腳本程式

[Code Quality] Evaluates risk level of proposed refactoring changes. Use to assess dependencies, blast radius, rollback difficulty, and determine if changes are safe to proceed.

This skill should be used when executing plan tasks autonomously, implementing features using TDD, running the red-green-refactor cycle, handling code review loops, or dealing with blocked tasks. Provides the autonomous TDD execution workflow.

PEP8、クリーンコード原則、Pythonのベストプラクティスに基づいてコード品質をチェック。Pythonプロジェクトでコード品質チェック、リント、フォーマットを依頼された時に使用。

Automatically capture Bash commands executed by Claude Code and convert them into documented, organized Makefile targets in .claude/makefiles/. Use when Claude executes any Bash command, when tempted to skip documentation ("too trivial", "one-time", "will do later"), or when user asks for Makefile generation. Process commands NOW while fresh, not later.

Analyzes Claude Code project structure detecting architectural patterns and anti-patterns by executing detection scripts

Python code linter and formatter for src/ directory

Generates LLM-optimized code context with function call graphs, side effect detection, and incremental updates. Processes JavaScript/TypeScript codebases to create compact semantic representations including multi-level summaries, entry point identification, and hash-based change tracking. Provides 74-97% token reduction compared to reading raw source files. Useful for understanding code architecture, debugging complex systems, reviewing pull requests, and onboarding to unfamiliar projects.

Use GitLab scripts instead of GitLab MCP for both read and write operations. Read operations (gitlab-mr-comments, gitlab-list-mrs) for fetching MR data. Write operations (gitlab-create-mr, gitlab-comment-mr, gitlab-inline-comment, gitlab-update-mr) for creating/updating MRs and posting inline code comments. Use when reviewing code, creating MRs, commenting on MRs, adding inline code review comments, updating MR metadata, listing MRs, or working with GitLab merge requests. Replaces 82 MCP functions (80k tokens) with lightweight bash scripts.

Execute Gray Swan Wave 3 MITM challenges across 10 challenges and 90 AI models using Playwright automation, tiered execution strategy, and compliance framing. Use for Wave 3 healthcare, critical infrastructure, WordPress, and web vulnerability challenges.

Expertise in deployment automation, container orchestration, and infrastructure as code. Activates when working with "deploy", "kubernetes", "docker", "terraform", "helm", "k8s", "container", or cloud infrastructure.

Python performance profiling with cProfile, line_profiler, memory_profiler, and py-spy. Covers profiling workflows, interpreting results, finding bottlenecks, memory leak detection, and optimization strategies. Use when code is slow, debugging performance issues, optimizing for production, or investigating memory usage.

数据分析助手，提供数据清洗、探索性分析（EDA）、统计分析、可视化图表生成等功能，支持Python（Pandas/NumPy/Matplotlib）和JavaScript（ECharts/D3.js），助力数据驱动决策。

Use this skill when creating new Claude Code skills from scratch, editing existing skills to improve their descriptions or structure, or converting Claude Code sub-agents to skills. This includes designing skill workflows, writing SKILL.md files, organizing supporting files with intention-revealing names, and leveraging CLI tools and Node.js scripting.

Add ADR references to code for decision traceability. Use when creating new files, documenting non-obvious implementation choices, or when user mentions ADR traceability, code reference, or document decision in code. Provides language-specific patterns for Python, TypeScript, Rust, Go.

This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to "configure opencode", "use opencode cli", "set up opencode", "opencode run command", "opencode model selection", "opencode providers", "opencode vertex ai", "opencode mcp servers", "opencode ollama", "opencode local models", "opencode deepseek", "opencode kimi", "opencode mistral", "fallback cli tool", or "headless llm cli". Covers command syntax, provider configuration, Vertex AI setup, MCP servers, local models, cloud providers, and subprocess integration patterns.

Claude Code native tools reference. Prefer native tools over bash commands for file operations, search, and orchestration.

Scaffolds a new Python agent for autonomous AI tasks in 'src/agents/'. Agents are autonomous components that handle complex operations (resume analysis, job matching, KSC generation). Use when asked to create a new AI agent or automation component.

Manage Google Drive files and folders with full CRUD operations via Ruby scripts. Use for file storage operations, folder organization, sharing permissions, searching across Drive, and uploading/downloading files of any type. Works seamlessly with google-sheets and google-docs skills for complete Google Workspace integration.

Intent-based code discovery for CLI AI agents using semantic search MCP tools. Use when finding code by what it does (not what it's called), exploring unfamiliar areas, or understanding feature implementations. Mandatory for code discovery tasks when you have MCP access.

Expert in Pyomo mathematical optimization modeling in Python - use for optimization problems, linear/nonlinear programming, constraint programming, and dynamic optimization