pai

Visual description specialist. Generates detailed prompts for image generation tools (DALL-E, Midjourney, Stable Diffusion). Creates visual concepts with style, composition, and mood specifications. Use for creating image prompts.

UI/UX design specialist. Creates wireframes, component specifications, user flows, and interaction patterns. Designs interfaces with accessibility, usability, and visual hierarchy in mind. Use for interface design tasks.

Code implementation specialist. Writes production-quality code, follows existing patterns, implements features, fixes bugs, and creates tests. Use for all coding tasks.

Use this agent to orchestrate comprehensive multi-perspective research using Google's Gemini model. Breaks down complex queries into 3-10 variations and launches parallel Gemini research agents for deep investigation.

Use this agent when you or any subagents need research done - crawling the web, finding answers, gathering information, investigating topics, or solving problems through research.

Quality assurance specialist. Writes and runs tests, identifies edge cases, validates implementations, and reports bugs with reproduction steps. Use for testing and validation tasks.

Information gathering specialist. Performs web research, codebase analysis, and documentation synthesis. Returns structured findings with sources. Use for research and exploration tasks.

PAI (Personal AI Infrastructure) - Your AI system core. AUTO-LOADS at session start. USE WHEN any session begins OR user asks about PAI identity, response format, stack preferences, security protocols, or delegation patterns.

Create, update, validate, and canonicalize Claude Code skills. USE WHEN user wants to create a new skill OR modify an existing skill OR validate skill structure OR fix skill format OR migrate legacy skills.

Native Fabric pattern execution for Claude Code. USE WHEN processing content with Fabric patterns (extract_wisdom, summarize, analyze_claims, threat modeling, etc.). Patterns run natively in Claude's context - no CLI spawning needed. Only use fabric CLI for YouTube transcripts (-y) or pattern updates (-U).

Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.

Comprehensive research, analysis, and content extraction system. Multi-source parallel research using available researcher agents. Deep content analysis with extended thinking. Intelligent retrieval for difficult sites. Fabric pattern selection for 242+ specialized prompts. USE WHEN user says 'do research', 'extract wisdom', 'analyze content', 'find information about', or requests web/content research.

Create compelling story-format summaries using UltraThink to find the best narrative framing. Support multiple formats - 3-part narrative, n-length with inline links, abridged 5-line, or comprehensive via Foundry MCP. USE WHEN user says 'create story explanation', 'narrative summary', 'explain as a story', or wants content in Daniel's conversational first-person voice.

10 hooks across 8 events