개발 스킬

Apply supported repetitive code edits with WebAssembly (WASM), a portable runtime, when a code pattern matches. Transforms include modernizing variable declarations, adding types or error handling, and converting Promise chains; unmatched patterns go to a coder fallback.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Modernizing repeated variable declarations
• Adding TypeScript annotations to matching functions
• Wrapping simple calls in error handling

Turn product requirements into a structured technical specification. The skill helps document technology choices, system architecture, data models, API contracts, and architecture decisions, then refine the document through architect feedback.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning interview notes into a technical specification
• Documenting architecture and technology choices
• Defining data models and API contracts

Guides test-first implementation by defining expected inputs, outputs, and edge cases before production code is written. It separates test writing from implementation, covers unit and integration tests as well as manual checks, and includes running tests to verify each task.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan implementation tasks with tests as the first step
• Define expected behavior and edge cases before coding
• Verify code changes with runnable tests and clear results

Investigate software bugs by reproducing the issue, forming and testing root-cause hypotheses, and narrowing the problem with logs or bisection. It helps guide a targeted fix and a follow-up check for regressions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating an unexpected test result
• Tracing a bug report to its root cause
• Finding the cause of a performance problem

Turn research findings into a practical implementation plan. The skill sets success criteria, breaks work into file-specific steps, places test specifications first, and records risks and verification methods, with the level of detail matched to the change’s impact.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a multi-file code change
• Breaking an implementation into verifiable tasks
• Defining tests before implementation

Carry out an approved implementation plan one step at a time, verifying each change and pausing at phase checkpoints. It investigates failures, tracks progress in the plan, and requires code and security reviews before completion.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing a change from an approved plan
• Verifying each implementation step
• Reviewing progress at phase checkpoints

Document significant technical decisions as Architecture Decision Records (ADRs). Capture the context, alternatives, chosen approach, and expected consequences, then organize the records with sequential numbers for future reference.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording why a technical approach was chosen
• Comparing options before an architecture decision
• Keeping decision context for future maintainers

Use this skill to understand a requested codebase investigation before opening files. It guides the agent through clarifying the goal, tracing relevant files and data flows, and writing findings to a dated research document before asking how to proceed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understanding an existing feature before changing it
• Tracing dependencies and data flows before planning
• Recording findings for a known engineering goal

Use this skill when a project idea or request is still unclear. It asks focused questions, surfaces assumptions, compares possible directions and trade-offs, then turns the chosen direction into clear requirements for research or implementation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarifying a vague feature request
• Comparing design options and trade-offs
• Aligning stakeholders on a direction

Set up and manage isolated Git worktrees for feature work. The skill helps name branches, install dependencies, check worktree status, compare changes with a base branch, sync updates, and clean up finished or stale worktrees.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting a feature in a separate worktree
• Checking changes against the base branch
• Syncing a worktree with updated base changes

Guide code changes through strict test-driven development: write a failing test first, add only enough production code to pass it, then refactor while tests stay green. The skill also calls for checks and separate commits at each phase.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting a change with a failing test
• Implementing one acceptance criterion at a time
• Refactoring with the full test suite passing

Use this skill to turn a task description into a structured software specification. It searches related code, resolves ambiguity with clarifying questions, breaks work into testable tasks, and refines acceptance criteria from review feedback.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a rough feature request into a specification
• Finding related code and existing patterns
• Clarifying assumptions before implementation

Analyze a codebase to map its structure, index source, tests, configuration, and APIs, then identify conventions such as naming, error handling, and testing practices. Produce a conventions guide, search index, and enforceable project rules.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Documenting conventions in an unfamiliar codebase
• Building searchable indexes of code and tests
• Generating project rules from existing patterns

Break an implementation plan into discrete work units, each with a definition-of-done checklist, file scope, dependencies, and flags for human review or safe parallel execution. Checkpoints highlight changes such as database updates, security-sensitive paths, and external API integrations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a large feature for orchestrated execution
• Defining file scope and completion checks
• Flagging work that needs human review

Use this skill to follow a pull request from creation toward merge. It monitors CI, handles review feedback, resolves addressed threads, and checks approvals, coverage, and conflicts to assess whether the PR is ready.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Monitoring CI for an open pull request
• Handling reviewer comments and code changes
• Resolving addressed review threads

Review a plan before presenting it for approval. Three independent reviewers assess feasibility, completeness, and alignment with the request, each giving a pass or fail verdict with specific references to plan sections.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a plan before asking for approval
• Finding missing edge cases in a work breakdown
• Catching scope creep against the original request

Prepare for development work by loading relevant rules, pitfalls, patterns, and decisions from a knowledge base. After the work, capture lessons and architectural choices so they can guide future tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing relevant project knowledge before starting work
• Recovering context after an interruption
• Recording lessons and decisions after implementation

Coordinate implementation and review work across OpenAI Codex and Google Gemini. It can route tasks between models, arrange independent review, and define escalation paths that may include Claude and a human reviewer.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Delegate implementation to an external AI tool
• Request an independent review from another model
• Set an escalation path across tools and reviewers

Review a feature or architecture proposal through six specialist perspectives: product, architecture, design, security, UX, and CTO. The process requires unanimous approval, consolidates objections, and allows up to three review rounds before escalating to a person.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a design for a new feature
• Checking a proposed architecture pattern
• Gathering security and usability feedback before implementation

Break a technical specification into small stories that one coder can complete in a batch. Map the existing modules and interfaces involved, order stories by dependency, estimate effort, and prepare a prioritized queue for implementation, including parallel work where appropriate.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a technical specification into implementable stories
• Ordering work by dependencies
• Estimating effort for each story

Review a software project for maintenance needs by checking branches, documentation, TODO markers, test coverage, and dependencies. Produce a project health score and remediation recommendations to help teams track and prioritize technical debt.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding stale branches and cleanup needs
• Scanning code for TODO and FIXME markers
• Checking documentation and dependencies

Maintain a DOT knowledge graph of architectural patterns and design decisions. Capture new knowledge, check graph consistency, find relevant patterns in the codebase, sync the graph with current code, and export it for visualization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording an architectural decision
• Checking graph consistency
• Finding code that uses a known pattern

Review code changes against four principles: avoid duplication, skip speculative features, use appropriate abstractions, and provide adequate test coverage. Get numeric quality scores and specific feedback tied to file names and line numbers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a pull request for unnecessary duplication
• Finding speculative features and overengineering
• Reviewing abstractions and encapsulation

Check GSD plans and phase artifacts for structural errors, missing files, broken references, and unmapped requirements. It returns a structured report showing passed checks, warnings, failures, and recommended fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a plan before execution
• Finding missing phase deliverables
• Scanning planning files for broken references