개발 스킬

Review LoongCollector code changes for concrete defects, security risks, and architectural mismatches. It tracks review history to focus on new changes and produces evidence-backed findings, lifecycle checks, and practical fix and validation plans.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review a pull request for security or behavior regressions
• Recheck whether earlier review comments were fixed
• Assess a branch change with architecture context

Use RIPER-5 to structure complex software engineering work into research, idea exploration, planning, execution, and review. It defines what each phase covers and uses explicit transition signals to guide work on design, refactoring, bug diagnosis, and integration tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Breaking down a complex bug investigation into phases
• Exploring alternatives for an architectural change
• Preparing a detailed implementation checklist

Consult this reference for OMC agent roles, tools, workflow skills, team pipeline stages, and commit message trailers. It helps users find the right orchestration commands and understand how work moves through planning, execution, verification, and fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Looking up an OMC agent role for a task
• Finding a team pipeline stage or orchestration command
• Checking commit trailers for recording decision context

Prepare a local pull request draft for Windows node changes using the current template, scoped validation results, and review evidence. It identifies readiness and blockers while keeping publication separate from preparation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Draft a Windows node pull request body
• Summarize validation evidence and limitations
• Check whether required reviews are complete

Use the `winnode` CLI to discover and invoke OpenClaw commands on a local Windows app through its MCP endpoint. The reference explains command arguments, outputs, and A2UI JSONL input so agents can prepare calls and troubleshoot errors.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• List commands exposed by the local Windows app
• Prepare a command with the required JSON arguments
• Send an A2UI surface using JSONL input

Use the Windows app’s local MCP server and `winnode` CLI to inspect available tools, invoke commands, and investigate development issues. The skill helps distinguish local app checks from tests that require the OpenClaw gateway.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspect tools exposed by a running Windows app
• Invoke a local command through `winnode`
• Diagnose MCP connection or capability issues

Triage the full OpenClaw Windows Node issue and pull request backlog. Classify landing readiness, required proof, ownership, review status, and dependencies, then produce an evidence-based report and an ordered work and release plan.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review the full issue and pull request backlog
• Identify safe landing candidates and blockers
• Plan proof pools, ownership, and release work

Run independent code reviews with two AI models, then compare their findings and verify potential issues. The skill organizes results by consensus and severity, adds fix confidence ratings, and reports clearly when either review is incomplete.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Request a thorough review of code changes
• Compare findings from two AI reviewers
• Review a security-sensitive change adversarially

Use the shared autoreview skill to review a selected code scope with explicit context and P0–P3 priorities. Check the fresh report, process outcome, and coverage together, and describe any fallback review with its actual limitations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review a scoped code change
• Check review findings across P0–P3 priorities
• Use the documented fallback when Codex CLI is unavailable

Create A2UI v0.8 interfaces for the OpenClaw Windows tray node using its native WinUI renderer. Build valid JSONL surfaces from the supported component catalog, bind values to data, and follow action-context rules so only permitted data is sent back.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a form for a Windows tray node
• Sending an A2UI surface through the canvas RPC
• Binding controls to values that update

Reviews a Skill’s `SKILL.md` description for accuracy, clarity, and useful task triggers, then can recommend a revision. It also guides copying a complete Agent Skill into a user-level or project-level `.agents/skills` location.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a Skill description for clarity and coverage
• Improving task triggers in SKILL.md frontmatter
• Installing an Agent Skill for personal use

Helps plan, write, update, and validate Agent Skills for AI agents. It guides authors through scope, folder structure, YAML frontmatter, clear activation descriptions, examples, supporting files, and troubleshooting when a skill is not discovered or used as expected.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a focused Agent Skill for a workflow
• Writing or improving a SKILL.md file
• Converting an existing prompt into a Skill

Review code changes across many languages and frameworks for correctness, security, performance, architecture, and maintainability. The skill provides checklists and language-specific guidance, and helps produce constructive feedback that explains priorities and supports team learning.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a pull request for bugs and edge cases
• Checking a design for security or performance issues
• Creating review standards and mentoring developers

Use the `gh` command line tool to review GitHub issues, pull requests, and CI workflow runs. Retrieve additional repository data through the API and filter structured JSON output for focused queries.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• List and filter repository issues
• Check pull request status and CI checks
• Inspect failed workflow steps and logs

Design or update browser-visible interfaces, from forms and dashboards to landing pages and prototypes. It considers layout, visual hierarchy, interaction states, responsive behavior, and accessibility, then checks the rendered result in a browser when browser tools are available.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a responsive dashboard or admin screen
• Redesigning a form or onboarding flow
• Improving a landing page's layout and visual hierarchy

Create and maintain agent skills by shaping their instructions, organizing supporting files, and checking required metadata. The workflow helps produce focused `SKILL.md` files with clear triggers, practical procedures, and validated directory structure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a new agent skill
• Reorganizing an existing `SKILL.md`
• Reviewing skill metadata and file layout

Creates a native SwiftUI iOS app, runs it in the Simulator, and guides command-line archiving and TestFlight upload. Includes scripts for generating icons, launching a simulator build, and uploading a signed app through the App Store Connect API.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Scaffolding a new SwiftUI iOS app
• Running an app in the iOS Simulator
• Archiving and uploading a build to TestFlight

Adjusts a Next.js app so PostHog session recordings and dead-click capture can load when browser blockers filter three specific script filenames. It routes those files through same-origin aliases while leaving other PostHog traffic on its existing host.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fixing blocked PostHog session replay scripts
• Restoring dead-click capture in a Next.js app
• Handling ERR_BLOCKED_BY_CLIENT for the named assets

Build MCP servers in TypeScript with the Leanmcp SDK and decorators. It guides tool, resource, and prompt definitions, automatic input schema generation, authentication, structured user input collection, and injection of user-specific environment secrets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building an MCP server with decorator-based tools
• Adding authentication to MCP services
• Collecting structured input from users

Build and troubleshoot 3D city games in Godot 4, from procedural streets and buildings to playable scenes. It also guides asset imports, project checks, browser exports, and cloud GPU streaming so you can prepare a game for others to play.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting a procedural city game in Godot 4
• Debugging slow or incorrectly generated city scenes
• Importing Blender models and character animations

Create TypeScript MCP servers with the official SDK to expose APIs and application features to AI agents. The guidance covers tools for actions, read-only resources, reusable prompts, Streamable HTTP transport, and session handling for connected clients.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Exposing an API as tools for AI agents
• Building an MCP server in TypeScript
• Providing read-only data as MCP resources

Build interactive React interfaces for MCP tools with the Leanmcp UI SDK. The skill covers connecting tool methods to UI components, reading tools and resources with hooks, creating forms and data grids, and supporting ChatGPT Apps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a React dashboard to MCP tools
• Building forms that call MCP tools
• Displaying tool data in sortable tables

Guides work on the Claude Code codebase by explaining its project structure, coding conventions, and patterns. Use it when adding or changing tools, commands, utilities, components, types, hooks, or services, fixing bugs, or learning how the code is organized.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a tool or command to Claude Code
• Fixing a bug while following existing conventions
• Understanding the codebase structure and architecture

Refresh website and README screenshots from the actual QualityLayer app after interface changes. It captures curated example scenes in light and dark themes, checks the output and manifest, and updates local image assets for the developer gallery.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Refreshing screenshots after UI changes
• Updating a developer example gallery
• Capturing real app screens for a README