개발 스킬

Helps an agent evaluate code review feedback against the actual codebase before making changes. It covers clarifying unclear requests, explaining technical disagreements, prioritizing fixes, and testing each change for regressions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarify ambiguous code review comments
• Check whether suggestions preserve existing behavior
• Explain disagreements using code and test evidence

Execute an implementation plan by assigning each independent task to a fresh helper agent in sequence. Review specification compliance and code quality after each task, track decisions in files, and finish with a review of the entire branch.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Execute a plan with separate implementation and review roles
• Check specification compliance and code quality after each task
• Resume work using a persistent progress ledger

Investigate bugs, failing tests, and unexpected behavior through reproducible steps, logs, and comparisons with working code. Follow four stages to identify the root cause, test a hypothesis, apply a focused fix, and verify the result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating failing tests
• Tracing production bugs to their source
• Finding where a build or integration breaks

Prepare a separate Git working directory for feature development, then install project dependencies and run baseline tests. Check for existing isolation first, use native worktree tools when available, and otherwise fall back to Git.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting feature development in a separate working directory
• Preparing a workspace before executing an implementation plan
• Reusing an existing isolated workspace

Turn development ideas into agreed designs through focused conversation. The skill clarifies goals, constraints, and success criteria, then chooses a process for feasibility research, small changes, or new systems before implementation begins.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarifying the purpose of a new feature
• Agreeing on a design for an existing code change
• Comparing approaches for a new system

Turn development requirements into an implementation plan with specific files, function signatures, tests, and verification commands. Use it before coding to document decisions and divide the work into independently testable tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a feature before writing code
• Handing implementation work to another developer
• Checking that planned tasks cover every requirement

Review AI agent session logs to document repeated work, departures from plans, delays, and token usage. Produce an evidence-based report with file and line references, and prepare a bug report when appropriate.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating delays or token usage in a session
• Reviewing repeated work or departures from a plan
• Checking whether a skill was activated

Carry out an existing implementation plan one task at a time in the current session. Verify each task with tests, record progress and decisions in a file, and review the whole branch after implementation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing an existing plan in a single session
• Resuming work from a saved progress ledger
• Recording decisions when a plan conflicts with its specification

Investigate independent bugs or test failures concurrently by assigning each problem area to a separate agent. Define clear boundaries and expected reports, then review the fixes, check for conflicts, and run the full test suite before integration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate unrelated test failures in parallel
• Split independent subsystem bugs among agents
• Write focused assignments with clear boundaries

Create and improve agent skills by testing behavior before and after adding guidance. The skill applies test-driven development to SKILL.md documents, covering structure, discovery descriptions, supporting files, and checks that reveal unclear or ineffective instructions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a reusable skill from a working method
• Testing an existing skill before deployment
• Improving descriptions so agents find relevant skills

Finish completed development work by verifying tests and the target branch, then choosing a local merge, a pull request, or leaving things unchanged. Cleanup follows the chosen action and respects who manages the working directory.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Merging a completed feature into its base branch
• Opening a pull request while keeping the working directory
• Cleaning up branches and working directories after a merge

Write Chinese code review feedback that clearly distinguishes required fixes, suggestions, and optional advice. Use question and suggestion templates, organize review summaries, and follow guidance for mixed Chinese-English comments and commit messages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Writing Chinese review comments with clear priorities
• Rephrasing blunt feedback as questions or suggestions
• Standardizing Chinese-English comments and commit messages

Set up Git workflows for Gitee, Coding.net, 极狐 GitLab, and CNB with platform-specific connection and authentication examples. Choose branching rules, standardize Chinese commit messages, and adapt automated testing and deployment configurations to your team's workflow.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Configure connections and authentication for Chinese Git platforms
• Choose branching rules that fit the team
• Standardize Chinese commit messages and review templates

Analyze Android packages by decompiling them into readable code. Identify app structure, list API endpoints—the addresses used for network requests—and trace how screen actions reach those requests, producing source files and structured documentation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating the internal structure of Android packages
• Listing API endpoints used by an app
• Tracing screen actions through to network requests

Create a temporary workbench for one existing component, using realistic mock data and a grouped state switcher. View loading, empty, error, access, and other implemented states individually, with a link to each state.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing loading, empty, and error states in a table
• Checking displays for different roles and plans
• Inspecting layouts with realistic amounts of sample data

Turn a Figma file or design image into a working interface using the project's existing components and design tokens, its shared visual settings. Compare the implementation with the design and report differences, missing states, and parts awaiting backend connections.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implement an interface from a Figma design
• Build a screen from a supplied design image
• Reuse existing components and shared visual settings

Review a branch, pull request, or uncommitted changes for interface problems involving accessibility, layout, text, typography, and color. The report distinguishes newly introduced issues, regressions, and existing problems, including effects on screens that use changed components.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review interface changes in a pull request
• Check whether shared component changes affect other screens
• Find accessibility regressions before merging

Manage agents on a host by listing their capabilities, reading source code, and downloading or deploying agents in the smith namespace. Check available language model connections and their roles without exposing API keys.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find available agents and check their capabilities
• Study existing agent source code
• Download and deploy smith agents for editing

Call Yao processes to query data models or run scripts. Check which operations are permitted, inspect their required arguments through the documentation workflow, and execute a process using its full name.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check which Yao processes are permitted
• Query records through a data model
• Run a named Yao script

Manage Git user settings and authentication for a specific workspace. Set configuration values, register HTTPS access tokens, and import SSH keys, with options to list or remove credentials without exposing stored tokens or private keys in listings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting Git user information for a workspace
• Registering an HTTPS access token
• Importing an SSH key for Git authentication

Look up callable processes in Yao, inspect their arguments and return types, and check whether a process name is valid. Use the documentation to prepare calls and find suggested alternatives for misspelled names.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find Yao processes by keyword
• Check arguments and return types before calling a process
• Validate process names when a call fails

Plan agent replacements while keeping the same workspace identity. The skill separates creating a successor from assigning it to the existing role, records both outcomes, and prepares durable handover notes and traceable replacement history.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Replace an agent while preserving its workspace identity
• Prepare recap notes for a successor
• Track successor creation and assignment separately

Helps older OpenRig instructions that reference software-for-agents lead to its maintained successor, agent-operated-software. This temporary compatibility redirect identifies where to find the current architecture and operating guidance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Following older OpenRig instructions
• Finding guidance under the successor skill name
• Checking the compatibility redirect's retirement schedule

Design and run bounded procedures in environments where current conditions are uncertain. The skill separates agent judgment from precise tool actions, verifies each effect, and records checkpoints so interrupted work can resume from observed evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing procedures for environments with varying conditions
• Resuming interrupted operations from verified evidence
• Deciding whether an agent or ordinary code should control a procedure