moai-adk 0.4.5__py3-none-any.whl → 0.20.1__py3-none-any.whl

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

@@ -1,95 +0,0 @@
----
-
-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-performance-optimizer/SKILL.md

@@ -1,105 +0,0 @@
----
-
-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

moai_adk/templates/.claude/skills/moai-alfred-refactoring-coach/SKILL.md

@@ -1,97 +0,0 @@
----
-
-name: moai-alfred-refactoring-coach
-description: Refactoring guidance with design patterns, code smells detection, and step-by-step improvement plans. Use when outlining refactor steps that preserve functionality.
-allowed-tools:
-  - Read
-  - Write
-  - Edit
-  - Bash
-  - TodoWrite
----
-
-# Alfred Refactoring Coach
-
-## 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 refactor lane |
-| Trigger cues | Refactoring retros, duplication cleanup, code health follow-ups inside Alfred. |
-
-## What it does
-
-Refactoring guidance with design pattern recommendations, code smell detection, and step-by-step improvement plans.
-
-## When to use
-
-- Activates when Alfred is asked to plan or stage refactoring work.
-- “Help with refactoring”, “How can I improve this code?”, “Apply design patterns” 
-- “Code organization”, “Remove duplication”, “Separate functions”
-
-## How it works
-
-**Refactoring Techniques**:
-- **Extract Method**: Separate long methods
-- **Replace Conditional with Polymorphism**: Remove conditional statements
-- **Introduce Parameter Object**: Group parameters
-- **Extract Class**: Massive class separation
-
-**Design Pattern Recommendations**:
-- Complex object creation → **Builder Pattern**
-- Type-specific behavior → **Strategy Pattern**
-- Global state → **Singleton Pattern**
-- Incompatible interfaces → **Adapter Pattern**
-- Delayed object creation → **Factory Pattern**
-
-**3-Strike Rule**:
-```
-1st occurrence: Just implement
-2nd occurrence: Notice similarity (leave as-is)
-3rd occurrence: Pattern confirmed → Refactor! 🔧
-```
-
-**Refactoring Checklist**:
-- [ ] All tests passing before refactoring
-- [ ] Code smells identified
-- [ ] Refactoring goal clear
-- [ ] Change one thing at a time
-- [ ] Run tests after each change
-- [ ] Commit frequently
-
-## 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
-- Fowler, Martin. "Refactoring: Improving the Design of Existing Code." Addison-Wesley, 2018.
-- IEEE Software. "Managing Technical Debt." IEEE Software, 2021.
-
-## 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-spec-metadata-validation/SKILL.md

@@ -1,97 +0,0 @@
----
-
-name: moai-alfred-spec-metadata-validation
-description: Validates SPEC YAML frontmatter (7 required fields) and HISTORY section compliance. Use when validating SPEC metadata for consistency.
-allowed-tools:
-  - Read
-  - Write
-  - Edit
-  - Bash
-  - TodoWrite
----
-
-# Alfred SPEC Metadata Validation
-
-## 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 spec validation |
-| Trigger cues | SPEC frontmatter checks, history table enforcement, metadata guardrails. |
-
-## What it does
-
-Validates SPEC document structure including YAML frontmatter (7 required fields) and HISTORY section compliance.
-
-## When to use
-
-- Activates when Alfred validates SPEC templates or enforces metadata standards.
-- "SPEC verification", "Metadata check", "SPEC structure check"
-- Automatically invoked by `/alfred:1-plan`
-- Before creating SPEC document
-
-## How it works
-
-**YAML Frontmatter Validation (7 required fields)**:
-- `id`: SPEC ID (e.g., AUTH-001)
-- `version`: Semantic Version (e.g., 0.0.1)
-- `status`: draft|active|completed|deprecated
-- `created`: YYYY-MM-DD format
-- `updated`: YYYY-MM-DD format
-- `author`: @{GitHub ID} format
-- `priority`: low|medium|high|critical
-
-**HISTORY Section Validation**:
-- Checks existence of HISTORY section
-- Verifies version history (INITIAL/ADDED/CHANGED/FIXED tags)
-- Validates author and date consistency
-
-**Format Validation**:
-```bash
-# Check required fields
-rg "^(id|version|status|created|updated|author|priority):" .moai/specs/SPEC-*/spec.md
-
-# Verify HISTORY section
-rg "^## HISTORY" .moai/specs/SPEC-*/spec.md
-```
-
-## 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
-- IEEE. "Software Requirements Specification Standard." IEEE 830-1998.
-- NASA. "Systems Engineering Handbook." https://www.nasa.gov/seh/ (accessed 2025-03-29).
-
-## Changelog
-- 2025-03-29: Added input/output/failure response to Alfred-specific skills.
-
-## Works well with
-
-- alfred-ears-authoring (SPEC writing guide)
-- alfred-tag-scanning (SPEC ID duplication check)
-
-## Reference
-
-SSOT (Single Source of Truth): `.moai/memory/spec-metadata.md`

