Update to OloLand DD

{
  "description": "Use when performing financial valuations, building DCF/LBO models, running Monte Carlo simulations, or analyzing comparable transactions. Provides deterministic valuation framework with strict unit enforcement.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 444
    }
  ],
  "name": "financial-valuation",
  "skill_md_contents": "---\nname: financial-valuation\ndescription: Use when performing financial valuations, building DCF/LBO models, running\n  Monte Carlo simulations, or analyzing comparable transactions. Provides deterministic\n  valuation framework with strict unit enforcement.\n---\n\n# Financial Valuation Methodology\n\n## Deterministic Engines (Not LLM-Generated)\n\nOloLand uses validated computation engines for all financial models. Never generate financial model outputs as prose — use MCP tools.\n\n### DCF (Discounted Cash Flow)\n- **Tool**: `get_dcf_valuation(deal_id)`\n- **Engine**: EBITDA → Free Cash Flow projection (5-10 years) → Terminal value (perpetuity growth) → WACC discount\n- **WACC**: CAPM-calculated (risk-free rate + beta * equity risk premium + size premium)\n- **Sensitivity**: Revenue growth rate vs EBITDA margin vs terminal growth rate\n- **Unit system**: `StrictFinancialValue` — ACTUAL dollars in storage, MILLIONS in calculation, Smart B/M/K in display\n\n### LBO (Leveraged Buyout)\n- Multi-tranche debt: Senior, Mezzanine, Subordinated, Revolver\n- Cash sweep ordering: Revenue → Operations → Debt repayment → Equity\n- PIK (Payment-in-Kind) toggle per tranche\n- Leverage covenants: Total leverage ratio, interest coverage ratio\n- Returns: IRR and MOIC at exit under multiple scenarios\n\n### Monte Carlo Simulation\n- **Tool**: `run_monte_carlo_simulation(deal_id, n_simulations, seed)`\n- **Execution boundary**: This tool creates and persists a new simulation. Authority must come from exactly one of these contexts:\n  1. A direct `ololand-dd-valuation <deal_id> run monte-carlo`, `ololand-dd-valuation <deal_id> refresh monte-carlo`, `ololand-dd-valuation <deal_id> run all`, or `ololand-dd-valuation <deal_id> refresh all` call.\n  2. The user's explicit invocation of, or unambiguous request to run, a named fixed-purpose workflow whose visible contract declares one Monte Carlo run, currently the **public branch only** of `ololand-dd-pre-screen`, `ololand-dd-ic-memo-skeptical`, or DD Analyst **Full DD mode**. That invocation authorizes only the single call, deal, and parameters declared by that workflow; it does not require a second `ololand-dd-valuation run` phrase. The private `ololand-dd-pre-screen` branch authorizes no valuation engine and must remain signal-only until a dedicated governed private-company tool exists.\n- Auto-loading this skill, routing to an agent, a generic diligence/memo question, a background task, a prior run, or merely recommending Monte Carlo grants no authority. A failed authorized call also grants no automatic retry. When neither context applies, do not call the tool; report that there is no governed Monte Carlo read endpoint.\n- Vectorized stochastic engine (not loop-bound)\n- Distribution support: Normal, LogNormal, Triangular\n- Gaussian copula for correlated variables\n- Output: Full EV/equity distribution + P5/P25/P50/P75/P95 + VaR/CVaR\n\n### Comparable Analysis\n- Trading multiples: EV/Revenue, EV/EBITDA, P/E\n- Precedent transactions: Recent M&A deal premiums\n- Peer selection by industry, size, geography, margin profile\n\n## Cross-Document Reconciliation\n\nBefore any valuation, verify input data consistency:\n- Compare revenue/EBITDA across: CIM, audited financials, management model, tax returns\n- Source hierarchy: CPA audited > tax return > management model > AI extracted\n- Flag discrepancies > 2% spread\n- Treat separately reconciled document values as evidence about a discrepancy, not as permission to rewrite an identified model. Report the exact model-returned input and the higher-confidence document value side by side, with their distinct citations and the variance.\n- Never substitute, recalculate, relabel, or explain a governed DCF/LBO using a separately reconciled figure unless the exact model lineage (run, publication, snapshot, and receipt) proves that figure was applied. Otherwise preserve the governed model as returned and report the discrepancy in a separate reconciliation section.\n- A reconciled value may enter a new model only through an explicitly authorized model workflow that records that exact value in its returned assumption/input lineage. Until a governed read binds the resulting run to the required identity, keep that result an unpublished candidate and do not imply the existing governed model incorporated the reconciliation.\n\n## Risk Context and Model Integrity\n\nRisk findings must remain separate from the governed valuation unless the\nidentified model's own returned assumption lineage proves an approved,\nsource-derived bridge for that exact model identity.\n\n- Present automated dollar impacts and WACC premiums as separately labeled\n  `heuristic_scenario` context. They are not source-derived or approved model\n  inputs merely because the risk engine returned them.\n- Do not alter, relabel, or substitute a governed DCF/LBO case using automated\n  risk amounts or WACC premiums. Do not require or invent a risk-adjusted range.\n- An adjustment may be described as applied only when the exact governed model\n  identity (run, publication, snapshot, and receipt) returns assumption lineage\n  proving a `source_derived` approved bridge. Otherwise report the governed\n  base case and the risk scenario separately, with `dcf_application_allowed`\n  stated as returned.\n- Keep the publication/candidate identity rules intact: a candidate run is not\n  the current decision artifact until a governed read binds it to the required\n  publication, receipt, snapshot, and matching run identity.\n\n\n## OpenAI execution requirements\n\nUse the connected MCP server's current tool schemas. Do not invent tool arguments, job-status endpoints, inputs, or outputs. If a referenced tool is unavailable, explain the limitation and request the needed connection or data. Invoke writes only when the user has requested the corresponding action. Do not initiate purchases or payments. An unrun, unsupported, or unavailable procedure is a gap, never a passing result.\n\n\nOpenAI cannot execute local lifecycle hooks. Use the packaged explicit setup/review workflow when requested. Server-side MCP auditing remains authoritative; preserve evidence blockers and human-only approval gates.\n\nClaim-correction submission is unsupported in this OpenAI upload because the current handler records surface=cowork. Do not invoke submit_agent_claim_correction from OpenAI. Explain the limitation and retain proposed correction text for human review without claiming submission. See unsupported-workflows.json for the excluded canonical workflow.\n"
}