Git & Version Control

Track complex, multi-session work with dependency graphs using bd (beads) issue tracker. Git-backed JSONL files are the source of truth, with SQLite as local cache. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.

Specialized agent for comprehensive testing of the BarqNet project across all platforms and layers. Handles unit testing, integration testing, E2E testing, performance testing, security testing, and test automation. Creates test plans, writes test code, executes tests, and generates test reports. Use when implementing tests, debugging test failures, or validating functionality.

This skill should be used when the user asks about "game architecture", "design patterns", "manager pattern", "singleton pattern", "ScriptableObject", "ScriptableObject architecture", "event system", "Observer pattern", "pub-sub", "MVC in Unity", "dependency injection", "service locator", or needs guidance on structuring Unity projects and game systems.

Use when automating browsers with Playwright/Puppeteer, testing Chrome extensions, using Chrome DevTools Protocol (CDP), handling dynamic content/SPAs, or debugging automation issues

Comprehensive guide for modern front-end testing with Playwright (2025). This skill should be used when writing end-to-end tests, component tests, or visual regression tests for web applications using Playwright. Covers Page Object Model patterns, TypeScript integration, modern SPA testing strategies, accessibility testing, and CI/CD automation with GitHub Actions.

Use this skill when implementing combat automation in SND macros using the BossModReborn plugin. Covers preset management, rotation configuration, and AI control via chat commands.

Post-session analysis agent that extracts learnings, decisions, user preferences, and "surprise moments" from conversation transcripts. Stores insights in Memory Lane with vector embeddings for future retrieval.

git 명령어 사용 및 커밋 생성 가이드

Generate conventional commit messages following best practices. Use when creating structured git commit messages.

Interpretive guidance for Python code quality using ruff (modern) or pylint+isort+black (traditional). Use when linting Python files, configuring Python tools, troubleshooting lint errors, or understanding tool selection.

Draft and review Git commits and commit messages with an emphasis on atomic change sets and clean history. Use when asked to commit changes, propose commit messages, split/squash/rebase commits, or clean up a branch via fixup commits and interactive rebase/autosquash.

Diagnose and resolve E2E test failures in Playwright. This skill should be used when E2E tests fail and need investigation, when Playwright test errors require root cause analysis, or when test failures need to be reproduced in the browser for debugging. Orchestrates MCP tools (Playwright, Chrome DevTools, Serena) and delegates code fixes to specialized agents.

Generate conventional commit messages based on git diff analysis. Use when you need to create well-structured commit messages following conventional commit format.

Automatically applies when engineering prompts for LLMs. Ensures proper prompt structure, templates, few-shot examples, context management, and injection prevention.

Commit and push changes to GitHub with proper messages. Use when ready to save changes, push to production, or deploy updates to GitHub Pages.

Git workflow best practices for commits, rebasing, conflict resolution, and branch management. Use when working with git operations, creating commits, resolving conflicts, or managing branches.

Jira Cloud REST API via curl. Use this skill to create, update, search, and manage issues, projects, and workflows in Jira.

Generates .lintstagedrc configuration to automatically fix and format staged files before commit. Runs ESLint, Stylelint, and Prettier on staged files.

Creates, validates, and updates GitHub Actions workflows for CI/CD. Covers build, test, Maven Central publishing, code quality analysis, Docker builds, and Kubernetes deployments.

When editing KINTSUGI notebook modules (Kdecon, Kstitch, Kreg, etc.), always edit the main repo first then sync to project folders