개발 스킬

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

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• Reviewing outdated instructions

Analyze TypeScript and JavaScript code for reusable design structures known as GoF patterns. Get detection reports, quality scores, and prioritized refactoring suggestions that account for the frameworks and libraries already used in the project.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find existing design patterns in a codebase
• Plan refactoring for complex conditionals
• Evaluate the quality of a pattern implementation

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

Polish Korean commit messages drafted by AI into natural developer language. The skill removes stiff wording and literal translations while preserving the stated changes, commit type, scope, issue numbers, and code identifiers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Polishing Korean commit message drafts
• Keeping Conventional Commits prefixes intact
• Reviewing several commit messages together

Compare baseline and current Pinot benchmark results from JMH, a tool for measuring code performance. The skill uses a separate baseline worktree, a working directory kept apart from the current code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare Pinot benchmarks before and after a code change
• Check performance differences against a baseline
• Keep baseline code in a separate working directory

Review Apache Pinot changes for correctness in null handling, numeric types, type-based processing, and resource lifecycles. Use it to examine changes to calculations, aggregations, window functions, and segment cleanup or persistence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing changes to null handling
• Checking branches based on data or index types
• Reviewing numeric processing in aggregations and window functions

Review architecture changes in Apache Pinot, focusing on module dependencies, extension interfaces, abstractions, and class placement. Use it to examine changes that cross module boundaries or introduce new plugins and interfaces.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing classes moved between modules
• Checking new extension interfaces or abstract classes
• Reviewing new plugin directories

Validate and fix Pinot pre-commit checks for modules affected by a change. Use it before a commit or pull request to address check failures in the relevant parts of the project.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking affected modules before a commit
• Validating changes before a pull request
• Fixing pre-commit check failures

Review the scope and process of Apache Pinot changes, including pull request descriptions, reverts, retries, and compatibility notes. Use it to examine large changes, test workarounds, and documentation needed for changes that break backward compatibility.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing large changes across multiple modules
• Reviewing Revert or Hotfix pull requests
• Checking retries and sleeps added to tests

Review Apache Pinot changes affecting frequently executed code or making performance claims in a pull request. Relevant areas include operators, segment readers, aggregation functions, and locking inside loops that process individual rows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review changes to frequently executed processing code
• Review performance improvement claims in a pull request
• Review locking inside per-row loops

Review Apache Pinot changes against naming and API conventions, including public names, method signatures, REST endpoints, JSON fields, and documentation. Use it when adding or renaming elements exposed to other code or users.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing public class, method, or field names
• Checking new enum constants or DataType values
• Reviewing REST endpoints and JSON fields

Review Apache Pinot changes for compatibility with existing configurations and consumers. Covers public APIs, extension interfaces, serialized data formats, and REST responses, helping focus code review on changes that may affect existing users.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing changes to configuration fields
• Checking compatibility after extension interface changes
• Reviewing enum and schema type changes

Review Apache Pinot changes for concurrency and state safety, including locks, shared callbacks, lifecycle changes, and distributed metadata. Use it to examine how changes affect shared state when multiple operations run at the same time.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing changes to locks and atomic operations
• Checking shared callback registration changes
• Reviewing Helix state transitions and ZK node changes

Start a local Pinot quickstart and verify it using modes supported by the checked-out code. Use it to bring up a local trial environment that matches the version you are working with.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Start a local Pinot quickstart
• Use a mode supported by the checked-out code
• Verify the quickstart after startup

Find API patterns and examples for coding agents with ADK, the Agent Development Kit. Covers tools, state, callbacks, multi-agent coordination, and graph workflows, with Python and Go references plus guidance on studying existing implementations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding tools and callbacks to an ADK agent
• Implementing state management and agent coordination
• Designing branching and parallel graph workflows

Guide development of a LangChain or LangGraph project created with agents-cli. It explains tool additions, local runs, evaluation, and serving while identifying the required graph structure and commands that differ from ADK projects.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding tools to an existing agent
• Running and evaluating an agent locally
• Editing a graph while preserving its required interface

Create starter projects for AI agents, add deployment configuration and automated build and release pipelines to existing projects, or update generated project files. Supports Python and Go ADK templates and a prototype-first approach.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting a Python or Go agent prototype
• Adding deployment configuration to an existing project
• Adding an automated build and release pipeline

Guide AI agent development from requirements and project setup through implementation, behavior evaluation, deployment, and monitoring. Provides coding rules, debugging steps, and links to specialized skills so each phase follows a defined process.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning an agent's requirements and architecture
• Running and debugging an agent locally
• Evaluating responses and tool use before deployment

Use a starter template to learn how an agent skill is organized and outline its intended use, required inputs, steps, and output format. Replace the placeholder body with your own working instructions before relying on it.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learn the basic layout of an agent skill
• Start drafting a custom skill
• Describe when an agent should select a skill

Apply related edits across several files using a unified diff, a file describing code changes. Check the patch with Git before applying it, and rebuild rejected patches using the current file contents.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Applying one related change across three or more files
• Handling repetitive edits or whitespace-sensitive changes
• Reusing a patch from a PR or git diff

Save the current code state in a local Git commit before risky changes, then return to that checkpoint if needed. Useful for multi-file refactoring and trying another approach after an unsuccessful edit.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving a checkpoint before multi-file refactoring
• Returning to saved code after unsuccessful changes
• Cleaning up temporary commits before pushing a PR branch

Locate function and class definitions, usages, and relevant files with ripgrep, using text patterns and file filters. Search Git history to see when text appeared or disappeared and investigate who changed specific lines.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding function or class definitions
• Locating usages of a particular function
• Narrowing searches by file type or path