Capture interface or documentation pages with Playwright and embed the screenshots in a GitHub pull request description. Reviewers can inspect visual changes without checking out the branch, using images hosted on a temporary branch.
Extract lessons from corrections, praise, and unexpected cases in conversations. Organize findings by confidence level and propose updates to individual agent histories or shared team decisions, with changes shown for approval before saving.
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.
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.
Clean up stored agent state in `.squad/` by compressing histories, pruning old logs, archiving stale decisions, and removing orphaned inbox files. Use it after long sessions or before starting work with many agents to reclaim context space.
Plan task handoffs between agents on different machines using Git to share YAML task and result files. This implementation specification describes validation, execution limits, result reporting, and GitHub Issues as an additional route for urgent requests.
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.
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.
Prepare an open pull request for human merging from a GitHub Copilot cloud agent. Address review threads, validate changes locally, resolve branch conflicts, and report remaining blockers, including the need for a human to rerun CI.
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.
Follow gh-aw development conventions with checks matched to Go, JavaScript, and workflow changes. Provides staged validation commands, capitalization rules, and pointers to more detailed guidance for specific parts of the codebase.
Guides the refactoring of large JavaScript files into smaller CommonJS modules within gh-aw. It covers source placement, function exports, tests, and action builds so extracted code remains testable and is included in generated actions.
Review and implement gh-aw workflows and Go code with security checks for untrusted input, shell commands, dependency versions, and permissions. The skill also covers event-specific conditions and tools that inspect workflows for errors and security risks without running them.
Resolve merge conflicts in generated workflow lock files by rebuilding them from merged Markdown sources. The skill checks for leftover conflict markers, stages regenerated files, and verifies that unresolved paths and whitespace errors are cleared.
Rewrite long prompts into shorter, clearer instructions for language models. Preserve essential requirements while removing repetition, defining scope, and making output formats and success criteria explicit to reduce ambiguity and unnecessary tokens.
Use this reference to configure GitHub access for AI agents through MCP, a protocol for connecting agents to tools. Covers tool selection, authentication, read-only access, and migration of existing workflow settings.
Write and edit gh-aw documentation using Diátaxis, a framework that separates learning, task instructions, reference, and explanations. Apply Astro Starlight Markdown conventions while keeping examples focused and removing repeated or unnecessary content.
Use concrete JSON and Markdown examples to structure Sergo tool caches, strategy histories, improvement tasks, and reports. The templates show which fields to record and how to organize findings for review.
Implement HTTP headers that pass GitHub Actions secrets through environment variables in gh-aw’s copilot engine. This reference explains secret extraction, generated MCP configuration, execution-step settings, and tests for keeping secret values out of configuration files.
Helps agents work within gh-aw tool restrictions by checking the allowlist, diagnosing denied calls, and choosing permitted alternatives. It guides agents to complete available work and report specific limitations before repeated denials end the session.
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.
Guide gh-aw release preparation and assess whether command-line changes break existing usage. The reference covers changesets, which record release changes, version previews, release steps, firewall log classification, and summaries of Go module usage.
Configure Skillz in Docker to expose SKILL.md instructions, resources, and helper scripts as tools for MCP clients, applications that connect to tool servers. Covers skill folder layouts, ZIP packaging, environment variables, and workflow integration.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)