lbo · diff

git:20260614.5208b4c to git:20260615.1734111

37 added, 41 removed. Audit A to A.

---

name: lbo

multi_ticker_semantics: target_with_optional_peers

description: LBO model, leveraged buyout, private equity acquisition, sources and uses, debt schedule, returns waterfall, sponsor IRR, MOIC calculation, PE exit analysis, LBO valuation

temporal_scope:

default_quarters: 4

max_quarters: 12

description: "Typical lookback: 4 quarters, max: 12"

allowed_tools:

- search_companies

- search_xbrl_facts

- get_company_financials

- get_company_profile

- search_earnings_calendar

- list_xbrl_concepts

- retrieval_scope: structured_only

+ - search_documents

+ - search_sec_filings

+ - read_source_outline

+ - read_source_deep_outline

+ - read_source_pages

+ - search_keyword_in_source

+ - search_cross_period

+ - batch_search

+ - get_statement_structure

+ retrieval_scope: unstructured_document_search

min_tool_diversity: 5

---

## Preflight

- !curl -s -o /dev/null -w "%{http_code}" --max-time 2 https://mcp.agentii.ai/mcp/health 2>/dev/null || echo "UNREACHABLE"

+ Run the canonical pre-flight sequence — MCP health probe, ticker resolution, workspace `style.md` override, memory load, and coverage check. See `contracts/preflight.md`.

- **Agent Call Tracing**: The first tool you call will return a `_run_id` in its result. On every subsequent tool call, include HTTP header `X-Agentii-Trace: agent={skill_name}; parent={caller_name}; instance={instance_label}`. The MCP server will inject run_id, depth, and user_id automatically. When spawning parallel sub-agents of the same type, assign each a unique instance label (e.g., equity-research-1, equity-research-2). See `contracts/x-agentii-trace-header.md` for the full contract.

+ Include the `X-Agentii-Trace` header on every tool call per `contracts/x-agentii-trace-header.md`.

## Triggers

- analyze lbo model

- run lbo model analysis

- produce lbo model report

- lbo model breakdown

- lbo model deep dive

- build a lbo model

- assess lbo model

- quantify lbo model

- compare lbo model across peers

- review lbo model for

- generate lbo model on

- lbo model for investment decision

## Defaults

| Parameter | Default | Notes |

|---|---|---|

| lookback_years | 3 | Historical data window |

| include_peers | false | Whether to surface a peer comparison block |

## Methodology

### Retrieval Scope

This skill performs unstructured document search at scale across SEC filings (10-K, 10-Q, 8-K). The three-layer agent-use-ready retrieval protocol (Document Discovery → Page Map → Deep Read) applies to all unstructured document search at scale.

### Retrieval Strategy

- Follow the retrieval strategy decision tree in `retrieval.md`. This skill uses:

- - Branch (a) for structured financial metrics via `search_xbrl_facts` with `list_xbrl_concepts` pre-condition for unfamiliar concepts.

- - Branch (b) for multi-period unstructured queries via `search_cross_period`.

- - Branch (c) for single-period document queries via direct `read_source_outline` → `read_source_pages`.

- - Branch (d) for simple lookups via `get_company_profile` / `search_earnings_calendar`.

+ See `contracts/retrieval.md` for the canonical decision tree; skill-specific retrieval detail is in `references/methodology.md`.

### Temporal Scope

Default: 12 fiscal quarters (max 20). Financial modeling: trailing 12 quarters (3 fiscal years) for long-range projection inputs.

### Tool Allowlist

- See frontmatter `allowed_tools` — 12 tools declared for this vertical.

+ See frontmatter `allowed_tools`.

### Protocol

- 1. Pre-retrieval: call `get_company_fiscal_calendar/{ticker}` to resolve fiscal period format.

- 2. Concept discovery: call `list_xbrl_concepts(query=<term>, ticker=<T>)` for unfamiliar XBRL concepts.

- 3. Retrieval: follow the three-layer protocol —

- - Layer 1: `search_documents` / `search_sec_filings` to discover candidate filings.

- - Layer 2: `read_source_outline` to scan page-level metadata.

- - Layer 2.5 (optional): `search_keyword_in_source` to filter large documents.

- - Layer 3: `read_source_pages` to deep-read only selected pages.

- 4. Evidence-pack handoff: produce `evidence-pack.json` + `evidence-digest.md` per the evidence-pack output contract.

+ Step-by-step execution detail is in `references/methodology.md`.

## Deliverable Chain

```

[search_xbrl_facts + get_company_financials] → xlsx_build(spec: lbo) → xlsx_recalc → xlsx_audit → [.xlsx output]

```

## Validation Gates

1. **sources vs uses**: sources = uses within 0.1% tolerance. *If failed*: If unbalanced: refuse delivery.

2. **sponsor IRR**: >= 20% at exit. *If failed*: If IRR < 20%: flag in assumptions.

3. **debt schedule**: mandatory repayments present for each tranche. *If failed*: If missing: refuse delivery.

4. **calculation arc cross-validation **: cross-statement balancing verified against `gold.xbrl_calculations` weights — the LBO model's financial projections MUST align with the filer's reported accounting relationships. Call `get_statement_structure/{ticker}?statement_type=balance_sheet&include_calculations=true`. Flag discrepancies ≥1% of parent concept value. *If failed*: If material discrepancy (≥1%): flag in audit findings.

