, and code smell detection.
+
+## When to use
+
+- Activates when Alfred needs to summarize diffs or prepare merge feedback.
+- “Please review the code”, “How can this code be improved?”, “Check the code quality”
+- Optionally invoked after `/alfred:3-sync`
+- Before merging PR
+
+## How it works
+
+**Code Constraints Check**:
+- File ≤300 LOC
+- Function ≤50 LOC
+- Parameters ≤5
+- Cyclomatic complexity ≤10
+
+**SOLID Principles**:
+- Single Responsibility
+- Open/Closed
+- Liskov Substitution
+- Interface Segregation
+- Dependency Inversion
+
+**Code Smell Detection**:
+- Long Method
+- Large Class
+- Duplicate Code
+- Dead Code
+- Magic Numbers
+
+**Language-specific Best Practices**:
+- Python: List comprehension, type hints, PEP 8
+- TypeScript: Strict typing, async/await, error handling
+- Java: Streams API, Optional, Design patterns
+
+**Review Report**:
+```markdown
+## Code Review Report
+
+### 🔴 Critical Issues (3)
+1. **src/auth/service.py:45** - Function too long (85 > 50 LOC)
+2. **src/api/handler.ts:120** - Missing error handling
+3. **src/db/repository.java:200** - Magic number
+
+### ⚠️ Warnings (5)
+1. **src/utils/helper.py:30** - Unused import
+
+### ✅ Good Practices Found
+- Test coverage: 92%
+- Consistent naming
+```
+
+## Best Practices
+- The text shown to the user is written using TUI/report expressions.
+- When running the tool, a summary of commands and results are recorded.
+
+## Examples
+```markdown
+- Call this skill inside the /alfred command to generate a report.
+- Add summary to Completion Report.
+```
+
+## Inputs
+- MoAI-ADK project context (`.moai/project/`, `.claude/` templates, etc.).
+- Parameters passed from user commands or higher commands.
+
+## Outputs
+- Reports, checklists or recommendations for your Alfred workflow.
+- Structured data for subsequent subagent calls.
+
+## Failure Modes
+- When required input documents are missing or permissions are limited.
+- When disruptive changes are required without user approval.
+
+## Dependencies
+- Cooperation with higher-level agents such as cc-manager and project-manager is required.
+
+## References
+- Google. "Code Review Developer Guide." https://google.github.io/eng-practices/review/ (accessed 2025-03-29).
+- IEEE. "Code Review Best Practices." IEEE Software, 2022.
+
+## Changelog
+- 2025-03-29: Added input/output/failure response to Alfred-specific skills.
+
+## Works well with
+
+- alfred-trust-validation
+- alfred-refactoring-coach

