개발 스킬

Design modular LangGraph workflows by building reusable subgraphs and composing them into larger graphs. Handle state mapping, nested or parallel execution, clear component interfaces, and error boundaries between workflow parts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Breaking a large graph into reusable parts
• Composing subgraphs into a parent workflow
• Mapping state between graph components

Add human review and approval points to LangGraph workflows. Configure when execution pauses, how workflows resume after input, and how pending approvals are handled through timeouts, escalation paths, and notifications.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Pausing a workflow before a sensitive step
• Reviewing tool calls before execution
• Resuming a graph after human approval

Turn a multi-step software specification into a practical implementation plan before coding. It breaks work into small tasks, tracks dependencies, and gives each task a test-first sequence with expected results and a handoff path for execution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a feature from written requirements
• Breaking a large change into testable tasks
• Preparing implementation work for agent or batch execution

Investigate bugs, failing tests, and unexpected behavior by tracing data flow, comparing working examples, and testing one hypothesis at a time. It guides a focused fix and verification, and prompts you to reconsider the architecture after repeated failed fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracing the cause of a bug before changing code
• Investigating a test failure with one hypothesis at a time
• Reassessing architecture after several fixes fail

Use this skill to carry out implementation plans with independent tasks in the current session. It assigns a fresh subagent to each task and adds separate checkpoints for checking whether the work meets the request and whether the code is well built.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Delegating independent implementation tasks
• Checking work against a specification
• Reviewing code quality after requirements pass

Evaluate code review feedback against the actual codebase before making changes. Clarify the requirement, check technical fit, respond with acknowledgment or a reasoned objection, then implement valid suggestions one at a time.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assessing a reviewer’s proposed code change
• Checking feedback against current architecture
• Explaining why a suggestion may cause a problem

Decide what to do with a development branch after implementation is complete and tests pass. The workflow checks the base branch, presents four integration choices, carries out the selected option, and cleans up the worktree when required.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finishing a feature branch after tests pass
• Choosing whether to merge, open a pull request, or keep work
• Cleaning up a worktree after integration

Execute a written implementation plan in a separate session, handling tasks in batches and reporting for review between them. It supports resuming saved tasks, setting up a worktree, and finishing the branch after the plan is complete.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run a written implementation plan in batches
• Review progress between task groups
• Resume saved tasks in a separate session

Use this skill to split independent engineering problems across parallel agents. It helps coordinate separate investigations, check their solutions for conflicts, and verify the combined result with the full test suite.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating unrelated subsystem failures
• Parallel work on independent code changes
• Coordinating agent results before integration

Turn a technical plan into small development tasks with acceptance criteria, effort estimates, dependencies, and links to specification requirements. The skill also identifies work that can happen in parallel, maps the critical path, and includes testing tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Breaking a large feature into implementable tasks
• Estimating effort and the critical path
• Finding tasks that can run in parallel

Convert feature requests into user-focused requirements and stories with testable acceptance criteria. The skill clarifies business value, scope, edge cases, assumptions, and open questions so a specification can be reviewed before planning.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn a vague feature request into structured requirements
• Write user stories with testable acceptance criteria
• Clarify what is inside and outside a feature’s scope

Carry out feature development from a specification by preparing project files, implementing tasks in dependency order, and checking acceptance criteria with tests. It also validates requirement coverage and includes integration testing and a human review step.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implement a feature from a written specification
• Break implementation into dependent tasks
• Check task acceptance criteria with tests

Define and document project-wide principles for how a team works, including development practices, code quality, testing, UX, performance, security, and architecture. Use it to formalize existing standards or set governance before planning a new feature area.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Documenting existing team standards
• Updating project governance as it evolves
• Setting principles before a new feature specification

Turn specifications and project constraints into a technical architecture and implementation strategy. Compare technology options, map components and integrations, plan milestones and testing, assess risks, and prepare decisions for human review before breaking work into tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning the architecture for a new component
• Comparing technology choices against project constraints
• Identifying implementation risks and mitigations

Sets up an isolated Git worktree and new branch for feature work, detects the project setup command, and checks the existing test baseline. It helps prepare a separate workspace before carrying out an implementation plan.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting a feature in an isolated workspace
• Preparing to execute an implementation plan
• Checking the project's test baseline before changes

Set up LangSmith tracing for LLM applications built with LangChain or LangGraph. Capture nested execution traces, inspect run history and metadata, and compare runs to help debug agent behavior. Requires a LangSmith account and API key.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracing LangChain chains and LangGraph workflows
• Inspecting failed or slow agent runs
• Comparing executions across versions

Clarify goals and requirements before coding begins. The process reviews project context, explores design options and tradeoffs, then prepares a design document for approval before implementation planning continues.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a new feature before coding
• Comparing design approaches
• Clarifying requirements for a component

Build custom tools for LangChain agents and connect existing tools or APIs. Define structured inputs, descriptions, return types, and error handling so an LLM can understand how to call each tool; the skill also covers tool chains and pipelines.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a custom tool for a LangChain agent
• Connecting an agent to an existing API
• Defining structured inputs for tool calls

Build routing for LangGraph workflows so the next node depends on the current state or a routing decision. The skill covers conditional edges, router nodes, multiple branches, and fallback paths, helping structure workflows that handle different outcomes and errors.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Routing a workflow based on state values
• Adding branches for different decisions
• Designing fallback and error paths

Guides the creation and editing of agent skill documents and checks whether they work before deployment. It uses pressure scenarios with subagents to see whether a skill changes agent behavior, then refines the document to close gaps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a new agent skill document
• Editing an existing skill's instructions
• Checking a skill before deployment

Plan and work through complex coding tasks in stages, using tools, correcting mistakes, and checking the proposed solution. The source describes autonomous engagement without human intervention, but provides no implementation details beyond that overview.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Working through a complex coding task
• Breaking a coding task into steps
• Reviewing a proposed solution

Coordinate multiple agents working in parallel by choosing a communication structure, assigning roles, and setting a consensus method. Use checkpoints to check that work stays aligned, then support a shared final decision.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Coordinating parallel work across agents
• Choosing a structure for agent communication
• Checking that a team stays aligned during execution

Route tasks according to complexity, from quick code transformations to multi-agent coordination. It uses Q-learning, a method that improves choices from past outcomes, and selects among a WebAssembly fast path and Mixture-of-Experts models for different workloads.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Routing simple code edits to fast transformations
• Choosing a handling path for multi-file changes
• Reducing delay on common code transformations

Coordinate decisions and shared state across groups of AI agents using several consensus protocols. The skill covers Raft leader election, Byzantine fault tolerance for unreliable participants, Gossip state propagation, CRDT conflict-free merging, and configurable weighted voting thresholds.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a protocol for an agent swarm
• Synchronizing state across distributed agents
• Merging concurrent updates without conflicts