Menu
Skills in this repository
SkillsMP has collected 1,360 skills from UitbreidenOS/UitKit. Open a skill to review its source and details.
UitbreidenOS/UitKitShowing 40 of 1,360 collected skills.
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
Master advanced tool use patterns including chaining, parallel calls, and error recovery for complex Claude Code workflows
Multi-agent architecture, orchestrator patterns, tool design, agent loops, memory, error handling, handoffs
Implement structured handoffs between agents with JSON-based state transfer, conflict detection, and acknowledgment protocols
Agent memory and context management: design persistent memory systems, manage context windows, implement summarization strategies, and build stateful agents that learn across sessions
Build AI agents using the Claude Agent SDK with tool use, memory, and multi-step orchestration
Build orchestrator agents that manage multi-agent workflows, enforce SLAs, handle escalations, and maintain overall task completion
Build observability into multi-agent systems with distributed traces, trace correlation, breakpoints, and execution replay
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
Claude Code Caveman mode: token-efficient communication, compressed responses, minimal output for context-heavy sessions, terse acknowledgments, and context budget optimization
Anthropic Claude API: prompt caching, streaming, tool use, batch processing, model selection, cost optimization
Run large-scale batch processing with Claude API for bulk text analysis, classification, and generation
Build multi-agent crews with CrewAI framework for collaborative AI task execution
Build, validate, and execute directed acyclic graph (DAG) topologies for multi-agent workflows with automatic parallelization and cycle detection
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
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
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
LangGraph stateful agent framework: StateGraph, nodes, edges, conditional branching, persistence/checkpointing, human-in-the-loop, multi-agent subgraphs
LLM benchmarking: design benchmark suites, establish baselines, run A/B model comparisons, detect regressions, track production quality metrics, and create leaderboards for model selection
LLM evaluation: build evaluation datasets, choose metrics (RAGAS, G-Eval, LLM-as-judge), run automated evals, monitor production quality, and detect regressions
Deploy and manage Claude agents with lifecycle management, monitoring, and scaling
Mastra AI: TypeScript agent framework — agents, workflows, tools, memory, RAG, evals — for building production-grade AI applications
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
Build custom MCP servers: expose tools, resources, and prompts via stdio or HTTP/SSE transport — connect proprietary data to Claude Code
Build serverless AI pipelines with Modal for cloud-based compute and inference
Build shared, versioned memory systems for multi-agent teams using blackboard pattern, conflict resolution, and eventual consistency
Optimize Claude API costs and latency with prompt caching strategies
Prompt engineering for production: few-shot prompting, chain-of-thought, system prompt design, output formatting, temperature settings, and evaluation — for Claude and other LLMs
Implement prompt-to-code workflows for rapid prototyping and code generation
RAG system design: chunking strategies, embedding model selection, vector store choice, retrieval patterns, reranking, evaluation — production-grade retrieval-augmented generation
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
Claude Code Session Handoff: structured context export/import between sessions, state serialization, continuation prompts, cross-session knowledge transfer, and resumable workflows
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
Safe isolated testing environment for multi-agent swarm topologies before production deployment
Vercel AI SDK: streaming AI responses to Next.js, useChat/useCompletion hooks, tool calls, generative UI, multi-provider routing (Claude, OpenAI, Gemini)
Browser automation with Playwright: web scraping, UI testing, form filling, screenshot capture, PDF generation, session recording
Create consistent brand systems with Claude Design including logos, colors, and typography
Build production-ready UIs and prototypes with Claude Design
Manage design tokens for consistent theming across Claude Design projects
Build end-to-end design workflows with Claude Design for rapid UI/UX iteration