moai_adk/templates/.claude/skills/moai-alfred-debugger-pro/SKILL.md

@@ -0,0 +1,103 @@
+---
+
+name: moai-alfred-debugger-pro
+description: Advanced debugging support with stack trace analysis, error pattern detection, and fix suggestions. Use when unraveling complex runtime errors or stack traces.
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - TodoWrite
+---
+
+# Alfred Debugger Pro
+
+## Skill Metadata
+| Field | Value |
+| ----- | ----- |
+| Allowed tools | Read (read_file), Write (write_file), Edit (edit_file), Bash (terminal), TodoWrite (todo_write) |
+| Auto-load | Triggered by Alfred debug-helper |
+| Trigger cues | Runtime failures surfaced in Alfred runs, stack trace walkthroughs, hotfix triage. |
+
+## What it does
+
+Advanced debugging support with stack trace analysis, common error pattern detection, and actionable fix suggestions.
+
+## When to use
+
+- Activates when Alfred encounters runtime errors and needs guided debugging steps.
+- “Resolve the error”, “What is the cause of this error?”, “Stack trace analysis”
+- Automatically invoked on runtime errors (via debug-helper sub-agent)
+- "Why not?", "Solving NullPointerException"
+
+## How it works
+
+**Stack Trace Analysis**:
+```python
+# Error example
+jwt.exceptions.ExpiredSignatureError: Signature has expired
+
+# Alfred Analysis
+📍 Error Location: src/auth/service.py:142
+🔍 Root Cause: JWT token has expired
+💡 Fix Suggestion:
+   1. Implement token refresh logic
+   2. Check expiration before validation
+   3. Handle ExpiredSignatureError gracefully
+```
+
+**Common Error Patterns**:
+- `NullPointerException` → Optional usage, guard clauses
+- `IndexError` → Boundary checks
+- `KeyError` → `.get()` with defaults
+- `TypeError` → Type hints, input validation
+- `ConnectionError` → Retry logic, timeouts
+
+**Debugging Checklist**:
+- [ ] Reproducible?
+- [ ] Log messages?
+- [ ] Input data?
+- [ ] Recent changes?
+- [ ] Dependency versions?
+
+**Language-specific Tips**:
+- **Python**: Logging, type guards
+- **TypeScript**: Type guards, null checks
+- **Java**: Optional, try-with-resources
+
+## Best Practices
+- The text shown to the user is written using TUI/report expressions.
+- When running the tool, a summary of commands and results are recorded.
+
+## Examples
+```markdown
+- Call this skill inside the /alfred command to generate a report.
+- Add summary to Completion Report.
+```
+
+## Inputs
+- MoAI-ADK project context (`.moai/project/`, `.claude/` templates, etc.).
+- Parameters passed from user commands or higher commands.
+
+## Outputs
+- Reports, checklists or recommendations for your Alfred workflow.
+- Structured data for subsequent subagent calls.
+
+## Failure Modes
+- When required input documents are missing or permissions are limited.
+- When disruptive changes are required without user approval.
+
+## Dependencies
+- Cooperation with higher-level agents such as cc-manager and project-manager is required.
+
+## References
+- Microsoft. "Debugging Techniques." https://learn.microsoft.com/visualstudio/debugger/ (accessed 2025-03-29).
+- JetBrains. "Debugging Code." https://www.jetbrains.com/help/idea/debugging-code.html (accessed 2025-03-29).
+
+## Changelog
+- 2025-03-29: Added input/output/failure response to Alfred-specific skills.
+
+## Works well with
+
+- alfred-code-reviewer
+- alfred-trust-validation

moai_adk/templates/.claude/skills/moai-alfred-ears-authoring/SKILL.md

@@ -0,0 +1,103 @@
+---
+
+name: moai-alfred-ears-authoring
+description: EARS (Easy Approach to Requirements Syntax) authoring guide with 5 statement patterns for clear, testable requirements. Use when generating EARS-style requirement sentences.
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - TodoWrite
+---
+
+# Alfred EARS Authoring Guide
+
+## Skill Metadata
+| Field | Value |
+| ----- | ----- |
+| Allowed tools | Read (read_file), Write (write_file), Edit (edit_file), Bash (terminal), TodoWrite (todo_write) |
+| Auto-load | /alfred:1-plan requirements phase |
+| Trigger cues | Plan board EARS drafting, requirement interviews, structured SPEC authoring. |
+
+## What it does
+
+EARS (Easy Approach to Requirements Syntax) authoring guide for writing clear, testable requirements using 5 statement patterns.
+
+## When to use
+
+- Activates when Alfred is asked to capture requirements using the EARS patterns.
+- “Writing SPEC”, “Requirements summary”, “EARS syntax”
+- Automatically invoked by `/alfred:1-plan`
+- When writing or refining SPEC documents
+
+## How it works
+
+EARS provides 5 statement patterns for structured requirements:
+
+### 1. Ubiquitous (Basic Requirements)
+**Format**: The system must provide [function]
+**Example**: The system must provide user authentication function
+
+### 2. Event-driven (event-based)
+**Format**: WHEN If [condition], the system must [operate]
+**Example**: WHEN When the user logs in, the system must issue a JWT token
+
+### 3. State-driven
+**Format**: WHILE When in [state], the system must [operate]
+**Example**: WHILE When the user is authenticated, the system must allow access to protected resources
+
+### 4. Optional (Optional function)
+**Format**: If WHERE [condition], the system can [operate]
+**Example**: If WHERE refresh token is provided, the system can issue a new access token
+
+### 5. Constraints
+**Format**: IF [condition], the system SHOULD [constrain]
+**Example**: IF an invalid token is provided, the system SHOULD deny access
+
+## Writing Tips
+
+✅ Be specific and measurable
+✅ Avoid vague terms (“adequate”, “sufficient”, “fast”)
+✅ One requirement per statement
+✅ Make it testable
+
+## Best Practices
+- The text shown to the user is written using TUI/report expressions.
+- When running the tool, a summary of commands and results are recorded.
+
+## Examples
+```markdown
+- Call this skill inside the /alfred command to generate a report.
+- Add summary to Completion Report.
+```
+
+## Inputs
+- MoAI-ADK project context (`.moai/project/`, `.claude/` templates, etc.).
+- Parameters passed from user commands or higher commands.
+
+## Outputs
+- Reports, checklists or recommendations for your Alfred workflow.
+- Structured data for subsequent subagent calls.
+
+## Failure Modes
+- When required input documents are missing or permissions are limited.
+- When disruptive changes are required without user approval.
+
+## Dependencies
+- Cooperation with higher-level agents such as cc-manager and project-manager is required.
+
+## References
+- Mavin, A., et al. "Easy Approach to Requirements Syntax (EARS)." IEEE RE, 2009.
+- INCOSE. "Guide for Writing Requirements." INCOSE-TP-2010-006-02 (accessed 2025-03-29).
+
+## Changelog
+- 2025-03-29: Added input/output/failure response to Alfred-specific skills.
+
+## Works well with
+
+- alfred-spec-metadata-validation
+- alfred-trust-validation
+
+## Reference
+
+`.moai/memory/development-guide.md#ears-requirements-how-to`

