Creates professional AI image/video prompts with photographer's and cinematographer's eye. Specializes in composition, lighting, color grading, and storytelling. Use when generating AI...
Strategic compaction suggestion framework that monitors session complexity and suggests context compaction at optimal logical boundaries rather than arbitrary thresholds.
Expert in Internet of Things, Edge Computing, and MQTT. Specializes in firmware (C/C++), wireless protocols, and cloud integration.
Write and optimize prompts for AI-generated outcomes across text and image models. Use when crafting prompts for LLMs (Claude, GPT, Gemini), image generators (Midjourney, DALL-E, Stable Diffusion,...
Document codebase as-is with thoughts directory for historical context
Document codebase as-is with thoughts directory for historical context
Organize and structure information for clarity and discoverability. Design navigation systems, hierarchies, and mental models that match user needs.
Validates agent configurations for model selection, tool permissions, focus areas, and approach quality. Use when reviewing, auditing, improving agents, or learning agent best practices.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when...
Use when designing or architecting Elixir/Phoenix/LiveView applications, creating comprehensive project documentation, planning OTP supervision trees, defining domain models, structuring multi-app...
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
Use when making decisions under time pressure or uncertainty, preventing errors in complex procedures, designing decision rules or checklists, simplifying complex choices, or when user mentions...
Generate SPEC-IT-{HASH}.md files for existing UI code. Enables progressive context loading for legacy codebases. Use when starting to track an existing project.
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
Implement dependency injection in PydanticAI agents using RunContext and deps_type. Use when agents need database connections, API clients, user context, or any external resources.
Create custom OpenCode commands for repetitive tasks. Define command prompts, arguments, shell output injection, file references, and configure agents, models, and descriptions.
Combine heterogeneous data sources into a unified model with conflict resolution, schema alignment, and provenance tracking. Use when merging data from multiple systems, consolidating information,...
Use when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced prompting techniques like chain-of-thought, few-shot learning, or...
Minimal SPARV workflow (Specify→Plan→Act→Review→Vault) with 10-point spec gate, unified journal, 2-action saves, 3-failure protocol, and EHRB risk detection.
Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from AGENTS.md, and reports progress to orchestrator.