Construct evidence-grounded persona panels from synthetic interviews and multiple data sources.
npx skills add https://github.com/NOMARJ/sigil --skill empathy-engine
Please help me install this Agent Skill. Skill: empathy-engine Source: https://github.com/NOMARJ/sigil/tree/main/packs/discovery/skills/empathy-engine Command: npx skills add https://github.com/NOMARJ/sigil --skill empathy-engine
Construct a robust, evidence-grounded persona panel framework for discovery projects, enabling teams to synthesize real user experiences into actionable insights for product and AI-agent design.
Define the research frame and initiate a synthetic persona panel for your discovery workflow.
High-intent search queries and answers about installing and using this skill.
To build an evidence-grounded persona panel for product discovery, you define a research frame and initiate synthetic interviews. The panel harvests evidence from multiple sources to construct 6-9 personas aligned with your empirical protocol.
A silence audit in user research is a mandatory empirical protocol step that reviews synthetic interview transcripts for unstated assumptions. It ensures evidence-grounded persona panels remain traceable and prevents unsupported insights from entering the discovery workflow.
You extract user insights by running structured synthetic interviews and harvesting evidence. The discovery workflow maps these insights through a traceable chain—Person to Insight to Epic to Feature to Story—to inform product and AI-agent design.
Yes, you can use synthetic interviews to generate user research data. The process constructs an evidence-grounded persona panel from diverse real-world data sources, requiring careful data governance and adherence to ethical guidelines to maintain validity.
Data governance for synthetic personas requires structured prompts and adherence to an empirical protocol. It mandates a silence audit and ethical guidelines to ensure the evidence chain remains traceable from real-world sources to extracted insights.
User research needs a traceable evidence chain to ensure product features are grounded in real experiences. Mapping the chain from Person to Insight to Epic to Feature to Story validates that discovery outcomes are evidence-based and actionable.
codesour-designMap domain concepts and terminology conflicts for product modelling.
marcmontecalvoOrchestrate PRD creation, requirements discovery, and stakeholder alignment within the BMad Method framework.
travisjneumanGenerate AI governance policies with risk assessment and compliance templates.
bowiemaxGenerate three user personas with jobs-to-be-done, pain points, and gains from research data.
