개발 스킬

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

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

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

Check whether a guide and its landing site show matching versions, template counts, and quiz totals. Get a structured status report that identifies mismatches, points to affected files, and suggests specific corrections.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking landing site figures after a guide update
• Finding mismatched template and quiz counts
• Identifying files that need synchronization fixes

Review code changes for concrete defects. Use it to examine modified code when you want to check whether a change contains a bug, with the review focused on specific problems in the changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing changes after editing code
• Checking a bug fix for further defects
• Reviewing code changes that add a feature

Turn a feature request into an implementation plan before coding. Five planning phases cover requirements, interface design, technical choices, research, and metrics, producing ordered tasks, a test plan, and records explaining major decisions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a feature that touches several files
• Resolving unclear requirements before implementation
• Recording architecture and interface decisions

Audit a collection of agent skills for valid settings, clear activation conditions, complete workflows, and required files. Get scores for each target platform, prioritized fixes, and a separate record of whether activation was actually tested.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking skill quality before publication
• Reviewing an imported skill collection
• Investigating excessive or missing automatic activation

Measure code patterns such as casts to any or disabled lint rules, then run repeated, targeted edits. Keep changes that improve the chosen metric, revert unsuccessful changes, and track results for each improvement loop.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding code patterns to prioritize for cleanup
• Preparing measurement files for an improvement loop
• Repeating targeted edits to reduce casts to any

Compare alternative ways to solve a coding problem, including when each approach fits and its advantages and drawbacks. Get a comparison table and a recommendation based on the current context, with code examples in detailed mode.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare authentication approaches
• Choose how to manage form state
• Evaluate data fetching or styling options

Examines project code, development history, tests, and documentation, then asks three focused questions to recommend a combination of AI-assisted development methods, with practical starting steps tailored to the project.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing development methods for a solo prototype
• Reviewing workflows for an existing SaaS product
• Selecting evaluation methods for an AI product

Explain code, design concepts, and system behavior at a chosen level of detail. Get a brief overview or a deeper walkthrough covering execution flow, design choices, alternatives, usage examples, and related code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understanding an unfamiliar file or function
• Tracing authentication or data flow
• Comparing design choices and alternatives

Build an MCP integration skill using a template that reads server-specific reference notes before calling tools. The Sentry example gathers unresolved errors, groups them by likely root cause, and produces a report with investigation suggestions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Design a skill that integrates with an MCP server
• Document server-specific query pitfalls
• Group Sentry errors by likely root cause

Read staged Git changes and suggest a message in Conventional Commits format, a structured way to describe changes. Include a concise subject and relevant details, then request confirmation before creating the commit.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Draft a message for staged changes
• Use a consistent commit message format
• Document the purpose of a change

Coordinate feature development from product direction through architecture, planning, validation, and implementation. Run the whole workflow or start at a selected stage, with saved decisions, review checkpoints, and a final pull request.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Take a feature idea through planning and implementation
• Review architecture before writing an implementation plan
• Validate an existing plan before execution

Remove a specific Git worktree, a separate working directory for a branch, after checking uncommitted work and merge status. Clean up branches and stale references, protect important branches, and provide reminders for related database cleanup.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Remove a worktree after finishing a task
• Check for unmerged or uncommitted work before removal
• Remove a worktree while keeping its branch

Analyze changed files and commits before opening a pull request, a proposed code change for review. Identify oversized or unrelated changes, suggest splits, and create a GitHub PR with a summary, description, and checklist.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare a pull request for review
• Check whether large changes should be split
• Create a draft PR with labels

Rebuild project context after clearing a conversation or returning to work. Review recent Git history, uncommitted changes, and TODO markers to get a structured summary of project status and suggested next steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Restoring project context after /clear
• Reviewing recent changes after a long break
• Checking unfinished work before choosing the next task

Audit Claude Code instruction rules against actual project files to find broken settings, overly broad scopes, and loading issues. Review each rule’s usefulness with the user, then apply confirmed changes or produce an audit report.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up Claude Code rules for the first time
• Investigating rules that apply too often or never
• Reviewing outdated instructions

Create a separate Git working directory for feature development without switching your current branch. The skill checks branch names and ignore settings, prepares dependencies, and starts background checks, with options for separate dependency installation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting feature work in a separate working directory
• Preparing a workspace for a bug fix
• Testing dependency upgrades with a fresh installation

Investigate bugs by tracing symptoms through code and recent changes, reproducing failures, and testing a specific cause before fixing it. Produce a focused correction, a regression test to catch recurrence, and an evidence-based debugging report.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate errors that keep returning after fixes
• Trace a regression through recent changes
• Analyze failures that occur only in certain environments

Organize open pull requests by size, automated check results, inactivity, and overlapping files. Review selected changes in depth, prepare comments for approval, and optionally create separate local working directories for hands-on review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prioritize a backlog of open pull requests
• Find overlapping changes and failing automated checks
• Draft and approve review comments before posting

Troubleshoot Claude Code problems by comparing reported symptoms with configuration scans and a troubleshooting guide. It asks follow-up questions when needed and proposes targeted fixes for permission prompts, tool connections, hooks, installation errors, and performance issues.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating repeated permission prompts
• Diagnosing MCP server connection failures
• Checking why settings or hooks are ignored

Clean up Git worktrees, separate working folders for branches, by identifying merged branches and reviewing unmerged ones. Preview deletions, preserve protected branches, and receive a report of removed folders and reclaimed disk space.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clean up worktrees after merging branches
• Preview deletions and potential disk savings
• Review unmerged worktrees individually

Analyze files or modules for duplicated code, excessive complexity, and violations of SOLID, five software design principles. Get prioritized refactoring suggestions with affected locations, risks, estimated effort, and testing needs to guide code improvements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing responsibilities in oversized files and classes
• Finding duplicated code and deeply nested logic
• Prioritizing refactoring by impact, risk, and effort