github-expert
Use when managing Git repositories, creating branches, handling pull requests, writing commit messages, or configuring GitHub Actions. Specializes in Git workflows, conventional commits, and CI/CD pipelines.
Explore AI skills for development, content, data and productivity. Compare the description and repository popularity before opening a skill.
Use when managing Git repositories, creating branches, handling pull requests, writing commit messages, or configuring GitHub Actions. Specializes in Git workflows, conventional commits, and CI/CD pipelines.
Run Phase 4 verification with Cursor and Gemini code review.
Create new GitHub Copilot-enabled projects from the base template with full security configuration, GitHub integration, and Archon project setup. Use when creating new projects, initializing repositories, or se...
Quality assurance, validation checks, metrics, and regression verification for pipeline outputs. Use when running validation suites, checking image quality, or defining acceptance criteria.
Set up GitHub repository integration for a SentryVibe project. Use this skill when the user wants to: - Connect their project to GitHub - Create a new GitHub repository for their project - Push their project co...
Guides through Red-Green-Refactor TDD cycle with strict test-first discipline. Helps write failing tests, suggests simplest implementations, and recommends when to refactor. Use when starting a new feature, wri...
Full autonomous feature development with single approval gate. Orchestrates: Research -> Plan -> APPROVAL -> Work (Atlas) -> Review -> Compound.
Safety checklist for DB/API changes covering compatibility, rollout, backout, and observability
See what's new in AG4 since your installed version
Analyzes existing code and specs to identify missing test coverage and formulate a robust Testing Plan. Used for adding regression tests, increasing coverage, and verifying legacy code behavior.
Execute development tasks using GitHub Copilot CLI for code generation, refactoring, feature implementation, and bug fixes. Use when the user asks to create code, add features, refactor, fix bugs, or generate t...
Use when CI/CD checks fail on a PR and you need to understand what went wrong
Use this skill ONLY for 'commit', 'save', or 'finish' prompts. Enforces strict manual approval, intelligent Topic-to-Global branching, and sync automation.
多 Agent 並行驗證框架 - 多視角測試驗證,發布許可決策
Manage feature specifications - create, track, and implement specs with structured templates and auto-generated indexes.
Release workflow for baoyu-skills plugin. Use when user says "release", "发布", "push", "推送", "new version", "新版本", "bump version", "更新版本", or wants to publish changes to remote. Analyzes changes since...
仕様を確定させるための壁打ち専用Agent。実装可能でテスト可能なSpec.mdを1枚で確定させる。
Orchestrates the Testing Strategy & Implementation process (Planning -> Execution -> Closing). Manages the workflow by invoking specialized sub-skills like code-testing-planning, tdd-refactoring, and tdd-audit....
Run comprehensive audit on completed work. Use after implementation is done, or when user says 'audit this', 'review the work', 'check for issues'. Spawns specialized auditors and fixes found issues.
Evaluate how well a codebase supports autonomous AI development. Analyzes repositories across eight technical pillars (Style & Validation, Build System, Testing, Documentation, Dev Environment, Debugging & Obse...
Build monitoring dashboards with Grafana. Covers panel types, queries, variables, alerting, provisioning, and data sources like Prometheus and InfluxDB. Use for infrastructure monitoring, observability, and met...
Claude Code CLI usage for automated/headless execution in Daytona sandboxes. Use when running Claude Code commands, configuring authentication, or setting up non-interactive mode.
Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives.
Verify code quality, type safety, memory leaks, and coding standards. Use when reviewing code, checking for issues, or validating a PR.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.