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