dcf
DCF valuation model, discounted cash flow, intrinsic value, WACC calculation, terminal value, free cash flow projection, equity value per share, DCF sensitivity analysis, unlevered free cash flow, present value calculation, build a DCF
agentii-ai · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add agentii-ai/agentii-investment-intelligence --skill dcf技能说明
name: dcf multi_ticker_semantics: target_with_optional_peers description: DCF valuation model, discounted cash flow, intrinsic value, WACC calculation, terminal value, free cash flow projection, equity value per share, DCF sensitivity analysis, unlevered free cash flow, present value calculation, build a DCF 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
- 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
- xlsx-read retrieval_scope: unstructured_document_search min_tool_diversity: 5
Preflight
Run the canonical pre-flight sequence — MCP health probe, ticker resolution, workspace style.md override, memory load, and coverage check. See contracts/preflight.md.
Include the X-Agentii-Trace header on every tool call per contracts/x-agentii-trace-header.md.
Triggers
- analyze dcf model
- run dcf model analysis
- produce dcf model report
- dcf model breakdown
- dcf model deep dive
- build a dcf model
- assess dcf model
- quantify dcf model
- compare dcf model across peers
- review dcf model for
- generate dcf model on
- dcf 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 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
- Inputs: resolved ticker +
search_xbrl_facts(Income Statement, Balance Sheet, Cash Flow) +get_company_financials+get_realtime_quotefor current price. - Build: write a self-contained Python script using
openpyxlthat creates the DCF workbook (projections, WACC, terminal value, sensitivity tables) per## Output Structure. Execute viaBash: python3 script.py. Verify the.xlsxexists. Ifimport openpyxlfails, fall back to.mdsummary withdata_availability: degraded(seecontracts/office-tooling.md). - Validate: run LibreOffice recalc; audit
hardcoded_count == 0for tagged cells per## Validation Gates; verify projection horizon ≥ 5 years, terminal growth < risk-free proxy. - Output: write the artifact path per
## Output File. (Optional) render an executive-summary.pptxviaBash+python-pptx; convert.xlsx → PDFvia LibreOffice. - Next: append to
agentii.md; hand off to a downstream pitch/review skill if requested.
Validation Gates
- projection horizon: ≥ 5 years (10 years for secular-trends analysis). If failed: If < 5 years: refuse delivery, report actual horizon.
- terminal growth rate: < risk-free rate proxy (current 10Y UST). If failed: If terminal_g ≥ rf: flag in assumptions section, note conservatism violation.
- WACC components: WACC = (E/V × Ke) + (D/V × Kd × (1-T) with all components cited to source data. For risk-free rate selection, ERP triangulation, beta de-levering/re-levering, industry betas, and cost of debt estimation, consult
references/cost-of-capital-methodology.md. If failed: If components uncited: refuse delivery, list missing citations. - hardcoded_count: == 0 for all cells tagged projection|margin|discount_factor|pv|sensitivity per xlsx_audit output. If failed: If hardcoded_count > 0: per the hardcode gate, refuse delivery. Bounce back to analytical-subagent ONCE with audit report.
- **calculation arc cross-validation **: cross-statement balancing verified against
gold.xbrl_calculationsweights — the DCF free-cash-flow projection and income statement structure MUST align with the filer's reported concept hierarchy. Callget_statement_structure(accession_number)(resolve the accession_number first). Flag discrepancies ≥1% as audit findings. If failed: If material discrepancy (≥1%): flag in audit findings, refuse delivery for discrepancies ≥5%. Tool-diversity is also tracked here: distinct MCP tools used MUST be ≥min_tool_diversity(5); below that, flag as depth-insufficient in Coverage Gaps (a quality signal, not a delivery blocker).
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}_dcf_{affix}.md .
Output Structure
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:
- Executive Summary — headline conclusions (≤200 words).
- Core analysis sections — per this skill's methodology and analyst modes.
- Data classification — tag findings
[FACT]/[DEDUCTED]/[VIEW]percontracts/snapshot-synthesis.md. - Coverage Gaps & Citations — inline
/v/citations are PRIMARY (immediately after each fact); the bottom Citations section is a non-duplicative roll-up index. - *Output frontmatter