moai_adk/templates/.claude/skills/moai-alfred-tag-scanning/SKILL.md

@@ -1,90 +0,0 @@
----
-
-name: moai-alfred-tag-scanning
-description: Scans all @TAG markers directly from code and generates TAG inventory (CODE-FIRST principle - no intermediate cache). Use when rebuilding the TAG inventory from live code.
-allowed-tools:
-  - Read
-  - Write
-  - Edit
-  - Bash
-  - TodoWrite
----
-
-# Alfred TAG Scanning
-
-## 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 traceability gate |
-| Trigger cues | Traceability scans, orphan TAG cleanup, TAG chain verification in Alfred. |
-
-## What it does
-
-Scans all @TAG markers (SPEC/TEST/CODE/DOC) directly from codebase and generates TAG inventory without intermediate caching (CODE-FIRST principle).
-
-## When to use
-
-- Activates when Alfred needs TAG inventories or chain verification.
-- "TAG Scan", "TAG List", "TAG Inventory"
-- Automatically invoked by `/alfred:3-sync`
-- “Find orphan TAG”, “Check TAG chain”
-
-## How it works
-
-**CODE-FIRST Scanning**:
-```bash
-# Direct code scan without intermediate cache
-rg '@(SPEC|TEST|CODE|DOC):' -n .moai/specs/ tests/ src/ docs/
-```
-
-**TAG Inventory Generation**:
-- Lists all TAGs with file locations
-- Detects orphaned TAGs (no corresponding SPEC/TEST/CODE)
-- Identifies broken links in TAG chain
-- Reports duplicate IDs
-
-**TAG Chain Verification**:
-- @SPEC → @TEST → @CODE → @DOC connection check
-- Ensures traceability across all artifacts
-
-## 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
-- BurntSushi. "ripgrep User Guide." https://github.com/BurntSushi/ripgrep/blob/master/GUIDE.md (accessed 2025-03-29).
-- ReqView. "Requirements Traceability Matrix Guide." https://www.reqview.com/doc/requirements-traceability-matrix/ (accessed 2025-03-29).
-
-## Changelog
-- 2025-03-29: Added input/output/failure response to Alfred-specific skills.
-
-## Works well with
-
-- alfred-trust-validation (TAG traceability verification)
-- alfred-spec-metadata-validation (SPEC ID validation)
-
-## Files included
-
-- templates/tag-inventory-template.md

moai_adk/templates/.claude/skills/moai-alfred-trust-validation/SKILL.md

@@ -1,99 +0,0 @@
----
-
-name: moai-alfred-trust-validation
-description: Validates TRUST 5-principles compliance (Test coverage 85%+, Code constraints, Architecture unity, Security, TAG trackability). Use when enforcing TRUST checkpoints before progression.
-allowed-tools:
-  - Read
-  - Write
-  - Edit
-  - Bash
-  - TodoWrite
----
-
-# Alfred TRUST Validation
-
-## 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 quality gate |
-| Trigger cues | TRUST checklist enforcement, release readiness scoring, risk gating. |
-
-## What it does
-
-Validates MoAI-ADK's TRUST 5-principles compliance to ensure code quality, testability, security, and traceability.
-
-## When to use
-
-- Activates when Alfred evaluates TRUST compliance before handoff.
-- "Check the TRUST principle", "Quality verification", "Check code quality"
-- Automatically invoked by `/alfred:3-sync`
-- Before merging PR or releasing
-
-## How it works
-
-**T - Test First**:
-- Checks test coverage ≥85% (pytest, vitest, go test, cargo test, etc.)
-- Verifies TDD cycle compliance (RED → GREEN → REFACTOR)
-
-**R - Readable**:
-- File ≤300 LOC
-- Function ≤50 LOC
-- Parameters ≤5
-- Cyclomatic complexity ≤10
-
-**U - Unified**:
-- SPEC-driven architecture consistency
-- Clear module boundaries
-- Language-specific standard structures
-
-**S - Secured**:
-- Input validation implementation
-- No hardcoded secrets
-- Access control applied
-
-**T - Trackable**:
-- TAG chain integrity (@SPEC → @TEST → @CODE → @DOC)
-- No orphaned TAGs
-- No duplicate SPEC IDs
-
-## 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
-- SonarSource. "Quality Gate: Developer's Guide." https://www.sonarsource.com/company/newsroom/white-papers/quality-gate/ (accessed 2025-03-29).
-- ISO/IEC 25010. "Systems and software quality models." (accessed 2025-03-29).
-
-## Changelog
-- 2025-03-29: Added input/output/failure response to Alfred-specific skills.
-
-## Works well with
-
-- alfred-tag-scanning (TAG traceability)
-- alfred-code-reviewer (code quality analysis)
-
-## Files included
-
-- templates/trust-report-template.md

