AI Engineering

Safety Guardrails helps design layered safety boundaries for AI systems, including refusal policies, prompt injection defenses, and domain-specific rules. Use it when an AI handles sensitive topics or needs clear ethical limits.

Search Integration defines when an AI should search, what sources to search, and how to handle results. Use it for real-time knowledge retrieval in chatbots, research assistants, and enterprise Q&A; it is not for offline or purely internal knowledge tasks.

Skill Init collects your current skills, experience, learning time, and goals to build an initial career profile. It then sets a starting tier and writes .skill-state.json so skill-scan and skill-plan can continue.

Skill Plan generates a personalized learning strategy for a chosen role, from gap analysis to phased study paths, portfolio projects, job-search timing, and stop-loss rules. Use it when you want an AI-guided plan for switching roles with verifiable milestones.

Skill Scan finds real hiring-market roles that fit a user’s current skills, using live job signals, AI-impact checks, and learnability scoring. It is used when someone wants honest high-pay roles they can realistically grow into.

State Management helps reduce token use with caching, progressive disclosure, and configuration patterns for plugin operations. Use it when working with large responses, cache invalidation, or consistent state across tests and workflows.

Technical Stack Selection determines which technologies to reuse, buy, integrate, or build for a product based on features, screens, risks, and existing assets. Use it during PRD v0.5 to document tech decisions and feed architecture design.

Tool Specification defines how to design AI tool interfaces, discovery, permissions, and parallel execution. Use it when an agent needs to call external APIs, manage many tools, or delegate work to sub-agents.

Ultracode runs a supervised coding workflow that plans, splits work, delegates when allowed, integrates results, and verifies the outcome. Use it for explicit ultracode requests and other multi-step tasks that benefit from parallel agent work.

User Journey Mapping turns personas, features, and KPIs into step-by-step user paths from trigger to value moment. Use it when defining user journeys, user flows, or the pain-to-value sequence for a PRD.

User Value Articulation transforms validated pain points into quantified value statements for PRD v0.1. It is used after problem framing to turn CFD pain entries into value hypotheses with evidence tiers and MVP scope signals.

Voice Optimization helps adapt system prompts for spoken interactions like voice assistants, voice search, and phone agents. It keeps answers concise, conversational, and safe for audio use, with rules for supported languages and no preambles.