Generate a complete OAF-compliant agent package from an Agent Case (requirements) and Agent Design (architecture). Use when asked to "package an agent", "generate an agent package", "create an agent from a design", or when you have both case/ and design/ folders and need to create the package/ folder with AGENTS.md, skills, and scripts.
Define canonical dotnet format and analyzer verification commands, and provide scripts that generate a format/analyzer report. Use when checking formatting or Roslyn analyzers without reformatting everything.
Ask clarifying questions and get approval before implementation.
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Use when facing 3+ independent failures that can be investigated without shared state or dependencies. Dispatches multiple Claude agents to investigate and fix independent problems concurrently.
Show LeetCode problem details and generate Rust template (project)
Data-only HS risk scoring (format/missing/haz/oog flags) with markdown report
Generate comprehensive test cases for code
Create and manage a git worktree for parallel feature development, then open the new worktree in the editor (code/Cursor) for a second Codex session. Use when the user asks to work on another feature simultaneously, spin up a parallel workspace, or open a new worktree even if they do not mention worktree explicitly.
Skill for integrating Better Auth - the comprehensive TypeScript authentication framework.
Next.js(App Router) の Server Actions を前提とした、エラーハンドリングと表示メッセージの統一ルール。
Safe code refactoring with step-by-step approach
Capture screenshots of all manual pages at high resolution for translation verification. Use when verifying that translations match page images, checking layout correctness, or inspecting for content mismatches.
Y---
Use this agent when reviewing code changes to ensure features are agent-native - any action a user can take, an agent can also take, and anything a user can see, an agent can see. Triggers on requests like "agent-native review", "AI accessibility check".
Creates, modifies, and manages Claude Code subagents by writing agent files with YAML frontmatter, system prompts, and tool configurations. Use when you need to "create an agent", "modify an agent", "set up a specialist", "I need an agent for [task]", "agent to handle [domain]", or "configure agent tools". Covers agent file format, YAML frontmatter, system prompts, tool restrictions, MCP integration, model selection, and testing.
Expert in designing Microsoft 365 Copilot agent architectures
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
NixOS and Nix flake development for multi-repo architectures, airgapped deployments, and K3s infrastructure. Use when working with flake.nix files, NixOS modules, derivations, devShells, overlays, OCI image packaging, or composing multiple flake repositories. Covers Nix language syntax, flake inputs/outputs, nixosModules exports, stdenv.mkDerivation, and home-manager integration.
Agent with selective Gemini safety settings for specific categories