LLM & Agents

Use this skill proactively and automatically after completing ANY development work. AI agent summarizes: what was done, what was changed/improved, and suggests future additions/improvements - all concisely in Korean.

Generate Midjourney prompts for 600x600 card news background images based on topic, mood, and style preferences. Use when user requests card news backgrounds or Instagram post backgrounds.

AI-powered comprehensive codebase documentation generator. Analyzes project structure, identifies architecture patterns, creates C4 model diagrams, and generates professional technical documentation. Use when users need to document codebases, understand software architecture, create technical specs, or generate developer guides. Supports all programming languages. Alternative to Litho/deepwiki-rs that uses Claude Code subscription without external API costs.

Testing patterns for PHPUnit and Playwright E2E tests. Use when writing tests, debugging test failures, setting up test coverage, or implementing test patterns for ActivityPub features.

Analyze coding agent session transcripts to improve existing skills or create new ones. Use when asked to improve a skill based on a session, or extract a new skill from session history.

Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.

Fetch and analyze Sentry issues, events, transactions, and logs. Helps agents debug errors, find root causes, and understand what happened at specific times.

Use when writing or modifying .txt test scripts in testdata/script/ for git-spice - covers txtar format, end-to-end testing, ShamHub forge simulation, interactive prompts, and golden file comparisons for branch operations and stack workflows.

Guide for creating new Claude Code skills. Use when you need to create a new skill to package expertise or workflow into a reusable capability that Claude can automatically invoke.

Structure Claude prompts for clarity and better results using roles, explicit instructions, context, positive framing, and strategic organization. Use when crafting prompts for complex tasks, long documents, tool workflows, or code generation.

Adapt Claude Code for different use cases beyond software engineering by customizing system prompts for teaching, learning, analysis, or domain-specific workflows.

Teaches how to write effective documentation and instructions for LLMs by assuming competence, using progressive disclosure, prioritizing examples over explanations, and building feedback loops into workflows.

Create and manage specialized Claude Code subagents for task-specific workflows. Use when delegating work to specialized agents, configuring agent permissions, or understanding subagent architecture and best practices.

Create and use custom slash commands to automate Claude Code workflows. Learn argument passing, frontmatter configuration, bash integration, and file references for building reusable prompts.

Specialized AI assistants for task-specific workflows with separate context. Learn when to delegate, configure tools, and apply best practices.

Create effective documentation that LLMs can discover and use. Use when documenting code, APIs, features, or creating reference materials. Covers structure, conciseness, examples, and anti-patterns for optimal LLM comprehension.

Write automated tests for features, validate functionality against acceptance criteria, and ensure code coverage. Use when writing test code, verifying functionality, or adding test coverage to existing code.

Comprehensive reference for the TypeScript Agent SDK with functions, types, and interfaces for programmatic Claude Code interactions

Coordinate concurrent task execution through agent delegation. Plan independent work, manage dependencies, and execute multiple agents simultaneously. Use when handling multiple unrelated tasks, research investigations, or layer-based implementations that can run concurrently.

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library