Git & Version Control

MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows

Generate comprehensive documentation including API docs, comments, and README

GitHub 設定ファイルをセットアップする。「GitHub 設定をセットアップ」「.github を作って」「Issue テンプレート作成」「PR テンプレート作成」「GitHub 設定を初期化」「リポジトリ設定をセットアップ」「ラベル設定を作成」などで起動。.github ディレクトリに必要な設定ファイルを一括生成。

CodeGenAgent スキル - Claude Sonnet 4によるAI駆動コード生成。GitHub Issueの内容を解析し、TypeScriptコード・ユニットテスト・型定義を自動生成。Use when:- 新しいコードを生成する時- Issue内容からコード実装が必要な時- TypeScript/Vitestテストの自動生成が必要な時- BaseAgentパターンに従った実装が必要な時- "コード生成", "実装", "feature", "bug fix" がキーワードに含まれる時

Automatically detects GitHub PR mentions (URLs,

This skill should be used when the user asks about "github issue workflow", "organize issues with milestones", "manage github project", "issue hierarchy", "sub-issues", "milestone planning", "PR workflow", "issue triage", "git commit", "create PR", "work on issues", "autonomous issue resolution", or needs guidance on GitHub issue management, milestone organization, commit workflows, PR creation, or automated issue workflows.

Kailash Kaizen - production-ready AI agent framework with signature-based programming, multi-agent coordination, and enterprise features. Use when asking about 'AI agents', 'agent framework', 'BaseAgent', 'multi-agent systems', 'agent coordination', 'signatures', 'agent signatures', 'RAG agents', 'vision agents', 'audio agents', 'multimodal agents', 'agent prompts', 'prompt optimization', 'chain of thought', 'ReAct pattern', 'Planning agent', 'PEV agent', 'Tree-of-Thoughts', 'pipeline patterns', 'supervisor-worker', 'router pattern', 'ensemble pattern', 'blackboard pattern', 'parallel execution', 'agent-to-agent communication', 'A2A protocol', 'streaming agents', 'agent testing', 'agent memory', 'agentic workflows', 'AgentRegistry', 'OrchestrationRuntime', 'distributed agents', 'agent registry', '100+ agents', 'capability discovery', 'fault tolerance', 'health monitoring', 'trust protocol', 'EATP', 'TrustedAgent', 'trust chains', 'secure messaging', 'enterprise trust', 'credential rotation', 'trust verificati

Use this skill when asked about "hooks", "PreToolUse", "PostToolUse", "SessionStart", "hook events", "validate tool use", "block commands", "add context on session start", or implementing event-driven automation.

Coordinate all freight intelligence gathering and campaign execution for systematic RFP inclusion. Use for daily workflow planning, weekly analysis, lead prioritization, and orchestrating all intelligence activities across job postings, RFP detection, competitor analysis, and campaigns.

Automatically bridge long technical sessions to keep context window small and costs low. Extracts key technical decisions, resolved bugs, active tasks, and essential code snippets from conversation history into a compact markdown summary (2,000–5,000 tokens). Use when reaching a project phase milestone, when Claude warns the context window is getting full, or to start a fresh session with minimal token cost while maintaining continuity.

Generate comprehensive test suites following the test pyramid: static analysis → unit → integration → E2E.LOAD THIS SKILL WHEN: User says "寫測試", "test", "測試", "TG", "coverage", "覆蓋率", "pytest", "unittest", "驗證" | wants test generation | asks about testing strategy | needs coverage report | code review requires tests | before release/deployment.CAPABILITIES: pytest configuration, mypy/ruff/bandit static analysis, parametrized tests, fixtures/conftest, async testing, httpx API tests, Playwright E2E, coverage reports (pytest-cov), CI integration, test data factories (factory-boy/faker).

Generate Claude Code configuration files (commands, agents, skills, settings.json) with proper YAML frontmatter and structure. Use when creating .claude/ configuration or .md files in .claude/commands/ or .claude/agents/ directories.

Type hints, dataclasses, async patterns, testing with pytest, and modern Python tooling

Build production-grade agentic workflows with LangGraph using graph-based orchestration, state machines, human-in-the-loop, and advanced control flow

Set up hk (git hook manager) with pre-commit hooks for any project. Detects project type (Python, JS/TS, Go, Rust, etc.) and configures appropriate linters/formatters. Use when user wants to add pre-commit hooks, set up hk, or configure linting for a project.

Design and manage TraitorSim agent archetypes with OCEAN personality traits, stat biases, and gameplay profiles. Use when creating new archetypes, modifying personality traits, defining character types, or when asked about archetype design, OCEAN traits, Big Five personality, or character templates.

Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.

Automatically generate Medium-style technical articles from projects, achievements, or workflows with consistent authentic voice and structure. Use when user invokes /write-medium-article.

Manage git worktree lifecycle for parallel development. Create worktrees with port isolation, manage multiple branches simultaneously, clean up worktrees. CRITICAL: Use /create_worktree command, never manual git worktree commands. Ports auto-calculated to avoid conflicts.

OpenAI API development patterns, SDK usage, chat completions, tool use, and best practices.