LLM & Agents

Implementation agent focused on high-integrity TDD-driven code generation.

Use PROACTIVELY when you need to create, update, configure, or validate Claude hooks for various events and integrations

Analyze test coverage, identify gaps, suggest strategic test cases. Use when writing features, after bug fixes, or during test reviews. Ensures comprehensive coverage without over-testing.

Enforces security guardrails for Claude Code. Blocks access to secrets, credentials, and sensitive files. Requires confirmation for network requests and infrastructure changes. Use when accessing files, making network requests, or running infrastructure commands.

Chat with local Ollama models that can explore your codebase using tools.

RAG 파이프라인 최적화 스킬. 검색 품질, 리랭킹, 쿼리 확장, 하이브리드 검색 관련 작업에서 자동으로 활성화됩니다. retrieval, rerank, embedding, vector search, semantic search 키워드에 반응합니다.

This skill should be used when the user asks to "write tests", "add unit tests", "create test cases", "test this function", "add test coverage", or discusses testing strategies and test implementation.

Migrate existing plugins to proper Claude Code format. Use when converting flat skill files, adding missing frontmatter, restructuring plugin directories, or upgrading plugin structure.

Migrate Claude Code session storage when directories are moved or renamed. Use when user mentions moving folders, renaming directories, relocating projects, or needs to update Claude session paths after filesystem changes.

Guide PRD document creation using the standard template. PRD contains REQUIREMENTS ONLY - no user stories (those are extracted separately). Use when EA agent drafts or updates a PRD, or when validating PRD structure.

Advanced LLM jailbreaking techniques, safety mechanism bypass strategies, and constraint circumvention methods

Handles integrations with trigger behavior for dynamic agent delegation

Guide for creating, configuring, and distributing Claude Code plugins with hooks, skills, commands, and MCP servers. Use when user asks to create a plugin, set up hooks, add plugin functionality, create a marketplace, or distribute custom Claude Code extensions.

Update ClaudeKit Engineer projects to the latest version. Capabilities include update single projects (safe mode with test branches), batch update multiple projects, find all ClaudeKit projects in home directory, verify updates with automated checks, preserve user settings and code, create timestamped backups, handle git workflows (branch, commit, merge), and rollback if needed. Use when user wants to update ClaudeKit framework, upgrade to latest version, apply new features/skills/commands, or maintain multiple ClaudeKit projects.

Testing workflow for quality assurance. Use after implementation to run tests, check coverage, and validate critical paths.

Create visual assets (images, illustrations) using AI (OpenAI DALL-E).

Brief description of what this skill does. Include specific triggers - when should Claude use this skill? Example triggers, file types, or keywords that indicate this skill applies.

Standards, architecture patterns, and best practices for Android app development with Kotlin, Jetpack Compose, and Android Jetpack libraries using clean architecture and MVVM. Use for any Android coding, review, refactor, or design task, especially when acting as an AI coding agent that must follow established project conventions.

Implement drag and drop using @atlaskit/pragmatic-drag-and-drop. Use when implementing sortable lists, reorderable items, kanban boards, or any drag-drop interactions. Covers draggable setup, drop targets, edge detection, drag previews, and critical state management patterns to avoid performance issues.

Coordinate multi-agent orchestration for complex tasks. Launch parallel and sequential agents, manage dependencies, aggregate results, and orchestrate sophisticated workflows. Use for tasks requiring multiple specialized perspectives or parallel processing.