moai_adk/templates/.claude/skills/moai-alfred-tui-survey/SKILL.md

@@ -1,87 +0,0 @@
----
-
-name: moai-alfred-tui-survey
-description: Standardizes Claude Code Tools AskUserQuestion TUI menus for surveys, branching approvals, and option picking across Alfred workflows. Use when gathering approvals or decisions via Alfred’s TUI menus.
-allowed-tools:
-  - Read
-  - Write
-  - Edit
-  - TodoWrite
----
-
-# Alfred TUI Survey Skill
-
-## Skill Metadata
-| Field | Value |
-| ----- | ----- |
-| Allowed tools | Read (read_file), Write (write_file), Edit (edit_file), TodoWrite (todo_write) |
-| Auto-load | On demand when AskUserQuestion menus are built |
-| Trigger cues | Branch approvals, survey menus, decision gating via AskUserQuestion. |
-
-## What it does
-
-Provides ready-to-use patterns for Claude Code's AskUserQuestion TUI selector so Alfred agents can gather user choices, approvals, or survey answers with structured menus instead of ad-hoc text prompts.
-
-## When to use
-
-- Activates when Alfred needs to gather structured choices through the TUI selector.
-- Need confirmation before advancing to a risky/destructive step.
-- Choosing between alternative implementation paths or automation levels.
-- Collecting survey-like answers (persona, tech stack, priority, risk level).
-- Any time a branched workflow depends on user-selected options rather than free-form text.
-
-## How it works
-
-1. **Detect gate** – Pause at steps that require explicit user choice.
-2. **Shape options** – Offer 2–5 focused choices with concise labels.
-3. **Render menu** – Emit the `AskUserQuestion({...})` block for the selector.
-4. **Map follow-ups** – Note how each option alters the next action/agent.
-5. **Fallback** – Provide plain-text instructions when the UI cannot render.
-
-### Templates & examples
-
-- [Single-select deployment decision](examples.md#single-select-template)
-- [Multi-select diagnostics checklist](examples.md#multi-select-variation)
-- [Follow-up drill-down prompt](examples.md#follow-up-prompt-for-deeper-detail)
-
-## Best Practices
-- Reduce context switching by putting questions, options, and follow-up actions on one screen.
-- Options are sorted according to comparison criteria such as risk and priority.
-- If safety measures are required, such as approval/suspension/cancellation, attach a warning message.
-- Submission results are recorded for reuse in the Sync step or reports.
-
-## Inputs
-- Decision scenarios and candidate options collected by Alfred workflows.
-- Definition of follow-up actions for each option (next command, subagent, TODO, etc.).
-
-## Outputs
-- AskUserQuestion block and choice → follow-up action mapping.
-- Summary of selection results and TODO items that require further confirmation.
-
-## Failure Modes
-- Ambiguous or duplicate options cause selection delays.
-- It is difficult to judge priorities when all options look the same.
-- AskUserQuestion does not work in a TUI-inactive environment, so plan B is needed.
-
-## Dependencies
-- Works with the main `/alfred:*` command and schedules follow-up actions with TodoWrite when necessary.
-- When combined with moai-foundation-ears · moai-foundation-tags, requirements → options → TAG records are connected.
-
-## References
-- Jakubovic, J. "Designing Effective CLI Dialogs." ACM Queue, 2021.
-- NCurses. "Programming Guide." https://invisible-island.net/ncurses/man/ncurses.3x.html (accessed 2025-03-29).
-
-## Changelog
-- 2025-03-29: Added input/output/failure response to Alfred-specific skills.
-
-## Works well with
-
-- `moai-foundation-ears` – Combine structured requirement patterns with menu-driven confirmations.
-- `moai-alfred-git-workflow` – Use menus to choose branch/worktree strategies.
-- `moai-alfred-code-reviewer` – Capture reviewer focus areas through guided selection.
-
-## Examples
-```markdown
-- In the `/alfred:1-plan` step, user priorities are collected and the results are written to the PLAN board.
-- Check user approval before high-risk operations while running `/alfred:2-run`.
-```