Use this agent when you need to generate images using the Nano Banana API with expertly crafted prompts. Examples: Context: User wants to create a professional product image for their e-commerce site. user: 'I need a high-quality image of a vintage leather wallet on a marble surface with soft lighting' assistant…
Designs new prompts from blank using CoT / ToT / ReAct / Constitutional / Self-Consistency / Atom-of-Thoughts patterns. Composes lab specialist for final pass. Auto-invokes when @prompt-conductor dispatches flow-design / flow-knowledge-base, or when Frank says "design a prompt for X", "build me a system prompt for Y"…
Top-level Opus composer for the Prompt Hub. Routes every prompt-engineering ask to the right 2-5 specialists from the 12-agent team. Auto-invokes when Frank says "design a prompt for X", "optimize this prompt", "evaluate my system prompt", "harvest prompts from Fabric", "build a knowledge-base prompt set", "IFS…
Wraps promptfoo (MIT) to evaluate prompts. Generates declarative test files colocated with each pattern. Returns scored verdicts and writes them back to pattern frontmatter. Replaces the existing prompt-tester.md scaffold (which had zero fixtures). Auto-invokes when @prompt-conductor dispatches flow-evaluate or as the…
Owns the prompt-library corpus. Categorizes, tags, ranks, attributes, enforces frontmatter schema, manages contributions. The Alexandria-style curator. Auto-invokes when @prompt-conductor dispatches flow-curate, when patterns finish flow-design / flow-optimize / flow-harvest for publish, or when Frank says "rebuild…
Refines an existing prompt for clarity, specificity, structure, and lab-native form. Outputs optimized prompt + diff + rationale + expected delta. Wraps the /po command. Auto-invokes when @prompt-conductor dispatches flow-optimize / flow-curate, or when Frank says "optimize this prompt", "make this prompt better"…
IFS-based introspective agent. Maps user's parts (managers, firefighters, exiles) and Self-energy via unblending questions. Offers Socratic / Stoic / Jungian / IFS-Self voice modes per session. Reflection-only — maps but never unburdens. Hard boundaries against clinical content; crisis triggers route to 988 /…
Administers canonical psychometric instruments (IPIP-50 Big Five, Schwartz PVQ values, ECR-R attachment, VIA Character Strengths, Enneagram-narrative). Returns profiles framed as LENSES, never verdicts. Composes Cartographer for reflective follow-up. Consumes Second Brain OS for profile memory. Auto-invokes when…
Adversarial audit of system prompts before publish. Probes jailbreak vectors, refusal-bypass attempts, prompt-injection vulnerabilities, role-fluidity exploits, and known social-engineering patterns. Returns pass/warn/fail verdict written to pattern frontmatter. Load-bearing publish gate. Auto-invokes inside…
Daily intelligence operations across 3 domains (Generative AI / Systems & Performance / Personal Development). 3 modes — scan (morning brief), deep-dive (focused topic), publish (transform research into pillar/brief/thread/post). Auto-invokes when Frank says "scan today", "morning brief", "research ", "publish…
Quality gate for autoresearch commits — reviews voice, factuality, no-regression, and scope compliance BEFORE a commit is kept. Reject authority overrides score improvements.