AI Engineering

Full Output Enforcement prevents truncated or placeholder-filled responses by requiring every requested deliverable to be generated completely. Use it for tasks that need exhaustive, unabridged output, like full files or multiple components.

Agent Builder provides a framework for designing and building AI agents for any domain, from customer service to research and operations. Use it when asked to create an agent, build an assistant, or understand agentic patterns.

MCP Builder guides development of Model Context Protocol servers that give Claude new tools, resources, and external service integrations. Use it to create MCP servers in Python or TypeScript and register them with Claude.

LangSmith Fetch fetches execution traces from LangSmith Studio to debug LangChain and LangGraph agents. Use it to investigate errors, analyze tool calls, check memory operations, and review agent performance.

MCP Builder guides creation of high-quality MCP servers that let LLMs interact with external services through well-designed tools. Use when building MCP servers in Python (FastMCP) or Node/TypeScript (MCP SDK) to integrate external APIs and services.

Skill Creator guides users through creating or updating skills that extend Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use it when building a new skill or improving an existing one for Claude Code.

Skill Template provides a starting point for creating new Claude Code skills, with placeholders for the skill description and instructions. Use it when scaffolding a new skill to ensure consistent structure.

Agent Reach routes internet research and content retrieval across 15 platforms, including Exa search, social media, LinkedIn, GitHub, YouTube, and stock data. Use it when you need to research, search, or look up anything online from within Claude Code.

H-1B Sponsor Check attaches a factual sponsorship signal to US job evaluations. Use it when a role is US-based, remote-US, or the user asks about sponsorship.

Upskill aggregates skill gaps from evaluation reports to show what a candidate should learn next. It can also compare against prior runs and, for single job descriptions, return the remaining gaps after known skills are excluded.

Give Me Tips explains any senpi tip in depth—startup tips, working tips, and Tip: lines shown in the TUI—by querying the live tip list, checking what the user can see, and verifying the real feature code before answering.

Hyperplan orchestrates five adversarial category agents in team mode to cross-critique plans, distills only defensible insights, and hands them to the plan agent for executable formalization. Use when planning needs maximum rigor.