.github

Automatic quality control, linting, and static analysis procedures. Use when validating code changes for syntax correctness and project standards. Triggers on keywords: lint, format, check, validate, types, static analysis.

Refactoring and cleanup - improving code structure, removing dead code, eliminating duplication, or pre-merge cleanup. Use when code is hard to maintain, has dead code or debug artifacts, or needs pre-merge polishing.

Fix a GitHub issue end-to-end - from reading the issue, understanding requirements, implementing the fix, writing tests, and creating a commit. Use when given a GitHub issue number or URL to resolve.

Optimize code for readability, performance, maintainability, and security across Bash, Python, and Rust. Use when asked to improve code quality, optimize performance, add type safety, or refactor for idioms.

Create, debug, and optimize GitHub Actions workflows with security best practices. Use when asked to "create workflow", "fix workflow", "add CI", or needs help with GitHub Actions.

Review code changes (diffs, PRs, patches) and provide structured, actionable feedback on correctness, maintainability, and test coverage. Use when the user asks for a code review, requests feedback on a patch/PR, or wants an assessment of changes.

Craft immersive, high-performance premium web experiences with advanced motion, typography, and architectural craftsmanship. Use when building award-level landing pages, interactive portfolios, or components requiring top-tier visual polish.

Coordinates greenfield app scaffolding and rapid prototyping with official starters and focused sub-agents. Use when creating a new application or shaping a fast prototype.

Docker containerization expert - multi-stage builds, image optimization, security hardening, Compose orchestration, and production deployment. Use when working on Dockerfiles, image size, security, networking, or container orchestration.

Write, review, or edit technical documentation for any `.md` files or `docs/` directory. Use when asked to write docs, update README, or improve documentation quality.

Code context using Exa. Finds real snippets and docs from GitHub, StackOverflow, and technical docs. Use when searching for code examples, API syntax, library documentation, or debugging help.

Clarify requirements, ask high-leverage questions, and produce scoped PRDs with measurable acceptance criteria. Use when handling vague requests, new features, or explicit planning/PRD tasks.

Search web content using Exa advanced search across categories - personal sites/blogs, research papers, and tweets/X. Use when searching for web content, academic papers, blog posts, or social media discussions.

Orchestrates a six-step sequential repository cleanup: separating code from docs, organizing folder structure, removing legacy code, removing script clutter, pruning documentation sprawl, and cleaning documentation content (emojis, hyperbole, 'comprehensive'). Use when asked to clean up a repository, organize a project, remove legacy code, prune AI-generated docs, clean documentation style, run janitor, or perform a full repo cleanup. Triggers on: 'clean up repo', 'janitor', 'organize repository', 'remove legacy', 'prune docs', 'doc sprawl', 'clean docs', 'remove emojis from docs', 'repo cleanup', 'tidy repo', 'remove script clutter'.

Proactively discover and use MCP servers and MCP tools before native CLI tools. Use when searching, reading, editing, refactoring, planning, or researching so Copilot gets higher-signal results with less context waste.

Create, debug, and optimize GitHub Actions workflows with security best practices. Use when asked to "create workflow", "fix workflow", "add CI", or needs help with GitHub Actions.

Applies pragmatic cleanup rules to keep code concise, direct, and maintainable. Use when refactoring, trimming duplication, or tightening readability without redesigning the subsystem.

Refactoring and cleanup - improving code structure, removing dead code, eliminating duplication, or pre-merge cleanup. Use when code is hard to maintain, has dead code or debug artifacts, or needs pre-merge polishing.

GitHub CLI (gh) reference for repositories, issues, PRs, Actions, releases, and all GitHub operations from the command line. Use when working with GitHub API, automating workflows, or managing repos.

Optimize code for readability, performance, maintainability, and security across Bash, Python, and Rust. Use when asked to improve code quality, optimize performance, add type safety, or refactor for idioms.

Simplifies noisy implementations and improves maintainability during code changes. Use when refactoring, trimming duplication, or tightening readability.

Routes GitHub tasks to the right `gh` or `git` command family. Use when working with repositories, issues, pull requests, Actions, releases, or GitHub search from the terminal.

Validates AI guidance files with claudelint and agnix. Use when checking SKILL.md, CLAUDE.md, prompts, hooks, or MCP config for structural issues.

Guides Node.js, Next.js, and NestJS work with stack-aware architecture and verification checkpoints. Use when building, reviewing, or refactoring TypeScript services and web apps.

Coordinates built-in and custom agents when work can be parallelized or staged. Use when one agent is not enough for the task.

Runs repeatable browser flows with playwright-cli. Use when a task needs navigation, form entry, snapshots, debugging, or artifact capture in a real browser.

Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.

Optimize and validate AI assistant configurations (CLAUDE.md, copilot-instructions.md, AGENTS.md, MCP, hooks, settings). Use when asked to tune guidance, deduplicate overlapping rules, or lint agent config files with claudelint or agnix.

Summarize changes in a pull request with structured analysis of what changed, why, and potential concerns. Use when asked to review a PR, summarize PR changes, or understand what a PR does.