moai_adk/templates/.claude/skills/moai-alfred-git-workflow/SKILL.md

@@ -0,0 +1,95 @@
+---
+
+name: moai-alfred-git-workflow
+description: Automates Git operations with MoAI-ADK conventions (feature branch, locale-based TDD commits, Draft PR, PR Ready transition). Use when orchestrating GitFlow checkpoints, commits, or PR transitions.
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - TodoWrite
+---
+
+# Alfred Git Workflow
+
+## Skill Metadata
+| Field | Value |
+| ----- | ----- |
+| Allowed tools | Read (read_file), Write (write_file), Edit (edit_file), Bash (terminal), TodoWrite (todo_write) |
+| Auto-load | /alfred:2-run Git automation |
+| Trigger cues | Branch provisioning, commit batching, draft PR preparation within Alfred flows. |
+
+## What it does
+
+Automates Git operations following MoAI-ADK conventions: branch creation, locale-based TDD commits, Draft PR creation, and PR Ready transition.
+
+## When to use
+
+- Activates when Alfred must manage branches, commits, or PR transitions.
+- “Create branch”, “Create PR”, “Create commit”
+- Automatically invoked by `/alfred:1-plan`, `/alfred:2-run`, `/alfred:3-sync`
+- Git workflow automation needed
+
+## How it works
+
+**1. Branch Creation**:
+```bash
+git checkout develop
+git checkout -b feature/SPEC-AUTH-001
+```
+
+**2. Locale-based TDD Commits**:
+- **Korean (ko)**: 🔴 RED: [Test Description]
+- **English (en)**: 🔴 RED: [Test description]
+- **Japanese (ja)**: 🔴 RED: [テスト説明]
+- **Chinese (zh)**: 🔴 RED: [测试说明]
+
+Configured via `.moai/config.json`:
+```json
+{"project": {"locale": "ko"}}
+```
+
+**3. Draft PR Creation**:
+Creates Draft PR with SPEC reference and test checklist.
+
+**4. PR Ready Transition** (via `/alfred:3-sync`):
+- Updates PR from Draft → Ready
+- Adds quality gate checklist
+- Verifies TRUST 5-principles
+
+## Best Practices
+- The text shown to the user is written using TUI/report expressions.
+- When running the tool, a summary of commands and results are recorded.
+
+## Examples
+```markdown
+- Call this skill inside the /alfred command to generate a report.
+- Add summary to Completion Report.
+```
+
+## Inputs
+- MoAI-ADK project context (`.moai/project/`, `.claude/` templates, etc.).
+- Parameters passed from user commands or higher commands.
+
+## Outputs
+- Reports, checklists or recommendations for your Alfred workflow.
+- Structured data for subsequent subagent calls.
+
+## Failure Modes
+- When required input documents are missing or permissions are limited.
+- When disruptive changes are required without user approval.
+
+## Dependencies
+- Cooperation with higher-level agents such as cc-manager and project-manager is required.
+
+## References
+- Vincent Driessen. "A successful Git branching model." https://nvie.com/posts/a-successful-git-branching-model/ (accessed 2025-03-29).
+- GitHub Docs. "GitHub Flow." https://docs.github.com/en/get-started/using-github/github-flow (accessed 2025-03-29).
+
+## Changelog
+- 2025-03-29: Added input/output/failure response to Alfred-specific skills.
+
+## Works well with
+
+- alfred-ears-authoring (SPEC ID-based branch naming)
+- alfred-trust-validation (PR Ready quality check)

