개발 스킬

Reduce changes on your own branch before opening or updating a pull request. Review added architecture and tests, remove unnecessary complexity, and verify that the smaller change still fixes the original problem and preserves supported behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Trim changes before opening a pull request
• Remove duplicate architecture after a large repair
• Keep tests that catch distinct failures

Check live ClawHub records to see how many public plugins reference a Plugin SDK method or other interface. Filter by release date, examine usage evidence and coverage gaps, and inform compatibility decisions before changing or deprecating an interface.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Count public plugins referencing an SDK method
• Limit usage research to recently released plugins
• Assess compatibility risks before deprecating an export

Build, migrate, review, and test OpenClaw interfaces with Solid 2. The skill covers state ownership, coexistence with Lit during migration, overlays such as dialogs, performance, and checks that preserve existing interface behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Migrating OpenClaw components from Lit to Solid 2
• Reviewing state ownership and reactive updates
• Building plugin views and dialog overlays

Investigate duplicate OpenClaw pull requests and issues using local history and current GitHub evidence. Organize confirmed or suspected duplicates in prtags, recording the decision, confidence, and reasons for maintainers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check whether a pull request duplicates existing work
• Find issues describing the same problem
• Organize related work into one duplicate group

Coordinate repairs across multiple OpenClaw issues or pull requests, which propose code changes. Assign owners, prove defects, verify fixes, and track outcomes through merging or closing resolved items within the authorized scope.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Coordinating repairs for multiple issues and pull requests
• Completing and verifying an existing repair pull request
• Closing issues already proven fixed on main

Build temporary OpenClaw terminal interfaces with fixed sample data and compare two to six interactive designs side by side in tmux, a terminal pane manager, using the actual rendering components without running the full application.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing onboarding screen designs
• Trying chat or selector layouts
• Comparing an existing screen with alternatives

Investigate OpenClaw issues and review pull requests, proposed code changes, using current source and test evidence. Depending on the authorized scope, repair defects locally or carry the change through review, merge, and final verification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing an OpenClaw pull request
• Investigating and repairing a reported defect locally
• Checking whether an issue is already fixed

ClawSweeper로 OpenClaw의 이슈와 PR을 점검합니다. 보고서 확인, 수정 작업 생성, GitHub Actions 조사와 권한 및 검증 조건에 따른 자동 수정·병합을 지원합니다.

• 이슈와 PR 점검 보고서를 확인할 때
• 기존 보고서로 수정 작업을 만들 때
• GitHub Actions 실패를 조사할 때

Prepare an agent activity transcript for a GitHub pull request or issue. Extract relevant prompts, decisions, and results from local logs, remove sensitive material, and preview the edited record before separately authorized publication.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing an agent activity record for a pull request
• Extracting task-relevant prompts and results from local logs
• Previewing a transcript with sensitive information removed

로컬에 저장된 GitHub 데이터에서 Issue, PR, 중복 후보를 찾습니다. 동기화 상태와 정보 누락을 확인하고 판단 전에 최신 상태를 대조합니다.

• 결함과 관련된 Issue와 PR을 찾을 때
• 중복 후보 Issue를 확인할 때
• 대응 결정 전에 저장 정보의 최신성을 확인할 때

OpenClaw에 전달한 자연어 요청을 Claude Code 같은 외부 코딩 에이전트로 연결합니다. ACP나 acpx로 작업을 시작하거나 이어가며 대화 맥락을 유지합니다.

• 스레드에서 Claude Code 시작
• 외부 에이전트의 기존 작업 계속
• acpx로 직접 지시 전달

Review code using shared OpenClaw instructions and a Python helper, while also following the target repository’s review requirements. This skill points to a common installation that supplies the actual review procedure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing code with shared OpenClaw instructions
• Applying repository-specific review requirements
• Keeping shared review instructions up to date

Turn before-and-after text or a patch into a view of changes. Create an interactive viewer URL, a PNG image, or a PDF so others can inspect edits and receive the comparison as an attachment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sharing text changes through an interactive viewer
• Attaching a comparison as a PNG or PDF
• Preparing high-quality files for reviewing edits

Collect OpenClaw pull requests, proposed code changes, and issues shared in a specified conversation and time window. Recheck them on GitHub, assess impact and readiness, and return a prioritized queue with evidence and coverage gaps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prioritizing change proposals shared in last week's conversation
• Rechecking the status of previously listed proposals
• Finding additional proposals within the same conversation window

Git 기록에서 OpenClaw 릴리스 변경 내역을 다시 작성합니다. 사용자 영향별로 정리하고 Issue와 PR 참조, 기여자 표기의 누락을 검증합니다.

• stable 버전 공개 전 변경 내역 작성
• 이전 beta 배포 기준과의 차이 정리
• 기여자와 PR 참조 표기 확인

Launch native or web apps on a temporary Crabbox machine and display them in the chat side panel. The skill covers setup, readiness checks, screen interaction, reopening previews, and stopping apps or releasing the environment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Launching and showing a native app
• Previewing a web app in the side panel
• Testing an app through screen interaction

Diagnose OpenClaw problems involving models, providers, tools, and streamed responses. Use targeted logs, repeat the failing operation, and inspect stored conversations and attachments to identify the cause, guide a repair, and verify the result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating differences between local tests and live runs
• Checking which tools are actually visible to a model
• Diagnosing delayed or stalled streamed responses

Work directly with MCP servers, which connect AI agents to external tools. List available tools, inspect their inputs, manage configuration and authentication, and call them through HTTP or local process connections using mcporter.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking available MCP tools and their inputs
• Configuring and authenticating an MCP connection
• Calling tools with JSON arguments

tmux에서 실행 중인 대화형 명령줄 프로그램의 화면을 확인하고 문자와 키를 보냅니다. 세션 목록, 출력 기록 조회, 입력 대기와 처리 완료 감시에 활용합니다.

• 대화형 프로그램의 출력 확인
• 실행 중인 세션에 문자와 키 전송
• 입력 대기와 처리 완료 감시

Bundle a question and selected project files for a second AI model to review code, investigate bugs, or assess design options. Preview the files and token usage before running through an API or browser.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Getting a second AI opinion on code
• Investigating errors with relevant project files
• Comparing design and refactoring options

Create or revise agent skills by defining when they run, what they produce, and how their files are organized. Validate SKILL.md settings, resource links, and changed helper scripts before completing the work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a skill for a recurring workflow
• Repairing an existing SKILL.md
• Organizing bundled references and scripts

Test an idea before committing to full development by building a small, disposable prototype. Compare approaches under equal conditions, try a failure case, and report feasibility with commands, results, or measurements supporting the verdict.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing whether an idea is technically feasible
• Comparing two approaches under the same conditions
• Checking an edge case before full development

Investigate Node.js bugs by pausing execution, examining variables, and stepping through code. Diagnose stalled asynchronous work and unreliable tests, or collect memory snapshots and CPU profiles to investigate growing memory use and slow execution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate stalled asynchronous work
• Debug tests that fail inconsistently
• Examine startup timing and child processes

Manage GitHub issues and pull requests, proposed code changes, using the gh command-line tool. Create and inspect discussions, check automated test results, investigate failed logs, rerun jobs, and track authorized merges through to their verified status.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating and updating issues or pull requests
• Checking pull request reviews and automated checks
• Investigating failed CI logs and rerunning jobs