Coding standards, frameworks, refactoring, and code review (15.5K skills)
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.
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.
Set shared development rules for an agent team: keep specific agent names out of product code, tests, and CI configuration, verify affected tests before finishing, and record lessons learned from mistakes.
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.
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.
Guide changes to the Squad CLI using its established coding conventions. Covers Node.js built-ins, standard tests, readable errors, cross-platform paths, and initialization and upgrade behavior that preserves user-owned files.
Prepare architecture proposals before implementation so the team can agree on a direction. Organize evidence, technical choices, effects on existing work, risks, and the first release’s scope into a document with clear recommendations and decision owners.
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.
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.
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.
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.
Coordinate work across AI agents with shared rules for locating team files, recording decisions and their reasons, and requesting help. It also defines who owns revisions after a reviewer rejects an artifact.
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.
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.
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.
Document responses to GitHub pull request reviews by replying to each comment thread after fixes are pushed. Connect feedback to specific changes and commits, explain rejected suggestions, and selectively resolve automated review threads.
Follow Squad's Git workflow from issue branches through pull requests and cleanup. It covers development from dev, isolated directories for parallel issues, coordinated changes across repositories, and promotion to preview, insiders, and stable releases.
Format gh-aw terminal output using Go struct tags, annotations attached to data fields. Set labels and section titles, format numbers and dollar amounts, omit empty fields, and render lists of records as tables.
Create and manage coding tasks for GitHub Copilot from the command line. The skill covers writing clear implementation requests, listing and updating sessions, and connecting task creation to automated GitHub workflows that produce pull requests for review.
Publish gh-aw changes as a draft pull request from a GitHub Copilot cloud agent. The workflow checks repository templates, runs required local validation, commits and pushes through runtime tools, and records the validation results in the PR.
Create GitHub Copilot coding tasks from plain-language instructions using the GitHub CLI extension. Tasks become issues that trigger code changes and pull requests for review, with commands to list tasks, inspect details, and update instructions.
Define and check GitHub Copilot instructions and specialized agents using Markdown files. It explains file locations, configuration fields, tool access, path-specific rules, and workflow integration, with examples for documentation, testing, reviews, and other development tasks.
Query GitHub issues and extract or summarize selected fields using jq, a JSON filtering tool. Inspect data structure and size before retrieving detailed results, then filter by status, author, labels, comments, or creation date.
Query GitHub Discussions and extract titles, authors, categories, or answer status. First inspect the data structure and size, then use jq, a JSON filtering tool, to select relevant discussions, sort updates, or count entries by category.