chain-builder
Build and execute multi-step prompt chains for complex tasks
Build and execute multi-step prompt chains for complex tasks
Create production-ready prompts using systematic methodology. Use when: (1) Building new prompts for Claude, (2) Improving existing prompts, (3) Creating prompt templates, (4) Designing system prompts for agents.
Analyzes your recent Claude Code chat history to identify coding patterns,
Deep Agents library for building complex, multi-step AI agents with planning, context management, and subagent delegation.
Orchestrate comprehensive assessment of newly created skills to determine if they should auto-trigger using context-gathering, code-analyzer, and optional research-expert agents with prioritized evaluation criteria
Create, validate, and package Claude skills - modular packages that extend Claude's capabilities through specialized knowledge, workflows, and tool integrations.
Analyze text sentiment at scale with nuanced understanding
Write effective LLM prompts, commands, and agent instructions. Goal-oriented over step-prescriptive. Role + Objective + Latitude pattern. Use when writing prompts, designing agents, building Claude Code commands, or reviewing LLM instructions. Keywords: prompt engineering, agent design, command writing.
Use when creating new Claude Code skills - guides SKILL.md structure, description writing, and file organization
Three-layer verification architecture (CoVe, HSP, RAG) for self-verification, fact-checking, and hallucination prevention
Cognitive superposition synthesizing Riehl (∞-categories), Sutskever
Enterprise session state management, token budget optimization, runtime tracking, session handoff protocols, context continuity for Claude Sonnet 4.5 and Haiku 4.5 with context awareness features
Use when creating Claude Code skills following official format with proper YAML frontmatter, progressive loading, and Guild system integration patterns.
Design and implement Model Context Protocol servers for standardized AI-to-data integration with resources, tools, prompts, and security best practices
Design and implement multi-agent workflows with LangGraph 0.2+ - state management, supervisor-worker patterns, conditional routing, and fault-tolerant checkpointing
Handle comprehensive project language and user setup workflows including language selection, agent prompt configuration, user profiles, team settings, and domain selection
Parallel strategy generation using G-5 Planning. Deploy 10 planning probes for multi-perspective implementation planning. Use for complex task planning after reconnaissance.
LLM architecture, tokenization, transformers, and inference optimization. Use for understanding and working with language models.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
LLM evaluation frameworks, benchmarks, and quality metrics for production systems.
Self-improvement protocol for Neo4j agents. Instructs agents to report skill updates needed.
This skill should be used when the user asks to "continue session", "resume work", "what was I doing last time", "pick up where I left off", "check recent activity", "what happened since last session", or needs context about previous sessions.