Git 與版本控制

Coordinate multi-agent workflows: sequential, parallel, and iterative patterns.Defines agent handoffs, dependencies, communication protocols, and integration.Use when designing multi-agent workflows, coordinating agent handoffs,planning agent dependencies, or building complex agent pipelines.

Validate test effectiveness with mutation testing using Stryker (TypeScript/JavaScript)and mutmut (Python). Find weak tests that pass despite code mutations.Use when user mentions mutation testing, Stryker, mutmut, test effectiveness,finding weak tests, or improving test quality through mutation analysis.

Generates metadata for research documents and specifications including date/time, git commit, branch, and repository info. Use when creating research documents, handoffs, or any documentation that needs timestamp and git metadata.

HODD-RUST: Validation-first Rust development. Strictly validation-first before-and-after(-and-while) planning and execution. Merges Type-driven + Spec-first + Proof-driven + Design-by-contracts. Use for Rust projects requiring formal verification, safety proofs, comprehensive validation, or when working with unsafe code, concurrency, or FFI boundaries. This skill provides both reference documentation AND execution capabilities for the full PLAN -> CREATE -> VERIFY -> REMEDIATE workflow.

Plan sprints and backlogs in an AI-Driven Development workflow. Define features (backlogs), organize sprints as cumulative demo-able milestones, and manage the full development lifecycle.

Modern Node.js development with Bun, Vite, Vue 3, Pinia, and TypeScript. CoversJavaScript/TypeScript projects, high-performance tooling, and modern frameworks.Use when user mentions Node.js, Bun, Vite, Vue, Pinia, npm, pnpm, JavaScript runtime,or building frontend/backend JS applications.

Write focused tests for core user flows and critical business logic, testing behavior rather than implementation, with clear names and fast execution. Use this skill when writing unit tests, integration tests, or end-to-end tests. When testing critical user workflows and primary application features. When creating tests that focus on what code does rather than how it does it. When mocking external dependencies like databases, APIs, or file systems. When naming tests to clearly describe the scenario and expected outcome. When keeping tests fast and independent. When completing feature implementation and adding strategic tests at logical completion points. When working with test files or test frameworks.

Escalation path when stuck on pattern development. Use when encountering TypeScript errors, framework confusion, unexpected behavior, or blocked progress. Five-step recovery: check docs, study examples, strategic investigation (plan mode + subagents), reset and retry, ask user.

Core Python development concepts, idioms, best practices, and language features.Covers Python 3.10+ features, type hints, async/await, and Pythonic patterns.For running scripts, see uv-run. For project setup, see uv-project-management.Use when user mentions Python, type hints, async Python, decorators, context managers,or writing Pythonic code.

Ensure AI agents work in an isolated Git worktree to prevent changes to the main working directory. Use when AI is about to make its first code modification in a session, or when the user requests isolated/safe editing. Triggers include starting to edit files, implementing features, or fixing bugs.

Convenience wrapper for listing Terraform Cloud runs in Forum Virium Helsinkiworkspaces (github, sentry, gcp, onelogin, twingate). Requires TFE_TOKEN.Use when user mentions TFC runs, Terraform Cloud workspace, listing TFC runs,infrastructure run history, or checking Terraform Cloud status.

Knip finds unused files, dependencies, exports, and types in JavaScript/TypeScript projects.Plugin system for frameworks (React, Next.js, Vite), test runners (Vitest, Jest), and build tools.Use when cleaning up codebases, optimizing bundle size, or enforcing strict dependency hygiene in CI.

Automatically generate and post detailed bug reports to GitHub Issues for the active project repository. This skill should be used when documenting bugs discovered during development, creating professionally formatted GitHub Issues with reproduction steps, technical insights, and recommended E2E tests.

Create new Claude Code skills with proper SKILL.md format, frontmatter, and best practices. Use when building, scaffolding, or generating a new skill for Claude Code.

Create isolated git worktrees for parallel development. Use when working on multiple issues simultaneously.

Help users deploy their portfolio to production. Covers Vercel, Netlify, Cloudflare Pages, GitHub Pages, Docker, and MCP integration for AI-driven deployment.

Generate GitHub repository social preview images (Open Graph images).Creates 1280x640 PNG images optimized for social media sharing.Uses nano-banana-pro for AI image generation with GitHub-specific prompts.Use when user mentions: social preview, Open Graph image, OG image,repository image, GitHub preview, social media preview, repo thumbnail,share image, or needs an image for repository settings.

Check CI/CD status of a pull request including workflow runs and test results. Use when verifying if PR checks are passing or investigating CI failures.

Comprehensive chezmoi dotfiles management expertise including templates, cross-platformconfiguration, file naming conventions, and troubleshooting. Covers source directorymanagement, reproducible environment setup, and chezmoi templating with Go templates.Use when user mentions chezmoi, dotfiles, cross-platform config, chezmoi apply,chezmoi diff, .chezmoidata, or managing configuration files across machines.

Sync skill definitions to agent proxy files (.agent/workflows/skills.md and .github/copilot-instructions.md). Use after adding, removing, or modifying skills.