本文へ移動
cccskills
無料GitHub で公開

trade-template

Standardized trade idea template, multi-method price target derivation PE and sales multiple approaches, GAAP to non-GAAP reconciliation, base bull bear scenario construction, investment thesis structuring, Zendesk-style case methodology

インストール方法を見る

含まれるファイル(3)

  • SKILL.md8.0 KB
  • references/modes.md720 B
  • references/template-methodology.md19.4 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Methodology fused from professional trading and investment frameworks; all text is an original paraphrase.

Defaults

ParameterDefault ValueRationale
target_horizon_months12Standard forward price target horizon
scenario_probability_sum100%Bear + Base + Bull must sum to 100%
default_position_size3-5%Standard single-position risk allocation

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).

Data Source Priority

  1. Upstream outputs — quantitative screening results + qualitative filtering assessment
  2. Market data — current price, sector multiples, historical ranges via market data tools
  3. Strategy frameworks — search_investment_strategies(kind=thesis) for thesis construction methodology

Methodology

Retrieval Scope

structured_only

Retrieval Strategy

Ownership & insider signals: search_institutional_holdings (top-10 holders + whale portfolios, direction=accumulating|reducing|new|exited) and search_insider_trades (Form-4 transactions with SEC URLs) are available as signal inputs.

Branch (d) Simple Lookup from contracts/retrieval.md: template methodology is embedded in this Protocol. Market data from data tools. Strategy frameworks via search_investment_strategies for thesis construction validation.

Temporal Scope

See frontmatter temporal_scope block.

Tool Allowlist

See frontmatter allowed_tools.

Protocol

This skill converts quantitative and qualitative analysis outputs into a structured, actionable trade template. A trade idea without a template is an opinion; with a template, it is a testable hypothesis. Every trade outcome becomes a learning data point because the template captures what was known and assumed at entry.

Detailed methodology: price target derivation with formulas, comps spreading workflow, GAAP/non-GAAP rules, scenario construction with probability calibration, and position sizing framework are in references/template-methodology.md.

Steps

  1. Data Assembly: Gather all upstream outputs (quant metrics, financial validation, qual assessments, management/board flags, peer group, macro bias). Organize into template sections. Flag gaps — incomplete templates cannot support capital allocation.

  2. Price Target Derivation (three methods, blend by business model per reference weights table):

    • P/E: Justified P/E triangulated from: historical range 25th-75th percentile, PEG-implied (growth × sector PEG), sector median with growth adjustment. Upper/lower bounds from bull/bear EPS × quartile multiples.
    • EV/EBITDA: For capital-intensive, highly levered, M&A contexts. Sector median ± growth/margin/ROIC adjustment. Target equity = Target EV − Net Debt.
    • Sales Multiple: For pre-profit/cyclical. Adjust for margin profile (5% margin at 2x P/S > 20% margin at 4x P/S). Recurring revenue premium.
    • Blend: asset-light 60/30/10 (PE/EV-EBITDA/PS), capital-intensive 30/50/20, financials 50/—/50(P/B), pre-profit —/30/70.
  3. Trading Comps Spreading: Select 4-6 peers via dual-path. Spread revenue, EBITDA, EBIT, EPS, FCF (3yr historical + 2yr forward). Normalize for SBC/amortization/non-recurring differences. Calendarize different fiscal years. Output median + quartiles. Target multiple = peer median ± adjustment for growth, margin, ROIC, leverage, liquidity.

  4. GAAP/non-GAAP Reconciliation: Identify all differences (SBC, amortization, restructuring, impairments, litigation, M&A, asset sales, debt extinguishment, tax). SBC: always include for true economic cost; may exclude for comps ONLY with flag. SBC > 10% revenue = structural issue. "Non-recurring" in 3+/4 quarters = recurring. Normalized = GAAP NI + justified adjustments. Show GAAP alongside.

  5. Scenario Construction: Base 55% (consensus + variant view), Bull 20% (all catalysts, multiple expansion), Bear 25% (catalyst failure, contraction). Probabilities sum to 100%. Bear must be genuinely adverse. EV = Σ(Value × Prob). Margin of Safety = (EV/Price)-1. > 30% high conviction, 15-30% medium, < 15% watchlist.

  6. Thesis Statement: One paragraph, five elements: (1) consensus view, (2) variant view + why, (3) dateable catalyst, (4) quantified return, (5) key risk. Format: "Market believes [X]. We believe [Y] because [evidence]. Converges when [catalyst] within [timeframe], generating [return] against risk of [downside]." Avoid: describing company (no variant), no catalyst, too long, no risk.

  7. Position Sizing: Default 3-5%. Conviction: high→5%, medium→3-4%, low→watchlist. Binary catalyst→reduce 25-33%. R/R > 3:1→upper, 2:1-3:1→standard, < 2:1→skip. Correlation check: correlated with existing→reduce/replace. Hard Day-60 review: no catalyst→exit. Build football field. Handoff complete template.