moai_adk/templates/.claude/skills/moai-alfred-language-detection/SKILL.md

@@ -0,0 +1,99 @@
+---
+
+name: moai-alfred-language-detection
+description: Detects the project’s primary language/runtime and recommends default testing tooling when initializing or planning workflows. Use when sizing up the project language and default tooling.
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - TodoWrite
+---
+
+# Alfred Language Detection
+
+## Skill Metadata
+| Field | Value |
+| ----- | ----- |
+| Allowed tools | Read (read_file), Write (write_file), Edit (edit_file), Bash (terminal), TodoWrite (todo_write) |
+| Auto-load | /alfred:0-project bootstrap |
+| Trigger cues | Repository language probing, framework detection, tooling recommendation via Alfred. |
+
+## What it does
+
+Automatically detects project's primary language and framework by scanning configuration files, then recommends appropriate testing tools and linters.
+
+## When to use
+
+- Activates when Alfred needs to detect project languages or recommend toolchains.
+- "Detect language", "Check project language", "Recommend testing tools"
+- Automatically invoked by `/alfred:0-project`, `/alfred:2-run`
+- Setting up new project
+
+## How it works
+
+**Configuration File Scanning**:
+- `package.json` → TypeScript/JavaScript (Jest/Vitest, ESLint/Biome)
+- `pyproject.toml` → Python (pytest, ruff, black)
+- `Cargo.toml` → Rust (cargo test, clippy, rustfmt)
+- `go.mod` → Go (go test, golint, gofmt)
+- `Gemfile` → Ruby (RSpec, RuboCop)
+- `pubspec.yaml` → Dart/Flutter (flutter test, dart analyze)
+- `build.gradle` → Java/Kotlin (JUnit, Checkstyle)
+- `Package.swift` → Swift (XCTest, SwiftLint)
+
+**Toolchain Recommendation**:
+```json
+{
+  "language": "Python",
+  "test_framework": "pytest",
+  "linter": "ruff",
+  "formatter": "black",
+  "type_checker": "mypy",
+  "package_manager": "uv"
+}
+```
+
+**Framework Detection**:
+- **Python**: FastAPI, Django, Flask
+- **TypeScript**: React, Next.js, Vue
+- **Java**: Spring Boot, Quarkus
+
+**Supported Languages**: Python, TypeScript, Java, Go, Rust, Ruby, Dart, Swift, Kotlin, PHP, C#, C++, Elixir, Scala, Clojure (20+ languages)
+
+## Best Practices
+- The text shown to the user is written using TUI/report expressions.
+- When running the tool, a summary of commands and results are recorded.
+
+## Examples
+```markdown
+- Call this skill inside the /alfred command to generate a report.
+- Add summary to Completion Report.
+```
+
+## Inputs
+- MoAI-ADK project context (`.moai/project/`, `.claude/` templates, etc.).
+- Parameters passed from user commands or higher commands.
+
+## Outputs
+- Reports, checklists or recommendations for your Alfred workflow.
+- Structured data for subsequent subagent calls.
+
+## Failure Modes
+- When required input documents are missing or permissions are limited.
+- When disruptive changes are required without user approval.
+
+## Dependencies
+- Cooperation with higher-level agents such as cc-manager and project-manager is required.
+
+## References
+- GitHub Linguist. "Programmatic language detection." https://github.com/github-linguist/linguist (accessed 2025-03-29).
+- JetBrains. "Project language insights." https://www.jetbrains.com/help/idea/project-tool-window.html (accessed 2025-03-29).
+
+## Changelog
+- 2025-03-29: Added input/output/failure response to Alfred-specific skills.
+
+## Works well with
+
+- alfred-trust-validation (language-specific tool verification)
+- alfred-code-reviewer (language-specific review criteria)

