Git 與版本控制

N-version programming for critical implementations - generates N independent solutions and selects the best through comparison

Guides architects on when and how to use goal-seeking agents as a design pattern.This skill helps evaluate whether autonomous agents are appropriate for a givenproblem, how to structure their objectives, integrate with goal_agent_generator,and reference real amplihack examples like AKS SRE automation, CI diagnostics,pre-commit workflows, and fix-agent pattern matching.

Use for running and editing notebooks efficiently via jtool/Jupyter; prefers uv for deps and headless execution.

Use when building JavaScript applications with modern ES2023+ features, async patterns, or Node.js development. Invoke for vanilla JavaScript, browser APIs, performance optimization, module systems. Keywords: JavaScript, ES2023, async, Node.js, Fetch API, Web Workers.

Specialized Native AOT, trimming, and optimization expert for morphir-dotnet. Expert in single-file trimmed executables, AOT compilation, size optimization, and guiding toward AOT-compatible features. Use when troubleshooting compilation, diagnosing trimming issues, optimizing binary size, implementing reflection workarounds, or maintaining best practices. Triggers include "AOT", "Native AOT", "trimming", "single-file", "size optimization", "reflection error", "IL2026", "IL3050", "PublishAot", "PublishTrimmed", "source generator", "Myriad".

Generate a concise commit message by analyzing git diff changes

Convert Obsidian WikiLinks ([[...]]) to standard Markdown links ([...](...)) for GitHub compatibility. This skill should be used when users need to make README files or other Markdown documents GitHub-compatible while maintaining Obsidian functionality, or when batch converting WikiLinks across multiple files.

Use when building TypeScript applications requiring advanced type systems, generics, or full-stack type safety. Invoke for type guards, utility types, tRPC integration, monorepo setup. Keywords: TypeScript, generics, type safety, tRPC, tsconfig.

Comprehensive codebase quality audit with parallel agent orchestration, GitHub issue creation, automated PR generation per issue, and PM-prioritized recommendations. Use for code review, refactoring audits, technical debt analysis, module quality assessment, or codebase health checks.

Use when aligning with Georgios’s default Git/GitHub conventions—cloning with gh, Conventional Commits, atomic staging, and guarded GitHub Actions for Rust/Python/TypeScript—so work matches his standard workflows.

Automates project setup with best practices including pre-commit hooks, linting, formatting, and boilerplate. Activates when creating new projects, missing configuration files, or setting up development environment. Ensures quality tooling from the start.

Comprehensive documentation generation through automated codebase analysis, pattern detection, and diagram creation.

Use when setting up CI/CD pipelines, containerizing applications, or managing infrastructure as code. Invoke for pipelines, Docker, Kubernetes, cloud platforms, GitOps. Keywords: DevOps, CI/CD, Docker, Kubernetes, Terraform, GitHub Actions.

Use when creating, editing, or managing GitHub issues. Provides issue type and label conventions for this project.

查看/更新 GitHub Issue、PR（含评论与 diff），并按团队规范非交互创建或修改 PR；涉及 GitHub Issue/PR 的操作时使用。

{Brief description for Claude Code skill invocation. Include primary triggers and capabilities.}

Comprehensive knowledge of Claude Agent SDK architecture, tools, hooks, skills, and production patterns. Auto-activates for agent building, SDK integration, tool design, and MCP server tasks.

Manage thoughts directory operations including initialization, synchronization, and metadata generation. Use after creating or modifying research documents, implementation plans, or notes to keep the searchable directory synchronized. Also use when gathering git metadata for document frontmatter.

MLOps engineering covering ML pipeline design, model versioning, experiment tracking, deployment strategies, drift detection, and monitoring for production ML systems with tools like MLflow, Kubeflow, and model registries

Generate clear, conventional commit messages from git diffs. Use when creating commits, reviewing staged changes, or writing commit messages.