GitHub
Official@github · United States of America
How people build software.
Agent Skills by GitHub
Showing 532 vetted skills indexed across 4 GitHub repositories.
playwright-cli
Automate browser interactions and generate Playwright tests via the playwright-cli command line.
session-recovery
Detects and resumes interrupted Copilot CLI sessions by querying the session_store SQLite database.
architectural-proposals
Write structured architectural proposals with problem statements, decisions, risks, and scope definitions.
pr-review-response
Replies to GitHub PR review comment threads after fixing flagged code issues.
distributed-mesh
Configures git-based state synchronization for squads distributed across multiple machines.
squad-commands
Presents a categorized interactive menu of Squad CLI operations and coordinator workflows.
history-hygiene
Record final confirmed outcomes to history files instead of intermediate or reversed decisions.
ralph-two-pass-scan
Reduces GitHub API calls by filtering issue lists before selective hydration.
iterative-retrieval
Structures sub-agent spawning with a 3-cycle retry protocol and coordinator validation.
fact-checking
Validate claims and deliverables using counter-hypothesis testing with structured verdict reports.
docs-standards
Enforces Microsoft Style Guide and Squad formatting conventions in documentation.
personal-squad
Configures user-level AI agents that persist across projects via a global squad directory.
agent-collaboration
Standardizes worktree awareness, decision recording, and cross-agent communication patterns for squad agents.
reskill
Extracts shared patterns from agent charters and histories into reusable skills.
notification-routing
Route agent notifications to topic-based channels using CHANNEL tags and a provider-agnostic dispatcher.
reviewer-protocol
Enforces reviewer rejection workflows with strict author lockout semantics in multi-agent teams.
client-compatibility
Detects Copilot platform surface and adapts agent spawning behavior for CLI, VS Code, and fallback modes.
e2e-template-testing
Validates coordinator and agent template changes through end-to-end squad sessions.
cross-squad-communication
Coordinates queries, task delegation, and context sharing between independent Squad instances across repositories.
git-workflow
Enforces a dev-first branching model with worktree-based parallel issue workflows.
reflect
Extracts confidence-rated learning patterns from conversations to update agent history and team decisions.
project-conventions
Documents codebase conventions, patterns, and anti-patterns for AI agent guidance.
init-mode
Proposes and creates a .squad team structure after user confirmation.
error-recovery
Applies standard recovery patterns when agent tasks encounter failures.
Frequently Asked Questions About GitHub
FAQPage SchemaWhat specific tasks can I perform using these repository management capabilities?▼
You can manage issues, query pull requests, coordinate stacked branches, and enforce conventional commit standards. These capabilities allow for programmatic interaction with repository metadata and branch structures using standardized command-line interfaces.
Which technical personas benefit most from these infrastructure and deployment skills?▼
Cloud engineers, DevOps practitioners, and software developers focused on Azure environments benefit most. These skills target professionals responsible for maintaining infrastructure-as-code, monitoring application telemetry, and ensuring secure, compliant deployment patterns.
What are the primary prerequisites for implementing these deployment and diagnostic skills?▼
Implementation requires access to the GitHub CLI, appropriate Azure service principal permissions, and configured environment variables for network access. Users must also ensure their local environment supports the Model Context Protocol for seamless integration with existing development environments.