synth-personas

Generates synthetic-persona feedback on an artifact (pitch deck, design doc, proposal, white paper) by fanning out parallel OpenRouter LLM calls — one per persona — against a curated library of ~80 personas (tech billionaires, VCs, tech media, podcasters, scientists, public intellectuals, developer audiences). Use when the user wants reactions "from a panel of", "as if from VCs/billionaires/tech-media", asks "what would X think of this", or asks to score a pitch deck / proposal across many viewpoints. Do NOT use for single-persona roleplay or generic feedback.

Generate synthetic-persona feedback on an artifact (pitch deck, doc, design proposal, white paper) by fanning out parallel OpenRouter LLM calls — one per persona — against a curated set of ~80 persona profiles (tech billionaires, VCs, tech media, podcasters, scientists, public intellectuals, developer audiences). TRIGGER when the user wants reactions "from a panel of", "as if from VCs/billionaires/tech-media", asks "what would X think of this", or asks to score a pitch deck / proposal across many viewpoints. DO NOT trigger for single-persona roleplay or general feedback requests.

Author a new synth-personas persona profile end-to-end: pick the slot, research from primary 2024–2026 sources, write the 9-section body with traceable verbatim quotes, validate via the CLI, and update the index. TRIGGER when the user asks to "add a persona", "create a persona for X", "write up X as a persona", or "add N more VCs/founders/investors/journalists" to the library. DO NOT trigger for: using the persona library against an artifact (that's `synth-personas`), releasing the public mirror (that's `release-public`), or editing personas in a project's private personas directory (different sourcing rules — consult the user directly).