UitbreidenOS/UitKit - الصفحة ١٩

session-memory

Claude Code session checkpoints and state restoration. Serialize working directory, uncommitted git status, recently modified files, and active task description into checkpoint.json to resume context later

لغة النص الأصلي: الإنجليزية

advanced-tool-use

Master advanced tool use patterns including chaining, parallel calls, and error recovery for complex Claude Code workflows

لغة النص الأصلي: الإنجليزية

agent-construction

Multi-agent architecture, orchestrator patterns, tool design, agent loops, memory, error handling, handoffs

لغة النص الأصلي: الإنجليزية

agent-handoff

Implement structured handoffs between agents with JSON-based state transfer, conflict detection, and acknowledgment protocols

لغة النص الأصلي: الإنجليزية

agent-memory

Agent memory and context management: design persistent memory systems, manage context windows, implement summarization strategies, and build stateful agents that learn across sessions

لغة النص الأصلي: الإنجليزية

agent-sdk

Build AI agents using the Claude Agent SDK with tool use, memory, and multi-step orchestration

لغة النص الأصلي: الإنجليزية

agent-supervisor

Build orchestrator agents that manage multi-agent workflows, enforce SLAs, handle escalations, and maintain overall task completion

لغة النص الأصلي: الإنجليزية

agent-tracing

Build observability into multi-agent systems with distributed traces, trace correlation, breakpoints, and execution replay

لغة النص الأصلي: الإنجليزية

artifact-first-workflow

Claude Code Artifact-First Workflow: single source of truth specifications. Draft, version, and edit specifications (SPEC.md) first, treating the actual codebase implementation as a compilable/generated output

لغة النص الأصلي: الإنجليزية

caveman-token-reduction

Claude Code Caveman mode: token-efficient communication, compressed responses, minimal output for context-heavy sessions, terse acknowledgments, and context budget optimization

لغة النص الأصلي: الإنجليزية

claude-api

Anthropic Claude API: prompt caching, streaming, tool use, batch processing, model selection, cost optimization

لغة النص الأصلي: الإنجليزية

claude-batch

Run large-scale batch processing with Claude API for bulk text analysis, classification, and generation

لغة النص الأصلي: الإنجليزية

crewai

Build multi-agent crews with CrewAI framework for collaborative AI task execution

لغة النص الأصلي: الإنجليزية

dag-scheduler

Build, validate, and execute directed acyclic graph (DAG) topologies for multi-agent workflows with automatic parallelization and cycle detection

لغة النص الأصلي: الإنجليزية

dispatch-background-jobs

Claude Code Dispatch: run long-running tasks as background jobs with progress polling, parallel sub-agent fan-out, result aggregation, and automatic retry on failure

لغة النص الأصلي: الإنجليزية

enterprise-search

Enterprise search and knowledge retrieval: design multi-source search systems, implement hybrid search (semantic + keyword + structured), build knowledge graphs, handle access control, and create unified search across docs, wikis, code, and databases

لغة النص الأصلي: الإنجليزية

graph-augmented-context

Claude Code Graph-Augmented Context (GAC): local SQLite codebase knowledge graph builder. Maps files, classes, functions, and import/dependency edges for advanced codebase RAG and contextual navigation

لغة النص الأصلي: الإنجليزية

langgraph

LangGraph stateful agent framework: StateGraph, nodes, edges, conditional branching, persistence/checkpointing, human-in-the-loop, multi-agent subgraphs

لغة النص الأصلي: الإنجليزية

llm-benchmark

LLM benchmarking: design benchmark suites, establish baselines, run A/B model comparisons, detect regressions, track production quality metrics, and create leaderboards for model selection

لغة النص الأصلي: الإنجليزية

llm-eval

LLM evaluation: build evaluation datasets, choose metrics (RAGAS, G-Eval, LLM-as-judge), run automated evals, monitor production quality, and detect regressions

لغة النص الأصلي: الإنجليزية

managed-agents

Deploy and manage Claude agents with lifecycle management, monitoring, and scaling

لغة النص الأصلي: الإنجليزية

mastra

Mastra AI: TypeScript agent framework — agents, workflows, tools, memory, RAG, evals — for building production-grade AI applications

لغة النص الأصلي: الإنجليزية

mcp-dynamic-discovery

Claude Code MCP Dynamic Discovery: zero-config external tool integration. Automatically scans system configuration directories for active Model Context Protocol (MCP) servers and configures them locally

لغة النص الأصلي: الإنجليزية

mcp-server-builder

Build custom MCP servers: expose tools, resources, and prompts via stdio or HTTP/SSE transport — connect proprietary data to Claude Code

لغة النص الأصلي: الإنجليزية

modal

Build serverless AI pipelines with Modal for cloud-based compute and inference

لغة النص الأصلي: الإنجليزية

multi-agent-memory

Build shared, versioned memory systems for multi-agent teams using blackboard pattern, conflict resolution, and eventual consistency

لغة النص الأصلي: الإنجليزية

prompt-caching

Optimize Claude API costs and latency with prompt caching strategies

لغة النص الأصلي: الإنجليزية

prompt-engineering

Prompt engineering for production: few-shot prompting, chain-of-thought, system prompt design, output formatting, temperature settings, and evaluation — for Claude and other LLMs

لغة النص الأصلي: الإنجليزية

ptc

Implement prompt-to-code workflows for rapid prototyping and code generation

لغة النص الأصلي: الإنجليزية

rag-architect

RAG system design: chunking strategies, embedding model selection, vector store choice, retrieval patterns, reranking, evaluation — production-grade retrieval-augmented generation

لغة النص الأصلي: الإنجليزية

remote-control-headless

Claude Code Remote Control: manage headless Claude Code sessions from anywhere, CI/CD integration, remote orchestration from mobile/laptop, session attach/detach, and remote execution patterns

لغة النص الأصلي: الإنجليزية

session-handoff

Claude Code Session Handoff: structured context export/import between sessions, state serialization, continuation prompts, cross-session knowledge transfer, and resumable workflows

لغة النص الأصلي: الإنجليزية

skill-composition

Skill composition and chaining: design multi-skill workflows, chain skill outputs as inputs, build reusable skill pipelines, and orchestrate complex tasks from atomic skill building blocks

لغة النص الأصلي: الإنجليزية

swarm-sandbox

Safe isolated testing environment for multi-agent swarm topologies before production deployment

لغة النص الأصلي: الإنجليزية

vercel-ai-sdk

Vercel AI SDK: streaming AI responses to Next.js, useChat/useCompletion hooks, tool calls, generative UI, multi-provider routing (Claude, OpenAI, Gemini)

لغة النص الأصلي: الإنجليزية

browser

Browser automation with Playwright: web scraping, UI testing, form filling, screenshot capture, PDF generation, session recording

لغة النص الأصلي: الإنجليزية

claude-design-branding

Create consistent brand systems with Claude Design including logos, colors, and typography

لغة النص الأصلي: الإنجليزية

claude-design

Build production-ready UIs and prototypes with Claude Design

لغة النص الأصلي: الإنجليزية

claude-design-tokens

Manage design tokens for consistent theming across Claude Design projects

لغة النص الأصلي: الإنجليزية

claude-design-workflow

Build end-to-end design workflows with Claude Design for rapid UI/UX iteration

لغة النص الأصلي: الإنجليزية