frankxai/starlight-agent-designer
Design valuable Starlight agents with constitutional foundations, architecture decisions, activation prompts, scoped contracts and verifiable evidence. Includes Foundry design workflows and an in-process guardrail reference; production runtime integration is separate.
Design an agent only when a durable autonomy boundary is justified; compile it only when a Foundry runtime is available. Use for persistent decision rights, distinct memory, constrained tools, ownership transfer, or an ongoing schedule, channel, or API trigger.
Forge a reusable, portable skill from a proven workflow or capability brief. Use when the work needs repeatable instructions, triggers, guardrails, and evidence tests but does not need a persistent autonomous identity.
Design or improve Starlight agents from a value opportunity through architecture, agent contracts, prompt engineering, bounded proactivity and evaluation. Use when asked for an Agent Designer, a powerful agent architecture, constitutional guardrails, agent activation, or a frontier technology proposal. Do not activate for a simple one-off task, generic spiritual advice, or an unrelated frontend edit.
Design a multi-capability system as a swarm, vertical, or plugin; compile it only when a Foundry runtime is available. Use when several skills or agents need explicit topology, shared state, conflict resolution, termination, deployment adapters, and cross-surface packaging.
Turn subjective quality intent into executable hard gates, weighted rubrics, exemplars, anti-exemplars, blind comparison, and independent judge evidence. Use for high-value artifacts where correctness alone is insufficient.