性能分析

Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter

LangGraph development for stateful multi-agent applications, cyclic workflows, conditional routing, human-in-the-loop patterns, and persistent state management. Use for complex AI orchestration, agent coordination, and production-grade agentic systems.

Create and maintain Claude Code agents/subagents (.claude/agents/*.md) with YAML frontmatter (name/description/tools/model/permissionMode/skills/hooks), least-privilege tool selection, delegation patterns (Task), context budgeting, and safety best practices.

Aggressive evidence-based audit to verify project claims match implementation reality

Constitutional compliance validator. Enforces all 5 Constitutional Articles to ensure AI trading decisions comply with human-defined rules. Works as second line of defense alongside Risk Agent.

Manage semantic versioning, changelog generation, and release notes. Auto-generates entries from completed issues or git diff.

Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.

Standards for creating redteam plugins and graders. Use when creating new plugins, writing graders, or modifying attack templates.

Create a new underwriting agent (assets, credit, collateral) following established patterns. Use when implementing new agents, extending the system with new document analysis capabilities, or understanding how agents work.

Fix speech-to-text errors and improve text clarity in dictated content related to GitHub Agentic Workflows

Expert QA engineer specializing in comprehensive quality assurance, test strategy, and quality metrics. Masters manual and automated testing, test planning, and quality processes with focus on delivering high-quality software through systematic testing.

Guide for using pagent - a PRD-to-code orchestration tool. Use when users ask how to use pagent, run agents, create PRDs, or transform requirements into code.

This skill should be used when the user asks about "job status", "check if request completed", "cancel request", "why is my request taking so long", "poll for result", "batch requests", "retry failed request", "request timeout", "async operations", "job lifecycle", "manual polling", or needs advanced control over SDK async operations, manual job polling, batch processing, retry logic, or job cancellation.

Create or refactor a .NET 8 WPF shell for a desktop widget host using CommunityToolkit.Mvvm and a custom viewmodel-first navigation service. Use when working on App.xaml, MainWindow/ShellWindow, shared ResourceDictionaries, runtime Light/Dark theming, or shell layout for widget-style apps. Avoid Prism, Frame navigation, and heavy region managers.

Conduct comprehensive research on any topic by coordinating 2-4 specialized researcher agents in parallel, then synthesizing findings into a detailed report via mandatory report-writer agent delegation

Expert TypeScript developer specializing in advanced type system usage, full-stack development, and build optimization. Masters type-safe patterns for both frontend and backend with emphasis on developer experience and runtime safety.

Guide for authoring specialized AI agents. Use when creating, updating, or improving agents, choosing models, defining focus areas, configuring tools, or learning agent best practices.

Create or update CLAUDE.md files following best practices for optimal AI agent onboarding

Claude Code: skills, agents, hooks, commands, MCP servers, IDE integrations.