개발 스킬

Guide cleanup of redundant, unused, or low-quality code while preserving observable behavior. Classify problems, remove them in small passes, and compare before-and-after checks, with a separate review of drafted cleanup changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Remove duplicated code from AI-generated output
• Delete unused code with regression checks
• Inventory cleanup issues within selected files

Explore an unfamiliar code repository and build a practical guide to its structure, reading order, terminology, risks, and unknowns. Use observed files to suggest low-risk starter tasks and the commands needed to verify them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Getting oriented in an unfamiliar repository
• Choosing which modules and tests to read first
• Preparing repository guidance for a new contributor

Examine a technical proposal through independent perspectives, challenge their findings, and resolve objections. The result is a structured set of constraints, decisions, risks, and open questions for a separate planning workflow.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a technical proposal before planning
• Challenging assumptions behind a migration
• Organizing risks and unresolved questions

Test one uncertain technical choice through a small, isolated experiment before planning. Record what actually happened with an API, interaction, performance question, or integration, then prepare a decision record and handoff for the next planning step.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing an uncertain API choice before planning
• Checking performance with a small experiment
• Recording integration findings for a planning handoff

Plan server, API, and data changes before implementation. Define who can access each operation, consistent response formats, error handling, and database migration steps, with compatibility plans for existing consumers and rollback points for storage changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Design an API and its database schema before coding
• Clarify authentication and authorization checks
• Standardize success and error response formats

Analyze failed builds and CI checks, including automated tests, using fresh logs. Group failures by likely cause, distinguish newly introduced issues from existing ones, and prepare a minimal repair handoff with ordered verification steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a failed build or compile error
• Sorting type check, lint, and test failures
• Distinguishing new failures from existing problems

Compare Codex, Claude Code, Hermes coding, and oh-my runtimes before assigning development work. Identify missing tools or credentials, clarify how work will be handed over, and distinguish preparation from confirmed execution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing between Codex and Claude Code
• Checking tools and credentials before handing over work
• Reviewing readiness after changing execution environments

Turn a repository's actual code structure into one readable PlantUML diagram and rendered PNG. Show packages or modules, public elements imported elsewhere, and dependency links, with a visible legend explaining which details were omitted to keep the picture readable.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Introducing repository structure to a new teammate
• Exploring dependencies around a specific package
• Adding a code structure diagram to a PR or document

Draft commit messages and pull request descriptions using the repository’s existing conventions. Explain why the change matters and separate commands with observed execution records from planned or skipped checks, so validation claims match the available evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Drafting a commit message for a code change
• Writing a PR description using the repository template
• Separating executed tests from skipped checks

Create or update repository instructions for AI agents, documenting knowledge the code cannot explain. It preserves handwritten sections, labels commands by verification status, and records how generated files are rebuilt and checked.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create an AGENTS.md for a project
• Update build and test commands in CLAUDE.md
• Document how to regenerate and check generated files

Investigate incorrect application behavior by recording a reproduction, comparing competing explanations, and choosing low-cost observations that distinguish them. Prepare a fix only after evidence identifies the cause, carrying the reproduction forward as a regression test.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating tests that fail intermittently
• Finding the cause of an incorrect return value
• Diagnosing lost updates during concurrent processing

Review pull requests, code changes, or documented claims for bugs using concrete evidence. Receive prioritized findings, a separate assessment of whether requirements are met, and clear lists of checked areas, unanswered questions, and testing gaps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find bugs in a pull request before release
• Check changes against stated requirements
• Compare README claims with supporting evidence

Plan a behavior-preserving refactor of oversized UI components, addressing state management before hooks, component extraction, and naming. Preview changes with safety reasons, then hand off approved implementation with tests that check behavior before and after.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning how to split an oversized component
• Untangling state managed by many boolean flags
• Reviewing excessive useEffect chains

Prepare updates to a local code index, a map used to navigate a repository. Summarize structure and task-relevant context for handoff, while distinguishing planned commands from verified outputs and generated files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Refreshing an outdated code index
• Summarizing repository structure before planning
• Preparing task-specific files and entry points for handoff

Turn recurring tasks into reusable agent skills, or improve skills you already have. Draft instructions, compare test outputs with and without a skill, review quality and resource use, and refine descriptions so skills trigger for appropriate requests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn a recurring workflow into a reusable skill
• Improve an existing skill using test results
• Compare output quality, runtime, and token use

Explore an unfamiliar codebase before editing it. Produce a ranked map of important files, functions, callers, and dependencies, with source locations and evidence types to guide code reading and assess the likely impact of changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understanding an unfamiliar module before editing
• Finding callers of a function
• Assessing the impact of changed files

Turn reviewed wiki knowledge into a reusable Agent Skill package with SKILL.md, supporting references, and source records. Output goes to a review directory so a person can inspect it before choosing to install it.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn reviewed wiki knowledge into a reusable skill
• Combine related pages into an agent's working guide
• Create a skill package with traceable sources

Write and review Go error handling so failures carry useful context and are handled once. Covers error creation, wrapping, inspection, panic usage, and structured logging, where named fields help organize and search production logs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding context to returned errors
• Finding ignored errors and duplicate logging
• Reviewing custom error types and error matching

Use samber/mo in Go to represent missing values, failures, and alternative value types explicitly. Learn to choose Option, Result, or Either and combine processing steps, including pipelines where each step changes the value's type.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Representing optional JSON and database fields
• Combining operations that may fail
• Choosing types for valid alternatives

Design how Go requests carry cancellation signals, time limits, and request metadata through application layers. Helps investigate work that continues after cancellation, choose suitable context types, and separate background tasks from the request lifecycle.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing context propagation from HTTP handlers to database calls
• Investigating missing cancellation and lingering timers
• Keeping background work running after a request ends

Build Go services with uber-go/fx by connecting components and managing startup and shutdown. This skill covers dependency injection, which supplies components with what they need, plus reusable modules, signal handling, logging, and tests with substitute dependencies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connect components in a Go service with fx
• Manage server startup and graceful shutdown
• Organize application features into reusable modules

Restructure existing Go code while preserving its behavior. Uses gopls, Go's code analysis tool, to map affected code and apply changes, with targeted tests and small pull requests for renaming, extracting functions, and moving code between packages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Split oversized functions or types
• Rename identifiers across a Go codebase
• Move code between packages or resolve import cycles

Build in-memory caches in Go with samber/hot to reduce repeated backend reads. Choose eviction rules, set expiration and capacity, load missing entries, and monitor cache behavior while accounting for memory limits and loading failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Caching frequently requested database records
• Choosing eviction rules for access patterns
• Planning capacity and expiration within a memory budget

Review Go code for accidental crashes and silent data corruption. This skill guides safer handling of nil values, shared slice storage, numeric conversions, resource cleanup, and types that work safely without explicit initialization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing nil handling before a code change
• Checking numeric conversions and floating-point comparisons
• Preventing unintended changes through shared slices and maps