moai_adk/templates/.claude/skills/moai-alfred-performance-optimizer/SKILL.md

@@ -0,0 +1,105 @@
+---
+
+name: moai-alfred-performance-optimizer
+description: Performance analysis and optimization suggestions with profiling, bottleneck detection, and language-specific optimizations. Use when planning performance improvements or regressions checks.
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - TodoWrite
+---
+
+# Alfred Performance Optimizer
+
+## Skill Metadata
+| Field | Value |
+| ----- | ----- |
+| Allowed tools | Read (read_file), Write (write_file), Edit (edit_file), Bash (terminal), TodoWrite (todo_write) |
+| Auto-load | /alfred:2-run performance lane |
+| Trigger cues | Performance regressions surfaced in Alfred workflows, profiling or tuning requests. |
+
+## What it does
+
+Performance analysis and optimization with profiling tools, bottleneck detection, and language-specific optimization techniques.
+
+## When to use
+
+- Activates when Alfred must diagnose or remediate performance bottlenecks.
+- “Improve performance”, “Find slow parts”, “How to optimize?”
+- “Profiling”, “Bottleneck”, “Memory leak”
+
+## How it works
+
+**Profiling Tools**:
+- **Python**: cProfile, memory_profiler
+- **TypeScript**: Chrome DevTools, clinic.js
+- **Java**: JProfiler, VisualVM
+- **Go**: pprof
+- **Rust**: flamegraph, criterion
+
+**Common Performance Issues**:
+- **N+1 Query Problem**: Use eager loading/joins
+- **Inefficient Loop**: O(n²) → O(n) with Set/Map
+- **Memory Leak**: Remove event listeners, close connections
+
+**Optimization Checklist**:
+- [ ] Current performance benchmark
+- [ ] Bottleneck identification
+- [ ] Profiling data collected
+- [ ] Algorithm complexity improved (O(n²) → O(n))
+- [ ] Unnecessary operations removed
+- [ ] Caching applied
+- [ ] Async processing introduced
+- [ ] Post-optimization benchmark
+- [ ] Side effects checked
+
+**Language-specific Optimizations**:
+- **Python**: List comprehension, generators, @lru_cache
+- **TypeScript**: Memoization, lazy loading, code splitting
+- **Java**: Stream API, parallel processing
+- **Go**: Goroutines, buffered channels
+- **Rust**: Zero-cost abstractions, borrowing
+
+**Performance Targets**:
+- API response time: <200ms (P95)
+- Page load time: <2s
+- Memory usage: <512MB
+- CPU usage: <70%
+
+## Best Practices
+- The text shown to the user is written using TUI/report expressions.
+- When running the tool, a summary of commands and results are recorded.
+
+## Examples
+```markdown
+- Call this skill inside the /alfred command to generate a report.
+- Add summary to Completion Report.
+```
+
+## Inputs
+- MoAI-ADK project context (`.moai/project/`, `.claude/` templates, etc.).
+- Parameters passed from user commands or higher commands.
+
+## Outputs
+- Reports, checklists or recommendations for your Alfred workflow.
+- Structured data for subsequent subagent calls.
+
+## Failure Modes
+- When required input documents are missing or permissions are limited.
+- When disruptive changes are required without user approval.
+
+## Dependencies
+- Cooperation with higher-level agents such as cc-manager and project-manager is required.
+
+## References
+- Google SRE. "The Four Golden Signals." https://sre.google/sre-book/monitoring-distributed-systems/ (accessed 2025-03-29).
+- Dynatrace. "Application Performance Monitoring Best Practices." https://www.dynatrace.com/resources/ebooks/ (accessed 2025-03-29).
+
+## Changelog
+- 2025-03-29: Added input/output/failure response to Alfred-specific skills.
+
+## Works well with
+
+- alfred-code-reviewer
+- alfred-debugger-pro