Найдите подходящую возможность для вашего агента.
This skill should be used when the user wants collaborative, iterative development instead of autonomous implementation. It transforms Claude from "autonomous implementer" to "pair programmer" by enforcing ask-before-assuming, show-before-writing, iterate-in-small-chunks, and get-approval-at-each-step patterns. Trigger when user explicitly requests paired programming or when working on complex/novel features requiring collaboration.
Interactive AI agent development workflow orchestrator. Guides users through complete agent creation from brainstorming to production-ready implementation. Use when user wants to build a new AI agent, design an agentic system, scaffold an agent project, or needs help with agent architecture decisions. Supports three-phase workflow - design documentation, implementation scaffolding, and operations (deploy/observe/evaluate).
Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
Opinionated constraints for building better interfaces with agents. Apply when writing UI code, implementing designs, or reviewing frontend components. Use within DevDocs workflow during development phase for UI-related tasks. Triggers on keywords like "UI", "界面", "前端", "组件", "animation", "动画", "layout", "布局".
Create structured Google NotebookLM lesson plans with curated sources and tailored audio overview prompts. Use when the user wants to create a NotebookLM notebook, generate learning content with audio overviews, or build a curriculum with multiple focused segments. Handles both single lesson creation and batch processing of multiple topics.
Create distinctive, production-grade layouts for aiandi.dev. Bold aesthetic vision + semantic token system. Use when designing pages, components, or visual treatments.
AI integration with Vercel AI SDK - Build AI-powered applications with streaming, function calling, and tool use. Trigger: When implementing AI features, when using useChat or useCompletion, when building chatbots, when integrating LLMs, when implementing function calling.
Intelligent learning system optimizer that analyzes session patterns, identifies improvement opportunities, and continuously enhances Alfred's performance through adaptive learning and knowledge optimization. Use when optimizing Alfred's behavior, analyzing session patterns, improving system performance, or when implementing adaptive learning capabilities.
Use when optimizing agent context, reducing token costs, implementing KV-cache optimization, or asking about "context optimization", "token reduction", "context limits", "observation masking", "context budgeting", "context partitioning"
Configuring Claude Code Hooks System. Design, implement, and manage PreToolUse/PostToolUse/SessionStart/Notification/Stop hooks. Use when enforcing safety checks, auto-formatting, running linters, or triggering automated workflows based on development events.
Invoke Gemini CLI as a partner AI developer for tasks benefiting from its 1M token context window or a second opinion. Use when analyzing large codebases, generating documentation, getting alternative perspectives, researching topics with web search, or creating UI wireframes/components. Gemini has read/write/edit/shell/web search capabilities like Claude.
3x3 Parallel Debate system for high-confidence research. Spawns 9 agent instances (3 Proposer/Skeptic/Judge cohorts) to argue, critique, and adjudicate claims. Use for complex queries, controversial topics, or when hallucination-free research is critical.
获取最新的AI行业新闻，进行智能总结和筛选，最多展示10条最重要的新闻资讯。当用户需要了解AI行业最新动态时使用此skill。
This skill should be used when the user asks about "AIP rules", "API Improvement Proposals", "Google API guidelines", "AIP-158", "AIP-193", or any specific AIP number. Also use when user asks "how should I implement pagination", "what's the right error format", "how do I design a REST API following Google's standards", or needs guidance on errors, pagination, filtering, field masks, long-running operations, or batch operations in REST/OpenAPI APIs.
Commission and process external AI analysis to reduce blind spots. Manual invocation only.
Validates AI prompts and LLM findings against source data to prevent hallucinations. Use when: (1) Adding new analysis prompts to server.js, (2) Reviewing prompts for hallucination risks, (3) Implementing validation rules in ATTRIBUTE_VALIDATION_RULES, (4) Auditing that findings match source JSON data
This skill should be used when building hybrid Knowledge Graphs that integrate structured data (CSV, databases) with automatically extracted entities from unstructured documents (PDFs, text). The pattern establishes a reliable join key between domain graphs and lexical graphs, enabling GraphRAG, document ingestion with metadata enrichment, and Knowledge Graph construction from heterogeneous sources using neo4j-graphrag SimpleKGPipeline.
Expert knowledge for building web APIs and real-time applications with Composable Rust. Use when building HTTP REST APIs with Axum, implementing WebSocket for real-time updates, working with authentication (magic link, OAuth, passkeys), setting up email providers (SMTP, Console), designing API routes or request handlers, or questions about web integration and real-time communication.
PAI (Personal AI Infrastructure) - Your AI system core. Platform-agnostic and bridge-enabled. AUTO-LOADS at session start. USE WHEN any session begins OR user asks about PAI identity, response format, stack preferences, security protocols, or delegation patterns.