Output File

{ticker}/{YYYY-MM-DD_HHMM}_trade-template_{affix}.md

Output Structure

  1. Executive Summary — Thesis in one paragraph, price target, expected return, conviction level
  2. Company Overview — Business description, sector, market cap, key financial summary
  3. Quantitative Summary — Key screening metrics, outlier classification, financial validation highlights, peer group
  4. Qualitative Summary — KPI assessment, MOP credibility (5-dimension scorecard), management/board quality flags, key catalyst(s)
  5. Price Target Derivation — PE method (justified P/E triangulation), EV/EBITDA method, Sales Multiple method, blended target with weights, cross-checks
  6. Trading Comps Output — Peer group with multiples, median/quartile statistics, calendarization notes, target multiple derivation
  7. GAAP/non-GAAP Reconciliation — Key adjustments with justification, SBC assessment, normalized earnings calculation
  8. Scenario Analysis — Bear (25%)/Base (55%)/Bull (20%) with probabilities, values, implied returns, probability-weighted expected value
  9. Investment Thesis — Market view vs. variant view (all 5 required elements), catalyst for convergence, timeframe
  10. Risk Assessment — Key risks, maximum adverse scenario, thesis invalidation triggers
  11. Position Recommendation — Suggested position size with conviction/catalyst/RR rationale, entry strategy
  12. Football Field Matrix — Trading comps vs. DCF vs. transaction comps vs. 52-week range vs. current price vs. target range
  13. Coverage Gaps — Data limitations, assumptions flagged for monitoring

Error Handling

ErrorFallback
Insufficient data for price targetUse single-method approach; flag low confidence
GAAP/non-GAAP data unavailableUse reported GAAP; flag potential distortion
No comparable peer groupUse historical company multiples; flag peer gap

Memory Load

See contracts/memory-load.md.

Snapshot

See contracts/snapshot-synthesis.md.

Final Summary (TUI)

Include ### Key Citations block with 0-10 clickable /v/ URLs.

References

  • references/template-methodology.md
  • contracts/citation-and-memory.md
  • contracts/output-frontmatter-schema.md
  • contracts/memory-load.md
  • contracts/snapshot-synthesis.md
  • contracts/preflight.md
  • contracts/retrieval.md

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

3-statement financial model, integrated IS BS CF, income statement projection, balance sheet forecast, cash flow statement, cross-statement balancing, financial model build, operating model, three statement model, integrated financial statements

日本語の概要は準備中です。原文の説明を表示しています。

agentii-ai/agentii-investment-intelligence2072026年9月29日 更新

Institutional-grade equity research skills for AI agents. 80 Claude-type skills across 14 verticals (equity-research-core, models-and-pitches, bio-pharm, scenarios, quantitative-analysis, idea-generation, options-derivatives, business-intelligence, industry-analysis, macro-strategy, portfolio-strategy, technical-analysis, risk-and-psychology, trading-as-business) powered by agentii.ai's agent-use-ready SEC filing data plane — SEC filings and 15K+ earnings call transcripts, 15.99M XBRL facts, and company profiles for 1,146+ US-public-equity tickers. Features the three-layer retrieval protocol (Document Discovery → Page Map → Deep Read, with deep-outline escalation) — measured, not asserted: 97.5% saved against a sequential read, and the page map itself is 10.0% of one (spec 062 T030, 2026-09-23) — server-side parallel multi-period search via search_cross_period, a full Excel/PPT generation pipeline with 3-tier office backend support, and the spec-046 governance layer (constitution, thesis and single-skill modes, mechanical gates, and a template-owned disclaimer on generated reports).

日本語の概要は準備中です。原文の説明を表示しています。

agentii-ai/agentii-investment-intelligence2072026年9月29日 更新

audit-xls

無料

Audit spreadsheet, formula error detection, hardcoded cell finder, cross-sheet reference audit, workbook auditor, Excel model audit, financial model QA, spreadsheet review, cell dependency trace, formula integrity check

日本語の概要は準備中です。原文の説明を表示しています。

agentii-ai/agentii-investment-intelligence2072026年9月29日 更新

Business model classification, business model analysis, structural analysis of how a company makes money, product offering decomposition, distribution channel analysis, customer segment analysis, revenue model identification, market sizing TAM SAM SOM, competitive positioning, business unit performance, management team & leadership analysis, what does the company sell, how does the company go to market, business model type platform service product, channel mix direct vs indirect, revenue concentration risk, CEO CFO executive backgrounds and changes

日本語の概要は準備中です。原文の説明を表示しています。

agentii-ai/agentii-investment-intelligence2072026年9月29日 更新

challenge

無料

Adversarial verification of research theses — cross-run/cross-thesis contradiction via the entity index, pre-mortem (Klarman/Kahneman: assume the loss already happened, reverse the path), inversion (Munger: invert, always invert), and wrong_if falsifiability review. ≈50-finding cap sorted by severity; content-derived finding IDs; incremental scoping with three backstops; lifecycle hooks at pillar-complete / thesis-complete / pre-reduction.

日本語の概要は準備中です。原文の説明を表示しています。

agentii-ai/agentii-investment-intelligence2072026年9月29日 更新

Chart pattern recognition, price action patterns, candlestick signal bars, pullback bar counting H1/H2/H3/H4, trend channels, micro channels, trading ranges, breakouts, major trend reversals 5-step sequence, wedges, double tops and bottoms, triangles, head and shoulders, climaxes, measured moves, support and resistance

日本語の概要は準備中です。原文の説明を表示しています。

agentii-ai/agentii-investment-intelligence2072026年9月29日 更新

agentii-ai のスキルをすべて見る

このスキルの問題を報告する