스킬 찾기

Review cross-platform code and Git commands for filename, path, and shell compatibility issues. Apply shared timestamp utilities, platform-aware path handling, and file-based commit messages when working across Windows, macOS, and Linux.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating timestamped filenames that work on Windows
• Reviewing path construction and comparison across platforms
• Writing multiline Git commit messages in PowerShell

Guides Squad documentation writing and review using Microsoft Style Guide rules and project conventions. It covers clear English, consistent page structure, practical examples near the top, and matching test updates when documentation pages are added.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Standardizing English documentation style
• Structuring feature and scenario pages
• Reviewing preview notices and related links

Manage rejected work in an AI team by assigning revisions to a different agent. Defines author lockouts, independent revision requirements, specialist escalation, and when the coordinator must ask the user to resolve a deadlock.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reassigning revisions after a review rejection
• Bringing in an agent with specialist expertise
• Checking that a revision author is eligible

Explains how Squad CLI records its installed version and handles upgrades, including which files it replaces or preserves. It also covers checking npm release channels and using cached version information when assessing available updates.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking the installed Squad CLI version
• Reviewing files affected by an upgrade
• Checking npm release channels

Review technical claims and deliverables by checking evidence and testing alternative explanations. Confirm that references and API endpoints exist, then report verified, unverified, or contradicted claims alongside evidence and an overall review verdict.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check claims in technical documents
• Verify URLs, package names, and API endpoints
• Review another agent's deliverables

Reduce GitHub API calls during issue monitoring by scanning basic issue details first, then fetching full descriptions and comments only for selected issues. Filters use assignees, status labels, and title patterns to narrow the list.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reducing API calls during recurring issue monitoring
• Filtering out assigned or blocked issues
• Fetching descriptions and comments only for relevant issues

Set up separate commands for personal and work GitHub accounts on Windows. Detects accounts already signed in through GitHub CLI, asks which serves each role, creates PowerShell shortcuts and CMD wrappers, and verifies the selected usernames.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Separate personal and work GitHub operations
• Add account-specific shortcuts to PowerShell
• Run account-specific GitHub commands from CMD

Find interrupted Copilot CLI sessions in stored history, review conversations, checkpoints, files, and linked issues or pull requests, then resume unfinished work with the context needed to understand where it stopped.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resuming work after a terminal crash
• Finding yesterday's work by topic or project folder
• Checking how far pull request preparation progressed

Learn how to start an AI team with Squad in Copilot CLI. This reference explains how to invoke the coordinator agent, find the command catalog, and initialize a new project while avoiding common invocation mistakes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learn how to invoke the Squad agent
• Find the catalog of available operations
• Check how to initialize a new project

Find unanswered GitHub issues and discussions, read their full conversations, and prepare response drafts. Organize drafts by response type and confidence for human review, with action logs and commands that help people post approved replies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding community questions that still need a team response
• Drafting replies to bug reports and feature questions
• Reviewing sensitive responses before posting

Guide agents in handling credentials safely by avoiding live environment files, using placeholders in shared records, checking staged changes before commits, and escalating secrets already exposed in Git history.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Documenting configuration without exposing credentials
• Checking shared agent records before committing
• Responding to secrets found in Git history

Guide npm package releases through dependency checks, version alignment, publishing procedures, and post-release smoke tests, which are basic installation and operation checks. It also documents fallback steps for failed automation and project-specific rules about who initiates releases.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check dependencies before publishing to npm
• Align package versions and CHANGELOG entries
• Handle failed release workflows

Structure delegated agent tasks with clear goals, success criteria, and a three-attempt limit. Provides handoff templates and coordinator checks, plus rules for escalating unresolved work and turning research findings into concrete follow-up actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing clear task briefs for sub-agents
• Checking delegated work against acceptance criteria
• Retrying incomplete tasks with specific corrections

Set up an AI agent team by proposing roles and names for a project, then creating shared team files after confirmation. Initialize member context, decision records, and logs so the team starts with a common project background.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up an AI team for a new project
• Review team roles before creating files
• Give agents shared project context

Guide agents through failures with timed retries, alternative methods, targeted fixes, and clear handoffs. It also explains when to continue with partial results, helping teams choose a recovery approach that fits the problem.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retrying temporary API and network failures
• Switching methods when a tool fails
• Diagnosing build and test errors

Coordinate work across independent Squad installations by discovering their capabilities and delegating tasks across repositories. It guides context sharing, acceptance criteria, and progress tracking, while distinguishing persistent Squad teams from temporary groups of agents.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding another Squad with the capabilities a task requires
• Handing off work for features that span repositories
• Tracking delegated infrastructure or support requests

Consult Squad’s file ownership and authority rules to decide where state belongs, who may read or write it, and which source takes precedence. Distinguish authoritative configuration from append-only histories and reference material.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Decide where Squad state or decisions should be stored
• Check who may read or write a particular file
• Resolve conflicts between file contents

Set up a Squad agent team in a repository that has no team yet. Propose roles and persistent names, obtain user confirmation, then create team files, shared context, built-in member policies, and merge settings for accumulated records.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a Squad team in a new repository
• Choosing agent roles for a project’s technology stack
• Giving new agents shared project context

Plan how Squad agents separate current tasks, summarized history, and lasting reference knowledge so each launch receives relevant context. The skill provides loading rules and prompt templates; the supporting runtime is still a design proposal.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan which context agents load at launch
• Separate session history from lasting knowledge
• Design context templates for interrupted work

Review agent charters and histories, extract repeated knowledge into shared skills, and shorten the original documents while preserving unique responsibilities. A before-and-after size report shows how much context each agent saves.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reducing oversized agent charters
• Extracting duplicated knowledge into shared skills
• Condensing accumulated agent histories

Extend safe-output jobs, which execute agent-generated actions, to reference newly created issues through temporary IDs. The guide covers job dependencies, issue-number resolution, input validation, tests, and warning-based handling of unresolved references.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Linking sub-issues to a parent created in the same run
• Adding temporary ID resolution to another safe-output job
• Testing temporary ID validation and job dependencies

Manage work and personal GitHub identities in agent workflows by checking the active account and selecting credentials for each operation. It covers personal repository pushes, pull requests from forks, and separate configuration directories for account isolation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Pushing to a personal repository from a work account environment
• Creating a pull request from a personal fork
• Separating authentication across parallel agents

Guides agents to record confirmed final outcomes in history.md and correct entries when decisions change. This keeps handoff records clear enough for future agents to understand what actually happened without checking other files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording confirmed task outcomes
• Correcting a decision that was reversed
• Preparing history for an agent handoff

Document project-specific development rules for an AI agent using a starter template. It provides sections for error handling, testing, code style, file organization, examples, and practices to avoid, ready to fill with actual conventions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Documenting project-specific development rules
• Organizing testing and error-handling conventions
• Recording code examples and practices to avoid