개발 스킬

Set up Ouroboros inside Claude Code with a guided wizard. Check runtime requirements, configure the Claude runtime, optionally add project instructions to CLAUDE.md, and register existing repositories as context for future interviews.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up Ouroboros in Claude Code
• Checking Python and runtime requirements
• Adding Ouroboros instructions to CLAUDE.md

Start and monitor an Ouroboros development loop that revises project concepts and acceptance criteria, the conditions for judging completion. Run and evaluate successive generations, focus revisions on failed criteria, inspect progress, or rewind to an earlier generation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Refining a project through repeated execution and evaluation
• Inspecting progress across generations
• Rewinding a development loop to an earlier generation

Get started with Ouroboros through an interactive introduction that checks setup readiness and asks about your goals. Learn the core commands, then move into a project interview, a tutorial, or the help reference.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Getting an introduction to Ouroboros
• Checking setup before starting work
• Starting a project or choosing a tutorial

Work through repeated failed fixes or difficult technical choices using five perspectives: practical action, missing information, simplification, architecture, and challenged assumptions. Compare alternatives and disagreements, then receive a recommendation while keeping the final decision with the user.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reconsider a fix that has failed repeatedly
• Compare difficult database or architecture choices
• Reduce scope when complexity blocks progress

Convert agreed goals, constraints, and success criteria into a Seed specification an agent can execute and verify. A quality review checks consistency and testable outcomes, with any suggested refinements left for the user to approve.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Formalize requirements agreed in conversation
• Create a specification after a requirements interview
• Check acceptance criteria for measurable outcomes

Turn a vague development idea into clear goals, constraints, and acceptance criteria through a guided interview. It checks unresolved decisions and confirms the agreed goal before moving toward a Seed, the requirements document used by Ouroboros.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarifying a vague idea before development
• Defining completion criteria for a new feature
• Agreeing on scope and constraints

Turn a multi-file development task or technology migration into a specification with acceptance criteria, then launch background implementation and verification. The workflow clarifies missing requirements, reviews the specification, and tracks progress and blockers through linked jobs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing a feature across multiple files
• Migrating a framework or programming language
• Replacing authentication, storage, or API layers

Run repeated Ouroboros execution and improvement cycles as a background job, starting from a Seed specification or continuing an existing lineage. The loop stops on a quality check pass, convergence, cancellation, or the generation limit, and reports the outcome.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting repeated improvement from a Seed specification
• Continuing an existing improvement lineage
• Following meaningful background progress

Execute an existing Ouroboros Seed, a specification containing a goal and acceptance criteria, as a background job. The workflow checks each criterion, normally queues formal evaluation, and follows a bounded improvement loop if evaluation rejects the result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Executing an existing Seed specification
• Checking whether each acceptance criterion is met
• Following execution, evaluation, and improvement results

Explore how a website provides data or handles actions, then turn verified methods into a reusable Skill package with SKILL.md and Python scripts. The workflow includes testing, installation, and execution when requested.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn recurring website tasks into reusable Skills
• Investigate how a site loads its data
• Build a verified method for bulk data collection

Build AI agents in Unity with PuerTsAgent by organizing role instructions, skills loaded when needed, and executable helper modules. The guide covers resource folders, module design, and TypeScript or JavaScript implementation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build an AI assistant for the Unity Editor
• Define a maze exploration agent's behavior
• Separate occasional knowledge into skills

Create English and Chinese changelogs for PuerTS releases on Unity or Unreal. Review platform-specific Git commits, investigate unclear changes, and summarize their impact on users using each platform’s required format.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a Unity release changelog
• Preparing an Unreal release changelog
• Updating English and Chinese changelogs together

Install PuerTS in a Unity project by selecting a version, identifying required packages and dependencies, and choosing downloads or Git URLs. The guide also covers Editor Assistant installation, verification, and Windows troubleshooting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Install PuerTS packages in a Unity project
• Set up the PuerTS Editor Assistant
• Identify dependencies for agent or mcp

Check whether tools for mathematical modeling, numerical analysis, charts, and paper compilation are installed. Get a report separating required and optional dependencies, platform-specific installation commands, and a follow-up check after approved installation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a computer for mathematical modeling
• Checking missing paper compilation and charting tools
• Installing required dependencies after reviewing the commands

Inspect a project's code, history, tests, and documentation, then ask three focused questions to recommend an AI-assisted development approach. Receive one combination of methods, reasons for the choice, and practical first steps tailored to the project.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing an AI-assisted workflow for a new project
• Reviewing development methods for an existing service
• Aligning specifications and tests across services

Turns Git commits and pull request details into release notes for CHANGELOG.md, a release pull request, and Slack. It categorizes changes, explains user impact in plain language, and flags database migrations that need attention.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing release notes since the last release
• Summarizing changes across a specified version range
• Drafting a release pull request body

Suggests running verbose shell commands through RTK, a tool that condenses command output, and executes them after confirmation. It helps reduce the text an AI agent processes when reviewing Git history, tests, builds, and files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reducing output when reviewing Git history and diffs
• Condensing long test and build results
• Reading large files with less command output

Turn an agreed product direction into a technical specification before coding. Create architecture and flow diagrams, define failure handling and input validation, and map tests to the behavior engineers need to implement.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Define architecture before implementing a complex feature
• Map background jobs and external API interactions
• Check failure recovery paths and test coverage

Read recent releases from CHANGELOG.md and display their version numbers, dates, and complete change sections. Choose how many entries to show, or view the full history while preserving the document’s formatting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing the five most recent releases
• Checking changes across ten releases
• Reading the complete release history

Validate an implementation plan before execution through structural checks and specialist agent reviews. Check dependencies, files, tests, and architectural decisions, then update the plan to resolve findings, requesting human decisions when existing guidance is insufficient.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking an implementation plan for missing sections or dependencies
• Reviewing security or database changes before implementation
• Checking consistency with architectural decisions and project rules

Review a pull request for code quality, correctness, security, tests, and documentation. Receive structured findings ranked by severity, with file references, approval status, positive highlights, and questions that need clarification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a pull request before merging
• Checking changes against the original plan
• Auditing error handling and validation of AI output

Answer a short series of questions about your workflow to choose a Claude Code agent, command, skill, hook, or rule, then generate a template with the structure and file location for that component.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing how to implement a Claude Code workflow
• Creating a template for a reusable team procedure
• Planning automatic checks or persistent behavior rules

Diagnose failures in an application or while it is running. Use it to investigate an application problem or a runtime error, meaning an error that occurs during execution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating an error during execution
• Diagnosing an application failure
• Asking an agent to examine a running application's problem

Create a custom Claude Code skill with a structured SKILL.md file and optional scripts, reference documents, and templates. Follow checks for metadata and usage examples, test a real task, and package the skill for distribution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a custom skill for a project
• Standardizing skill structure across a team
• Preparing a skill with scripts and templates