개발 스킬

Design and review concurrent Go code with clear goroutine ownership, shutdown paths, and error handling. Choose channels, locks, or atomic operations to protect shared data, and structure worker pools with controlled concurrency and cancellation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Design goroutine shutdown and cancellation
• Choose channels or mutexes for concurrent code
• Protect shared maps and counters

Enable or disable disconnect recovery for the current Codex thread running inside tmux, a terminal session manager. Explicit on and off commands control the setting, and the skill reports the command result or error.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Enable disconnect recovery for the current Codex thread
• Disable disconnect recovery for the current Codex thread
• Check the result or error when changing recovery settings

Turn a high-level task plan into detailed execution notes, an evidence map, acceptance criteria, and worker handoff instructions. Return the documents and a structured JSON manifest for import by the workflow's scripts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Detailing a task before assigning it to a worker
• Mapping task requirements to supporting evidence
• Preparing acceptance criteria and verification notes

Assess a supplied task and execution contract, then propose one to four workgroups with clear scopes, dependencies, and verification references. Returns a structured plan for a controller to validate and use.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning how to divide a development task
• Identifying work that can proceed in parallel
• Defining verification requirements for each workgroup

Submit implemented and verified work to its assigned Reviewer, the agent responsible for checking it. Follow a bounded review and repair process, and report completion only after approval, or return a blocked or rework outcome.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Submitting implemented work for review
• Applying requested repairs and resubmitting
• Requiring review approval before completion

Carry out one clearly scoped implementation or investigation task, verify the work where possible, and submit evidence to the assigned reviewer. Reports changed paths, verification results, and blockers while preserving controller authority.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing a change within assigned file paths
• Investigating a narrowly defined issue
• Submitting verification evidence to an assigned reviewer

Consult a historical reference for describing why an agent role is needed, what blocks it, or when it can be released. It separates evidence supplied by the AI session from lifecycle operations owned by the runner script.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review the boundary between AI sessions and runner operations
• Describe a needed agent role and the reason for requesting it
• Organize blockers and evidence for readiness or release

Clear the conversation context of one or more CCB-managed agents while preserving project state. The skill runs the matching ccb clear command and reports its output, with specific handling for DSH sessions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clear an agent's context while preserving project state
• Clear several agents' contexts in one command
• Clear a DSH context while retaining old session logs

Capture reusable lessons from agent work, including user corrections, recurring problems, and useful methods. Keep observations for weekly reviews that inform skill updates, and identify repeated workflows that could become new skills.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preserve reusable lessons from user corrections
• Review accumulated skill improvements weekly
• Identify repeated workflows as new skill candidates

Reviews generated skills against the Ars Contexta knowledge base and proposes improvements with research support. Checks existing customizations, explains risks and workflow changes, and applies only the updates the user approves.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing generated skills for methodology improvements
• Comparing customizations with recommended changes
• Choosing updates based on research support and risk

Audit openai-go during recurring maintenance to identify correctness, security, performance, and design issues. Receive at most one evidence-backed recommendation, with compatibility considerations, generated-code ownership, validation requirements, and the next area to review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recurring openai-go maintenance audits
• Rotating security and architecture reviews
• Selecting one evidence-backed improvement

Review openai-go pull requests, branches, or commit ranges for Go behavior, SDK compatibility, generated-code ownership, and security. Get prioritized, actionable findings with evidence, suggested fixes, completed checks, and clearly stated review gaps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing openai-go pull requests
• Checking SDK compatibility across commits
• Reviewing credential and provider changes

Explain a team's shared Claude Code setup to new teammates. Summarize what each configuration file controls, distinguish shared and personal settings, and identify what the team-kit plugin adds without changing files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Onboarding a teammate after cloning the repository
• Understanding shared versus personal Claude Code settings
• Checking what the team-kit plugin adds

Turn a repeated workflow into an agent skill with SKILL.md and supporting reference files. Plan its structure, improve existing instructions, and assess quality using a ten-part rubric with scores and prioritized recommendations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a repeated manual workflow into a skill
• Planning and writing a new agent skill
• Fixing instructions in an existing skill

Try a simple skill invocation with `/example`, which returns a friendly greeting and explains that the demo was loaded from the workspace skills directory. The sample also shows the basic file structure for creating your own skills.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Trying a skill through the /example command
• Checking the demo’s greeting and explanation
• Learning the basic structure of a custom skill

Run coding agents from scripts, continue saved conversations, submit queued tasks, and compare responses across agents. Use structured JSON output to collect results and build workflows that coordinate multiple agents.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continue an agent conversation across commands
• Compare responses from multiple coding agents
• Collect agent results as JSON in scripts

Review code using shared OpenClaw instructions and a Python helper, while also following the target repository’s review requirements. This skill points to a common installation that supplies the actual review procedure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing code with shared OpenClaw instructions
• Applying repository-specific review requirements
• Keeping shared review instructions up to date

Launch and monitor coding agents such as Claude Code and Codex through Agent of Empires. Capture their output, send instructions, and organize parallel development using separate Git working directories, groups, and profiles.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Launch coding agents for a project
• Monitor progress and review agent output
• Work on multiple fixes in separate Git working directories

Launch and monitor coding agents such as Claude Code and Codex through Agent of Empires. Capture their output, send instructions, and organize parallel development using separate Git working directories, groups, and profiles.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Launch coding agents for a project
• Monitor progress and review agent output
• Work on multiple fixes in separate Git working directories

Audit branch changes for maintainability, including oversized files, tangled conditionals, unclear types, and misplaced logic. Identify ways to preserve behavior while removing unnecessary complexity, and produce a summary report with detailed supporting reports.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing structural quality before approving a PR
• Reconsidering how to split a growing file
• Finding simpler alternatives to tangled conditionals

Investigate why code or a design decision took its current form using version history and available connected sources. Produce a cited explanation of motivations and tradeoffs, separating documented findings, reasonable inferences, competing explanations, and gaps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understanding the reasons behind a design decision
• Tracing the background of retries and defensive checks
• Investigating the evidence behind a threshold

Apply consistent rules when reading or editing TypeScript files. Model valid states with types, validate incoming data, avoid unchecked casts, and review tests and logging so code behavior and failures are easier to assess.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review type design in .ts and .tsx files
• Validate data received from external sources
• Rework unsafe casts and overly loose types

Reviews the current conversation from three perspectives to find reusable lessons and propose concrete skill improvements. It separates findings into accepted, rejected, and backlog items, with user approval required before applying accepted edits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing lessons from a completed agent session
• Turning repeated mistakes into skill improvements
• Separating skill edits from structural fixes

Guide validation and error handling toward system boundaries, where external data enters the application. Keep business rules in functions independent of frameworks, use validated types internally, and avoid repeating checks throughout the code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Organizing configuration validation
• Separating business rules from framework code
• Reviewing repeated internal checks