Update to Equity Council

{
  "description": "Investigate macroeconomic, financing, regulatory and technology risks in equity theses, linking causal industry tangents and dependent tail outcomes to shareholder scenarios.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 246
    }
  ],
  "name": "equity-risk",
  "skill_md_contents": "---\nname: equity-risk\ndescription: Investigate macroeconomic, financing, regulatory and technology risks in equity theses, linking causal industry tangents and dependent tail outcomes to shareholder scenarios.\n---\n\n# Equity Risk\n\nIdentify mechanisms that can prevent forecast business value from reaching shareholders. Read the [operating contract](../../references/operating-contract.md), [evidence standard](../../references/evidence-standard.md), and [ranking policy](../../references/ranking-method.md). Use [sector lenses and the causal tangent filter](../../references/sector-lenses.md) to bound adjacent research and the [agent protocol](../../references/agent-protocol.md) for council handoffs.\n\n## Workflow\n\n1. Map exposures before collecting headlines: customers, geography, currency, critical suppliers, regulation, funding sources, variable costs, asset duration and technology substitutes. Separate company-specific fragility from industry, macro and familiar market-factor exposure. A U.S. listing does not establish U.S.-only economic exposure.\n2. Translate each material uncertainty into a chain: external event -> operating driver -> cash flow or balance sheet -> shareholder outcome. State exposed candidates, direction, magnitude range, timing, supporting evidence and the observation that would weaken the mechanism. Higher industry demand can benefit suppliers while raising the candidate's costs; test both sides.\n3. Build a financing timeline from usable liquidity, operating burn, committed investment, maturities, covenants and realistic refinancing alternatives. Compare funding needs with the dates of commercialization or cash generation. Distinguish cash exhaustion, covenant breach, liquidity stress and insolvency. Include issuance price, dilution, priority claims and recoveries when supportable; terminal enterprise success does not guarantee existing shareholder success.\n4. Verify legal and regulatory claims against current official materials for the relevant jurisdiction. Distinguish proposal, enacted rule, effective date, litigation, stay and enforcement practice. An old rule may remain operative; neither age nor a recent article proves current applicability. Specify affected products and economic channels instead of assigning a generic regulatory haircut.\n5. Construct coherent joint stresses. Demand, margins, refinancing spreads, issuance prices and valuation multiples may deteriorate together. Use conditional probabilities when the evidence supports them; do not multiply dependent marginal events or sum overlapping loss mechanisms. Compare candidates under common external shocks while allowing different exposures. Carry unweighted stress ranges when probabilities cannot be defended.\n6. Investigate tangents one causal link at a time when accessible evidence could change the shortlist, valuation, financing outcome or ranking. Prioritize plausible impact, resolvable uncertainty and research feasibility. Park interesting but immaterial branches with a reason rather than claiming exhaustive coverage.\n\n## Interpretation checks\n\nHistorical correlations can fail during funding stress; diversification among similar tickers need not diversify their economic driver. A terminal loss estimate is not maximum drawdown or proof of permanent impairment. Do not add a broad risk premium and separately haircut the same modeled loss without explaining the treatment. Evidence confidence and modeled event probability remain distinct.\n\n## Output contract\n\nReturn a source-linked risk and tangent brief with causal channels, financing timeline, joint stress assumptions, conditional dependencies, mitigants and their limits, scenario changes for valuation, unresolved evidence and rank-changing observations. Include a concise failure path and an alternative benign explanation. Label confidence by evidence quality, report unknown probabilities honestly, and assign complete, conditional or blocked status. The director owns final probability reconciliation and ranking.\n"
}