Trade Idea Generation logo

Trade Idea Generation

Community
agentii-ai
trade-idea-generation

Systematic trade idea generation framework, fundamental quantitative and qualitative screening pipeline, catalyst-driven trade structuring, macro-to-micro idea translation, 20-60 day long-short portfolio management process

Overview

Publisheragentii-ai
Repositoryagentii-investment-intelligence
Skill nametrade-idea-generation
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 Idea Generation 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-idea-generation
  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-idea-generation .claude/skills/trade-idea-generation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Trade Idea Generation 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 Idea Generation 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 Idea Generation 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
trade_horizon_days20-60Professional long/short portfolio management sweet spot
volatility_target20% annualizedTarget portfolio volatility (1.5-2x VIX)
screening_universeS&P 500 + liquid mid-capsDefault screening universe for trade ideas
portfolio_bias_sourcemacro-analysis skillDerive bias from upstream macro view

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. Process framework — embedded in this Protocol (proprietary systematic process)
  2. Quantitative data — search_investment_strategies + financial data from market data scripts
  3. Qualitative context — search_investment_cases + search_by_analogue for historical analogues
  4. Real-time context — market conditions and sector trends from data tools

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.

This skill follows Branch (d) Simple Lookup from contracts/retrieval.md: query search_investment_strategies for fundamental analysis frameworks, search_investment_cases for historical case analogues, search_by_analogue for cross-strategy discovery. Delegates detailed analysis to sub-skills. No unstructured document retrieval.

Temporal Scope

See frontmatter temporal_scope block.

Tool Allowlist

See frontmatter allowed_tools.

Protocol

This skill orchestrates a systematic trade idea generation pipeline for the 20-60 day long/short portfolio management horizon. Detailed methodology, funnel architecture, composite scoring, operational cadence, and the trade-vs-investment hard gate are in references/pipeline-orchestration.md.

Core formula: Trade Idea = Fundamentals + Timing + Trade Structure. If any component is missing, the idea is not actionable.

Hard gate: A trade idea requires a specific, dateable catalyst within 20-60 days. Without one, the idea is an investment, not a trade — move to watchlist.

Pipeline funnel (6 gates, see reference for thresholds):

Universe → Gate 1: Quant Screen → Gate 2: Financial Validation → 
Gate 3: Qualitative Filter → Gate 4: Template Assembly → 
Gate 5: Strategy Match → Gate 6: Trade Structure → Pipeline Ranking

Composite: (Quant × 0.30) + (Qual × 0.30) + (Catalyst × 0.25) + (Macro × 0.15), each 1-10.

Phase 1 — Theory
  1. Macro Bias Input: Receive portfolio bias (long/short/neutral) from upstream. Long → $3B-$10B mid-caps. Short → $20B+ large caps (never short mid-caps — takeover risk). Neutral → emphasize pair trades. Assess sector tailwinds/headwinds.
  2. Quantitative Screening: Delegate to quantitative-screening. Inputs: bias, sectors, universe. Outputs: ranked outlier list, financial validation, growth profiles, trap classification, data quality flags.
  3. Qualitative Deep Dive: Delegate to qualitative-filtering for top <10 candidates. Inputs: candidate list, metrics, sector context. Outputs: KPI analysis, MOP credibility (5-dimension scorecard), management/board assessment, catalyst calendar with specificity/magnitude/probability.
  4. Template Assembly: Delegate to trade-template. Inputs: all quant/qual outputs, macro, peer data. Outputs: multi-method price targets, probability-weighted scenarios (Base 55/Bull 20/Bear 25), GAAP reconciliation, thesis statement.
  5. Macro-Driven Cases: Delegate to macro-idea-generation for top-down ideas. Inputs: regime, indicators, international context. Outputs: regime-to-sector mapping, macro catalyst timeline, ADR candidates, invalidation thresholds.
Phase 2 — Implementation
  1. Strategy Matching: search_investment_strategies(domain=fundamental) → search_by_analogue(company_situation, event_type) → get_investment_strategy. Cross-reference: do matched strategies confirm or challenge the thesis?
  2. Historical Precedent: search_investment_cases(domain=[derived]). Flag parallels and divergences. Cite via /v/ links. Note gaps explicitly — absent precedent is itself information.
  3. Trade Structure: Stock (default), options (delegate to options-execution), or pair trade (market-neutral, macro divergence). Requirements: identifiable catalyst within 60 days, R/R > 2:1.
  4. Pipeline Output: Rank by composite. Classify: Actionable (all gates, catalyst < 60d, R/R > 2:1) / Watchlist (catalyst > 60d, R/R borderline) / Discard (failed gates 1-3). Document full audit trail.

Output File

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

Output Structure

  1. Executive Summary — Pipeline funnel statistics (universe → gate 1 → ... → gate 6 counts), composite scores, top 3 actionable recommendations
  2. Macro Context — Portfolio bias (long/short/neutral), macro regime, sector tailwinds/headwinds
  3. Quantitative Screening Results — Outlier list with sector-relative metrics, peer groups, financial validation flags, data quality report
  4. Qualitative Filtering Results — KPI analysis, MOP credibility scores, management/board assessments, catalyst calendar with quality ratings
  5. Trade Templates — Full templates for top candidates: price targets (all three methods with weights), trading comps output, GAAP reconciliation, scenario analysis
  6. Strategy Framework Matches — Matched strategies from knowledge base with /v/ citations, confirmation or challenge to thesis
  7. Historical Analogues — Matched cases with parallels/divergences analysis, key learnings from precedent
  8. Trade Structure Recommendations — Stock/options/pair trade decisions with catalyst timelines and R/R ratios
  9. Prioritized Pipeline — Ranked watchlist with composite scores, conviction levels, position sizes, classification (Actionable/Watchlist/Discard)
  10. Audit Trail — Full documentation from macro bias → screen → filter → template → strategy → structure
  11. Coverage Gaps — Data limitations, degraded-mode annotations, candidates flagged for further research

Error Handling

ErrorFallback
No macro bias inputRun with neutral bias; screen both directions; flag missing context
Quantitative screening returns emptyBroaden screening parameters; check data sources; flag
No strategy frameworks foundProceed with manual analysis; flag knowledge base gap
search_by_analogue emptyNote "no relevant historical analogues found"; do not fabricate
Sub-skill unavailableExecute steps manually using embedded framework; flag degraded

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/pipeline-orchestration.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 Idea Generation AI skill do?

Systematic trade idea generation framework, fundamental quantitative and qualitative screening pipeline, catalyst-driven trade structuring, macro-to-micro idea translation, 20-60 day long-short portfolio management process

Why use Trade Idea Generation on TypingMind?

Because you install it once and use it with any model. Trade Idea Generation 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 Idea Generation 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-idea-generation. 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 Idea Generation?

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 Idea Generation?

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

Is the Trade Idea Generation 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 👇