LLM & Agents

Comprehensive guide for building AI agents using Google's Agent Development Kit (ADK). Use when building agentic systems, orchestrating multi-agent workflows, creating AI assistants with custom tools, implementing LLM-powered applications, or working with Google Gemini models. Covers agent types (LlmAgent, SequentialAgent, ParallelAgent, LoopAgent), tool integration (FunctionTool, built-in tools, MCP), session management, deployment strategies, and multi-agent coordination patterns.

Create feature specifications using Specification-Driven Development (SDD) methodology.Use when starting a new feature, documenting requirements, or executing the /specify command.This skill guides the creation of comprehensive feature specifications following the SDDframework's spec-template.md structure. It ensures specifications include all requiredsections, validates completeness, detects domains/agents needed, and prepares for theplanning phase.Triggered by: /specify command, user request for "specification", "requirements","feature spec", or "document requirements".

CRITICAL AUTOMATION: Automatically performs comprehensive study guide verification using the study-guide-analyzer agent.ACTIVATES when user requests accuracy verification, post-creation validation,or analysis of existing study guides.Launches the study-guide-analyzer agent to implement systematic 6-step verification protocol,ensuring study guides contain only source-accurate information with complete coverage and proper formatting.

Log work sessions with timestamps, decisions, agent handoffs, issues, and outcomes. Use when a session log needs to be created or updated.

Claude 4.5 Opus 기반 자가성장 지능형 루프. Effort Parameter, Memory Tool, 병렬 작업 관리에 사용.

Implement reusable embedding functions using Gemini embedding models via LangChain with proper error handling and batching for sitemap-crawled content.

Dispatch code-reviewer subagent to review implementation against plan or requirements before proceeding

Assess and enhance software projects for enterprise-grade security, quality, and automation. Use when evaluating projects for production readiness, implementing supply chain security (SLSA, signing, SBOMs), hardening CI/CD pipelines, or establishing quality gates. Aligned with OpenSSF Scorecard, Best Practices Badge (all levels), SLSA, and S2C2F. By Netresearch.

Analyze test coverage and add new test cases to improve coverage without changing implementation

LLMプロンプトの最適化・テスト支援スキル。プロンプトのパフォーマンス評価、改善提案、A/Bテスト、ベストプラクティス適用、再現性検証を行います。

Optimize AI assistant configurations for maximum effectiveness. USE THIS SKILL when user says "improve CLAUDE.md", "better copilot instructions", "tune AI", "optimize prompts", "MCP configuration", or wants to enhance AI assistant behavior.

Creates concise, executable implementation plans for solo developer working with AI agents. Validates assumptions, avoids timelines, focuses on actionable steps with clear human/AI delegation.

Meta-skill to generate new Claude Agent Skills from natural-language descriptions. Use when creating skills, building custom workflows, generating new capabilities, or extending Claude's functionality. Outputs complete SKILL.md files with proper frontmatter (name, description, optional allowed-tools) and clear instructions. Handles multi-file skills with progressive disclosure patterns. Triggers on requests to "create skill", "build skill", "generate skill", or "new capability".

Use when reviewing test suites, after test runs pass, or when user asks about test quality - performs exhaustive line-by-line audit tracing code paths through entire program, verifying tests actually validate what they claim. Outputs structured report compatible with fix-tests skill.

Multi-agent orchestration system sử dụng Claude subagents thực tế từ thư mục agents/ cho security reviews, code quality analysis, deployment validation, infrastructure checks. Auto-activates với orchestrator-worker pattern và extended thinking mode.

Designs deployment strategies and configurations for applications

Create a new Claude Code agent with proper YAML frontmatter structure. Use when the user wants to add a specialized agent to a plugin. Handles agent file creation with name, description, tools, model selection, and color configuration.

World-building assistant for maintaining canonical lore of imaginary countries. Use when Saul wants to create new countries, add historical events, create biographies of figures, expand existing canon, correct errors in canon, or ask questions about the world-building repository. Manages git repository of markdown files with validation for internal consistency.

Guide for creating production-grade ChatKit chatbots that integrate OpenAI Agents SDK with MCP tools and custom backends. Use when building AI-powered chatbots with specialized capabilities, real-time task execution, and user isolation for any application.

This skill should be used when auditing or comparing Claude Code and Cursor IDE configurations to identify feature gaps, equivalencies, and migration opportunities. Useful when managing AI development tooling across both platforms or deciding how to structure AI workflows.