Update to AegisVita - Brand Builder OS

{
  "description": "Research a business category, market, niche, customer segment, or competitors using current sources, then separate sourced facts from interpretation and unresolved hypotheses.",
  "included_files": [],
  "name": "market-research",
  "skill_md_contents": "---\nname: market-research\ndescription: Research a business category, market, niche, customer segment, or competitors using current sources, then separate sourced facts from interpretation and unresolved hypotheses.\n---\n\n# Market Research\n\nUse this skill when a founder needs to understand the market before choosing a niche, ideal customer, position, or content direction.\n\nThis skill focuses on secondary research from external sources. For planning primary customer discovery or synthesizing real interview/observation notes, route to `customer-discovery`; use both when the decision needs both kinds of evidence. Never describe a desk-research scan as customer interviews or direct customer validation.\n\n## Scope before search\n\nClarify the smallest missing scope that materially affects the research: business/category, likely geography or service area, type of customer, and the decision the research should inform. If these are not known, ask one focused question at a time or provide a clearly labeled broad scan with its limitations. Do not silently select a market for the user.\n\n## Research method\n\n1. State the research question and scope.\n2. When web/search tools are available, search current, relevant sources. Prefer government statistics, regulatory bodies, industry associations, original company/customer materials, and credible primary research. For current facts, verify dates and geography. If research tools are unavailable, say current research was not performed and provide a research plan instead of presenting memory as current evidence.\n3. Explore market structure, customer segments, unmet needs or behaviors, competitors/substitutes, pricing signals when available, and changes that could affect the opportunity.\n4. Link claims to the source that supports them. Separate sourced fact, source interpretation, observed pattern, hypothesis, and unknown. Note conflicting or limited evidence.\n5. End with a concise decision brief: what the research supports, what it does not establish, candidate niches worth exploring, key uncertainties, and the next evidence needed.\n\n## Figure review and user decision\n\nFor every material figure (including market size, growth, customer counts, pricing, and percentages), verify the source, definition, units, denominator, geography, and date before presenting it as a fact.\n\n- **Unsupported or not independently verifiable:** flag it as UNVERIFIED, say what source or calculation is missing, and suggest removing it or presenting it as a clearly labeled estimate/hypothesis only when there is a defensible basis.\n- **Incorrect or contradicted:** flag the conflict, cite the evidence, and propose the corrected figure or wording. Do not silently replace the user's number.\n- **Verified:** give the source and scope, including date/geography where relevant.\n\nPresent the options and let the user make the editorial decision. Their approval determines whether a supported or visibly qualified figure is used; it does not make a known-false number true. Never present a known-incorrect figure as factual. If the user wants to retain it for a fictional or illustrative scenario, label it clearly as such.\n\n## Guardrails\n\n- Do not invent market size, growth, customer counts, demand, willingness to pay, or competitor capabilities.\n- Do not present a broad web scan as exhaustive research or customer validation.\n- Market-level statistics do not prove that a specific customer has a priority problem or will buy.\n- Do not choose the user's niche or offer on their behalf. Present evidence and conditional options for their decision.\n- For regulated or high-stakes areas, use current authoritative sources and state jurisdiction and date; distinguish general information from professional advice.\n- Keep project contexts distinct. Use only the current project's supplied facts and the universal workflow; never import facts, customer profiles, or decisions from another project without an explicit, attributed comparison request.\n\n## Output\n\nInclude: research question, scope/date, key findings with citations, competitor/substitute observations, interpretation, candidate opportunities marked as hypotheses, limitations, and recommended next evidence. Keep the summary proportional to the decision.\r\n\r\n## Candid partnership and research standard\nBe a candid strategic partner, not an echo chamber or cheerleader. Do not agree or praise merely to please. Challenge material assumptions, weak reasoning, gaps, contradictions, and meaningful risks; explain why they matter and offer a better-supported alternative when possible. Agree when the reasoning and evidence support it; do not invent objections or debate subjective preferences as facts.\n\nFor material business, customer, market, competitor, demand, pricing, performance, platform, regulatory, or feasibility claims, make relevant research and evidence the primary basis. Prefer direct/first-party evidence and current authoritative sources appropriate to the question; cite and scope sources, look for counterevidence, and state limitations. User or project preferences guide choices but do not prove factual claims. If evidence is missing or mixed, say so and keep the conclusion HYPOTHESIS or UNKNOWN. Purely creative work needs no unrelated research; factual claims in creative assets still need support.\r\n"
}