5. **tool diversity**: distinct MCP tools used in this invocation >= `min_tool_diversity` (5). *If failed*: flag as depth-insufficient in Coverage Gaps, listing which tool categories were unused (structured data / document retrieval / company metadata / earnings calendar / coverage). This gate does NOT block analysis completion — it is a quality signal for your review.

## Tool Fallbacks

- |------|-------------|-----------------|---------------------|

- | `read_source_pages` | SQL error / PROXY_ERROR | Use `search_keyword_in_source(document_id, keyword)` if document_id known; otherwise `search_documents` with same query | "source file unavailable; used keyword search instead" |

- | `list_xbrl_concepts` | Timeout / 503 | Use direct `search_xbrl_facts` with standard US-GAAP concepts (Revenues, NetIncomeLoss, EarningsPerShareDiluted, OperatingIncomeLoss, Assets) | "concept discovery skipped due to timeout; using standard US-GAAP concepts" |

- Tool errors are retried ONCE with the fallback action before escalating to the retrieval gaps failure policy. If both Layer 2 and Layer 3 tools are unavailable, enter document access degradation mode (structured data + metadata only, flag output as degraded).

+ Per-tool failure modes and fallback actions are tabulated in `references/tool-fallbacks.md`.

## Output File

- Write the final deliverable to `{ticker}/{{YYYY-MM-DD_HHMM}}_lbo_{{affix}}.md` .

+ Write the final deliverable to `{ticker}/{YYYY-MM-DD_HHMM}_lbo_{affix}.md` .

## Output Structure

- 1. **Executive Summary** — sponsor IRR, MOIC, exit year, key value creation drivers (EBITDA growth, debt paydown, multiple expansion)

- 2. **Transaction Assumptions** — entry EBITDA, entry multiple, purchase price, debt/equity split, management equity rollover, transaction fees

- 3. **Sources & Uses** — sources (debt tranches, sponsor equity, management rollover) = uses (purchase price, fees, cash to B/S) within 0.1% (Validation Gate 1)

- 4. **Debt Schedule** — term loan, senior notes, subordinated notes, revolver: opening balance, mandatory repayments, optional repayments, interest rate, interest expense, closing balance per period (Validation Gate 3: mandatory repayments present for each tranche)

- 5. **Pro Forma Income Statement** — revenue, EBITDA, D&A, EBIT, interest expense, pre-tax income, net income per projection year

- 6. **Pro Forma Balance Sheet** — assets, debt tranches, equity accounts; calculation arc cross-validation per

- 7. **Cash Flow & Debt Paydown** — EBITDA → operating CF → total debt service → ending debt balances → cash generation

- 8. **Returns Waterfall** — enterprise value at exit → net debt at exit → equity value → sponsor equity return → IRR and MOIC

- 9. **Sensitivity Analysis** — 2-way table: entry multiple (rows) × exit multiple (columns) → IRR/MOIC matrix

- 10. **Coverage Gaps & Citations** — data not retrievable + full citation index in `{ticker} {citation_id} page<N>` format

+ The deliverable is a structured markdown report written to the path in `## Output File`. Full section-by-section template (headings, tables, and field definitions) lives in `references/output-structure.md`. Required elements:

+ 1. **Executive Summary** — headline conclusions (≤200 words).

+ 2. **Core analysis sections** — per this skill's methodology and analyst modes.

+ 3. **Data classification** — tag findings `[FACT]` / `[DEDUCTED]` / `[VIEW]` per `contracts/snapshot-synthesis.md`.

+ 4. **Coverage Gaps & Citations** — inline `/v/` citations are PRIMARY (immediately after each fact); the bottom **Citations** section is a non-duplicative roll-up index.

+ 5. **Output frontmatter** — emit the FR-090 structured block per `contracts/output-frontmatter-schema.md`.

+ **Citations & memory**: follow `contracts/citation-and-memory.md` — ≥1 citation per 200 words; every material fact, table row, and metric is immediately followed by its inline clickable `https://agentii.ai/v/{ticker}/{citation_id}/{N}` link; a bottom **Citations** section provides a non-duplicative roll-up index; the closing TUI reply includes a compact **Key Citations** list (headline 5–10 facts) of clickable `/v/` URLs; and append the run to `agentii.md` per `contracts/agentii-md-schema.md`.

+ ## Memory & Snapshot

+ - **Memory load** (pre-flight): load prior workspace context for the ticker before retrieval — see `contracts/memory-load.md`.

+ - **Structured output frontmatter**: emit the FR-090 block (`key_metrics`, `conclusions`, `facts_count`, `deducted_count`, `views_count`, `citation_count`) per `contracts/output-frontmatter-schema.md`.

+ - **Snapshot synthesis**: after writing the deliverable, update the two-tier snapshot and classify findings as `[FACT]`/`[DEDUCTED]`/`[VIEW]` — see `contracts/snapshot-synthesis.md`.

+ - **Session archival**: record the run under `sessions/{YYYY-MM-DD}/` and update `sessions/INDEX.md` per `contracts/session-format.md`.

+ ## Final Summary (TUI)

+ End the closing chat reply with a compact **Key Citations** list (headline 5–10 facts), each a clickable `https://agentii.ai/v/{ticker}/{citation_id}/{N}` link, so the user can cmd+click straight to the exact SEC page. See `contracts/citation-and-memory.md`.

## Error Handling

|---|---|---|---|

| Missing data | Data API returns empty result set | Widen date range and retry once | "No data available for {ticker} in requested window." |

| Sector mismatch | Peer sector != target sector | Filter out mismatched peers | "Removed {n} peer(s) due to sector mismatch." |