3 Statement

Preflight

Run canonical pre-flight per contracts/preflight.md.

Include the X-Agentii-Trace header on every tool call per contracts/x-agentii-trace-header.md — carry the _run_id from your first tool result and name yourself (and your parent, if you were spawned).

Triggers

• analyze 3 statement model
• run 3 statement model analysis
• produce 3 statement model report
• 3 statement model breakdown
• 3 statement model deep dive
• build a 3 statement model
• assess 3 statement model
• quantify 3 statement model
• compare 3 statement model across peers
• review 3 statement model for
• generate 3 statement model on
• 3 statement model for investment decision

Defaults

Methodology

Retrieval Scope

This skill performs unstructured document search at scale across SEC filings and earnings call transcripts (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

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.

Protocol

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

Deliverable Chain

Inputs → Build → Validate → Output → Next

1. Inputs: resolved ticker + 3 years of search_xbrl_facts (Income Statement, Balance Sheet, Cash Flow) + get_statement_structure for presentation tree.
2. Build: write a self-contained Python script using openpyxl that creates the 3-statement workbook per ## Output Structure. Execute via Bash: python3 script.py. Verify the .xlsx exists at the output path. If import openpyxl fails, fall back to .md summary with data_availability: degraded (see contracts/office-tooling.md).
3. Validate: run LibreOffice recalc; audit cross-statement checks (BS balances, CF ties to BS, IS flows to CF) per ## Validation Gates.
4. Output: write the artifact path per ## Output File.
5. Next: append to agentii.md; hand off to a downstream pitch/review skill if requested.

Validation Gates

1. balance sheet balance: Assets = Liabilities + Equity within 1% tolerance. If failed: If unbalanced > 1%: refuse delivery, report imbalance amount.

2. cash flow tie-out: CF ending cash = BS cash for current period. If failed: If mismatched: refuse delivery, report discrepancy.

3. forecast years: exactly 5 historical + 5 forecast years. If failed: If < 5+5: flag in Coverage Gaps, proceed with available data.

4. **calculation arc cross-validation **: cross-statement balancing verified against gold.xbrl_calculations weights — each parent concept's value equals the weighted sum of its children per the XBRL calculation linkbase (e.g., Assets = +1.0 × CurrentAssets + 1.0 × NoncurrentAssets, NetIncomeLoss = +1.0 × Revenues - 1.0 × OperatingExpenses + ...). Call get_statement_structure(accession_number) (resolve the accession_number first via search_sec_filings) to retrieve the weighted parent-child relationships. Flag discrepancies ≥1% of parent concept value as audit findings. If failed: If any material discrepancy (≥1% of parent value): flag in audit findings, refuse delivery for discrepancies ≥5%.

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

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}_3-statement_{affix}.md .