আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
Use when multiple tools are available for a task and intelligent routing is needed. Activates when routing-detector hook suggests it, or when user asks "which tool should I use" or "what's the best plugin for this". Provides context-aware tool ranking based on file context, user preferences, and tool specialization.
Use this skill to learn from mistakes. Activate when Claude makes tool call errors, incorrect assumptions, oversights, or when the user corrects Claude. Maintains auto-learning.md as a knowledge base of lessons learned.
OpenAI SDK development with GPT-5 family, Chat Completions, Responses API, embeddings, and tool calling. Use for AI-powered applications, chatbots, agents, and semantic search.
Интеграция Google Custom Search API в AI-чат. Используй этот skill когда нужно добавить веб-поиск в чат-бота, настроить поиск актуальной информации в интернете, или интегрировать Google Search в приложение.
Create Architecture Decision Records for important technical decisions. Guides you through trade-off analysis, fact-checks claims, and generates a structured ADR document. Triggers on: create adr, architecture decision, document decision, record decision, technical decision, adr for.
Access and interact with Large Language Models from the command line using Simon Willison's llm CLI tool. Supports OpenAI, Anthropic, Gemini, Llama, and dozens of other models via plugins. Features include chat sessions, embeddings, structured data extraction with schemas, prompt templates, conversation logging, and tool use. This skill is triggered when the user says things like "run a prompt with llm", "use the llm command", "call an LLM from the command line", "set up llm API keys", "install llm plugins", "create embeddings", or "extract structured data from text".
Use when user mentions 'climpt' or 'climpt-agent', or gives project-specific instructions where general knowledge is insufficient. Climpt provides pre-configured prompts tailored to the project's workflow.
Use when "training LLM", "finetuning", "RLHF", "distributed training", "DeepSpeed", "Accelerate", "PyTorch Lightning", "Ray Train", "TRL", "Unsloth", "LoRA training", "flash attention", "gradient checkpointing"
Expert guidance for creating, configuring, and using Claude Code hooks. Use when working with hooks, setting up event listeners, validating commands, automating workflows, adding notifications, or understanding hook types (PreToolUse, PostToolUse, Stop, SessionStart, UserPromptSubmit, etc).
LLM keyring management, multi-provider support, and AI agent orchestration
Capture screenshots of aiandi.dev for visual verification. Puppeteer-based, outputs to /tmp. Foundation for the design-loop skill.
Generate a CLAUDE.md file for an Obsidian vault. Analyzes existing vault structure and creates an instruction file that helps AI understand and navigate the vault. Use when setting up a new vault or when CLAUDE.md is missing/outdated.
Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.
Enable AI to make intelligent decisions about where to place new things and how to find existing things
Expert guide for Flutter and Dart development. Use this skill when users want to build, refactor, or understand Flutter applications following modern best practices, including state management, theming, and testing.
Comprehensive guide to implementing audit trails and logging for AI agents including tracing, observability, compliance, and debugging
AI Design Lead: Access to style, palette, and typography databases.
Systematic AI extraction prompt design expert with Socratic methodology
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
