개발 스킬

Build and review React, Next.js, and TypeScript interfaces, including pages, components, forms, and responsive styles. The skill follows a project’s existing design system, shared UI components, language settings, and frontend conventions, then checks the result with relevant tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a page or reusable UI component
• Styling a responsive layout with Tailwind
• Adding form validation and interactions

Assess software architecture choices by examining system boundaries, constraints, risks, and tradeoffs. Compare viable designs, recommend an approach, and document the reasoning and validation steps in an architecture decision record when needed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing system design options
• Clarifying module or service ownership boundaries
• Investigating hidden dependencies or awkward APIs

Analyze software architecture questions, compare design options, and examine risks, costs, and quality needs. Get a grounded recommendation or an ADR-style decision record with assumptions, tradeoffs, and validation steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing between system designs
• Defining module or service boundaries
• Investigating hidden dependencies or change pain

Implement mobile screens, widgets, platform integrations, and application data flows in Flutter, React Native, or native Swift. The skill follows the existing app architecture and supports platform-specific behavior, offline data handling, and relevant mobile testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing a mobile screen in Flutter
• Building an iOS feature in native Swift
• Connecting a screen to application data

Create or revise OMA skills by clarifying when they should be selected, defining one usable workflow, and organizing supporting references. It also helps validate structure and report checks or unresolved limitations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Drafting a new OMA skill
• Reviewing a skill’s routing and workflow
• Deciding what belongs in a conditional reference

Handle Git work such as commits, branches, merges, conflict resolution, and release baselines. It helps keep changes scoped and traceable, inspect repository history, and report created commits or refs and any checks or unresolved work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Committing a focused set of changes
• Creating or managing branches and worktrees
• Resolving merge conflicts

Use this skill to investigate bugs, crashes, errors, and regressions. It guides an agent to reproduce the failure, find its root cause, make a focused fix, add a regression test, and report verification results or blockers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a crash from its traceback
• Finding the cause of a failing test
• Fixing an intermittent failure

Review staged and unstaged changes, select relevant files, and create a Git commit using Conventional Commits, a format for structured commit messages. The workflow adds the required DCO sign-off and checks the repository status afterward.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Committing a focused set of changes
• Writing a commit message in Conventional Commits format
• Adding the required DCO sign-off to a commit

Prepare a pull request for the current branch by reviewing its commits and diff, choosing a conventional title, and filling in the repository’s pull request template. Then push the branch and create the PR targeting the default main branch.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Opening a pull request for a completed branch
• Summarizing all changes since the branch split from main
• Creating a PR using the repository’s contribution format

Builds resource hubs, section listings, and article pages from existing Markdown files, following a website’s framework and design system. It also connects related resources with navigation and links, so the pages are ready to publish with their content and metadata rendered.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a resource center from existing Markdown articles
• Creating section listings and article pages for a website
• Adding breadcrumbs and links between related resources

Inspect a website codebase and make targeted changes that help AI search tools find, understand, and cite its pages. The skill addresses metadata, structured data, crawler access, content structure, and freshness, then supports verification against an audit baseline.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Improving a site's visibility in AI search results
• Adding structured data and page metadata
• Making key content easier for AI tools to parse

Sets up Storybook for React Native projects by identifying whether they use Expo, Expo Router, the React Native CLI, or Re.Pack. It guides dependency setup, configuration files, bundler integration, app entry points, and running Storybook on iOS or Android.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding Storybook to an Expo or Expo Router app
• Configuring Storybook for a React Native CLI project
• Connecting Storybook to a Re.Pack bundler

Creates and edits React Native Storybook stories in Component Story Format. It helps describe component variants, configure interactive prop controls and addons, add wrappers or custom rendering, and reuse stories in Jest tests for consistent component examples and checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding Storybook stories for React Native components
• Configuring controls, actions, and backgrounds for stories
• Reusing component stories in Jest tests

Use this skill to move a React Native Storybook project through supported version upgrades one step at a time. It identifies the current setup, updates dependencies and configuration, regenerates required files, and converts `storiesOf` stories to CSF on the relevant upgrade path.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Upgrade a React Native Storybook project to its next supported version
• Identify the installed Storybook version and choose the next migration step
• Convert remaining `storiesOf` stories to CSF during the 6.5 to 7.6 upgrade

Use this reference when designing or debugging agent skills that repeat actions such as searching, fetching, or scanning. It explains how to verify progress, set stopping limits, manage context, and avoid loops that run indefinitely or claim success without evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Design a research skill that searches until results are verified
• Set clear stop conditions for a repeated fetch workflow
• Debug a loop that stalls or repeats without progress

Develop Vben Admin 5.0 management interfaces with Vue 3, Vite, and TypeScript. Get guidance for routes and menus, access control, themes, API requests, state management, localization, components, and deployment configuration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding routes and menus to a Vben Admin project
• Configuring roles, permissions, or themes
• Connecting APIs and localizing an admin interface

Choose how Deep Agents store working files and memory, from temporary thread-scoped state to storage shared across sessions or local disk access. Learn to route paths between backends and understand which data persists and where.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Keeping temporary files for one agent thread
• Sharing saved preferences or notes across sessions
• Routing temporary and persistent files to different backends

Set up and run a small LangChain agent in a fresh local Python project by following the official quickstart. Choose a model provider, add its API key locally, and see the example agent run before moving on to further customization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Try a LangChain agent locally
• Start a small Python agent project
• Choose a model provider for a quickstart

Guides the use of the LangGraph CLI across an application’s lifecycle: creating a project, configuring `langgraph.json`, running locally, building or launching with Docker, and deploying to LangGraph Platform. It also covers deployment logs and common setup requirements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Scaffolding a new LangGraph application
• Running a local development server with hot reload
• Building and validating a Docker deployment

Build and run a minimal local Deep Agent in Python from the official quickstart. Choose a model provider and use its built-in web search for a research example, avoiding a separate search service and its API key.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Try a Deep Agent locally
• Build a small Python research agent
• Use provider-native web search

Configure how Deep Agents divide work among specialized subagents, track multi-step plans, and pause sensitive tool actions for human approval. Learn when each capability fits and how to set up and resume these workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Delegating research or specialized work to a subagent
• Planning and tracking a multi-step agent task
• Requiring approval before a deployment or database write

Build stateful workflows and agents with LangGraph. Learn how to design state, implement nodes, connect and route edges, run or stream graphs, and handle common errors. Includes guidance on choosing the matching Python or TypeScript implementation reference.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a graph for a branching workflow
• Choosing state fields and reducers
• Routing work with `Command` or parallel `Send` calls

Create a minimal LangGraph agent locally in TypeScript by following the official quickstart. Choose a chat model provider, set its API key in a local `.env` file, install the needed packages, and run a small calculator agent example.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Trying a LangGraph agent in a new local project
• Scaffolding the TypeScript Graph API quickstart
• Selecting a model provider for a calculator agent

Build applications with Deep Agents by configuring its agent harness, the framework layer that supplies planning, file tools, subagents, memory, approvals, and on-demand skills. Covers `create_deep_agent()`, configuration choices, and the `SKILL.md` format.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up a Deep Agents application
• Choosing middleware and configuring agent behavior
• Loading skills from a filesystem or store backend