Git 與版本控制

Optimize system prompts for Claude Code agents using proven prompt engineering patterns. Use when users request prompt improvement, optimization, or refinement for agent workflows, tool instructions, or system behaviors.

Pulumi infrastructure as code using Python with Pulumi Cloud and ESC integration. Use when working with Pulumi Python projects, ESC environments, dynamic secrets, OIDC credentials, or infrastructure automation with Python.

Repository structure optimization and multi-repo management with swarm coordination for scalable project architecture and development workflows. Use for structure analysis, template management, cross-repo synchronization, and architecture recommendations.

Defines the standard 8-category taxonomy for classifying project files: Config, Tests, Docs, Scripts, Source Code, Data, AI Tooling, and Other. REFERENCE THIS SKILL whenever categorizing files, auditing project structure, or answering 'what types of files are here.' Apply these categories and patterns whether using the bundled script or manual analysis.

Core implementation logic for working on a single GitHub issue. Used by both /work command and /work-all subagents to ensure consistent behavior.

Expert in voice synthesis, TTS, voice cloning, podcast production, speech processing, and voice UI design via ElevenLabs integration. Specializes in vocal clarity, loudness standards (LUFS), de-essing, dialogue mixing, and voice transformation. Activate on 'TTS', 'text-to-speech', 'voice clone', 'voice synthesis', 'ElevenLabs', 'podcast', 'voice recording', 'speech-to-speech', 'voice UI', 'audiobook', 'dialogue'. NOT for spatial audio (use sound-engineer), music production (use DAW tools), game audio middleware (use sound-engineer), sound effects generation (use sound-engineer with ElevenLabs SFX), or live concert audio.

This skill should be used when the user asks to "implement with TDD", "write tests first", "do test-driven development", or as Phase 3 of the /dev workflow. Enforces RED-GREEN-REFACTOR cycle with mandatory test-first approach.

Standard agent pipelines for audit, coding, new project, refactor, and simple workflows. Defines 5 workflow types with specific agent sequences (AUDIT: BA→PM→Workers→Reviewer→PM, CODING: Architect→PM→Workers→Validator→Reviewer→PM, NEW_PROJECT and REFACTOR follow coding pipeline, SIMPLE: direct processing). Includes agent contracts, workflow detection logic, and orchestration best practices. Use when /ms command needs to determine workflow type and coordinate multi-agent execution.

Financial close acceleration, reconciliation automation, and audit readiness for controllers managing month-end/quarter-end close processes

Git Worktree Isolation - safe feature development in isolated workspaces

Provides Git version control operations for managing code repositories. Allows agents to check repository status, view commit history, and perform basic Git operations.

Comprehensive Bun runtime expertise covering all major features.Use when working with Bun projects, migrating from Node.js, or leveraging Bun-specific APIs.Activates for: Bun.serve, Bun.file, bun:test, bun:sqlite, bun install, bun build,bunfig.toml, TypeScript in Bun, package manager operations, bundler configuration,and Node.js compatibility questions.

Create compelling demo narratives, flows, and presenter scripts for CustomGPT.ai Labs projects using existing demo links, project docs, and Innovation context.

Automatically designs, initializes, implements, validates, and packages new skills from a single high-level request. Use when the user gives a short, possibly vague description like "社内Redshift向けのSQLヘルパースキル作って" and wants a complete, production-ready .skill file generated with minimal manual intervention.

プロジェクトの .claude/settings.local.json を更新する。「ローカル設定を更新して」「local settings を変更」「個人用設定を変えて」「自分だけの設定」「ローカル permissions を追加」「個人設定ファイルを編集」「settings.local を更新」などで起動。Git にコミットされない個人用の Claude Code 設定を管理。

A2A agent card JSON templates with schema validation and examples for different agent types. Use when creating agent cards, implementing A2A protocol discovery, setting up agent metadata, configuring authentication schemes, defining agent capabilities, or when user mentions agent card, agent discovery, A2A metadata, service endpoint configuration, or agent authentication setup.

Enrich a Github [DB] entry with GitHub API metadata (description, stars, language, cover image). Use when user wants to populate a GitHub repo entry with live metadata, enhance github entry, or add github info.

Scan ~/dev recursively for git repos and report today's work with commits, branches, stats, and detailed change analysis. Use when user asks "what did I work on", "show my work", "daily summary", "what repos did I touch".

Unified markdown and skill management specialist providing document quality enforcement (structure, c7score, style), content optimization for AI assistants, and complete skill creation workflow (scaffolding, validation, packaging).

Create new workflow nodes for the Workscript engine or refactor existing nodes. Generate complete, production-ready node implementations following the single-edge return pattern. Use when creating new nodes, developing custom integrations, building data manipulation nodes, refactoring existing nodes, or implementing workflow capabilities.