A layered system of AI agents that guide each experiment from initial idea to shipped prototype. Central agents define workflow standards; experiment-specific agents add domain intelligence on top.
Two layers: hub-level agents shared across all experiments, and experiment-specific agents for domain intelligence.
@experiment-creatorTurns a raw idea into a structured experiment with metadata and directory.
@market-researchResearches TAM/SAM/SOM, competitive landscape, and generates experiment scores.
@prd-writerProduces a comprehensive PRD from the experiment statement and market research.
@prototype-builderScaffolds the prototype from the PRD and wires up the dev environment.
@design-advisorReviews code and live URLs for design quality, accessibility, and heuristics. Auto-invoked by prd-writer and prototype-builder.
@design-guidelinesDesign system and UX principles used by design-advisor and prototype-builder.
@commit-messageStandards for well-formed commit messages.
@scoring-criteriaDetailed 1–5 rubric for each scoring dimension.
Live at /experiments/{slug}/agents/. They extend or compose central agents with domain knowledge unique to that experiment.
listing-generator.mdExperiment-specific capability not present in any central agent.
prototype-builder-extensions.mdAdds extra steps on top of a central agent for this experiment only.
listing-workflow.mdOrchestrates multiple agents into a domain-specific sequence.