发现 testing security llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Learn and refine user ideas through brainstorming. Use when user uploads idea files to the Workplace. Analyzes uploaded content, asks clarifying questions, and produces structured idea summary. Triggers on requ...
Manage idea tracking during ideation-stage tasks. This is a category-level skill called during Step 4 (Category Closing) for ideation-stage tasks. Accepts Task Data Model. Outputs category_level_change_summary.
Professional AI and System Orchestrator. Specialized in GPT-5, autonomous agents, Auth.js v5, Stripe v13, Monorepos (Bun/pnpm), and large codebase intelligence. Optimized for January 2026 standards.
Expert in integrating third-party APIs with proper authentication, error handling, rate limiting, and retry logic. Specializes in Auth.js v5, GPT-5 model orchestration, Stripe SDK v13+, and architectural contex...
Master of Filament v4 (2026), specialized in Custom Data Sources, Nested Resources, and AI-Augmented Admin Panels.
Expert in json-render (Vercel Labs), specialized in AI-generated UI with guardrails, JSONL patch streaming, and Next.js 16 integration. Use when implementing predictable, catalog-based UI generation, real-time...
Master of the Modern Utility Toolbelt, specialized in AI-enhanced CLI, structured data transformation, and advanced Unix forensics.
Run Claude Code programmatically without interactive UI. Triggers on: headless, CLI automation, --print, output-format, stream-json, CI/CD, scripting.
Use this skill when documenting significant architectural decisions. Provides ADR templates following the Nygard format with sections for context, decision, consequences, and alternatives. Helps teams maintain...
Explore problems from multiple perspectives through structured role-playing techniques. Use when user wants to "see different viewpoints", "consider perspectives", "what would X think", "six hats", "stakeholder...
Build AI-first applications with RAG pipelines, embeddings, vector databases, agentic workflows, and LLM integration. Master prompt engineering, function calling, streaming responses, and cost optimization for...
Engages structured analysis to explore multiple perspectives and context dependencies before responding. Use when users ask confirmation-seeking questions, make leading statements, request binary choices, or wh...
Guide learning and deep understanding through proven methodologies (Socratic, Feynman, Problem-Based). Use when user says "help me understand", "teach me", "explain this", "learn about", "socratic", "feynman",...
Troubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found.
Model Context Protocol (MCP) server patterns for building integrations with Claude Code. Triggers on: mcp server, model context protocol, tool handler, mcp resource, mcp tool.
Senior Prompt Engineer & Agentic Orchestrator. Expert in Reasoning Models (o3), Tree-of-Thoughts, and Structured Thinking Protocols for 2026.
Senior SDK Master for @google/genai v1.35.0+, expert in Controlled Outputs, Multimodal Context, and Structured Intelligence.
Master of Voice-First Interfaces, specialized in sub-300ms Latency, Spatial Hearing AI, and Multimodal Voice-Haptic feedback.
Master of LLM Economic Orchestration, specialized in Google GenAI (Gemini 3), Context Caching, and High-Fidelity Token Engineering.
Research-driven critique and enhancement of Amelia architecture or ideas docs. Use with GPT-5.2 when given a design/architecture doc to analyze concepts, find sources, and propose improvements plus OSS candidat...
Debug and improve the Bifrost vibe coding experience. Use this skill when working on Bifrost platform development in Claude Code where you have access to Bifrost source code. Helps identify system bugs vs docum...
Best practices for using the Council MCP server in Tzurot v3 development - When to consult external AI, how to structure prompts, model selection, and multi-turn conversations. Use when planning major changes o...
Meta-skill for writing and maintaining Claude Code skills. Use when creating new skills, updating existing skills, or reviewing skill quality. Enforces progressive disclosure and size limits.
Transform raw ideas into structured business requirements by clarifying the problem, defining the solution, and identifying target users. Use when starting stage 00 (init-ideas) or when user asks to define busi...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。