Trade Template logo

Trade Template

Community
agentii-ai
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

Overview

Publisheragentii-ai
Repositoryagentii-investment-intelligence
Skill nametrade-template
Stars
207
Forks
16
Bundled files
2
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by agentii-ai on GitHub. Read the source before you install it.

Installation

Install the Trade Template AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/plugins/vertical-plugins/idea-generation/skills/agentii/trade-template
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/agentii-ai/agentii-investment-intelligence.git /tmp/agentii-investment-intelligence
mkdir -p .claude/skills
cp -r /tmp/agentii-investment-intelligence/plugins/vertical-plugins/idea-generation/skills/agentii/trade-template .claude/skills/trade-template
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Trade Template in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Trade Template on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Trade Template is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Trade Template AI skill do?

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

Why use Trade Template on TypingMind?

Because you install it once and use it with any model. Trade Template is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Trade Template in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/plugins/vertical-plugins/idea-generation/skills/agentii/trade-template. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Trade Template?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Trade Template?

As many as you like. As long as a model supports skills, you can use Trade Template with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Trade Template AI skill free?

Yes. It is published on GitHub by agentii-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