doc-generation
Skill4 starsChanged 4 months agoMITView on GitHub
Generates documentation for trading and financial code: strategy documentation, API references, usage examples, README files, and inline code comments. Trigger when the user wants to document trading code or generate project documentation.
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- report-generationSkill
- visualizationSkill
- data-cleaningSkill
- code-review-financeSkill
- opentdx-engineeringSkill
- gelan-trinity-tradingSkill
- query-skillsSkill
- new-skillSkill
- backtest-strategySkill
- evf-stock-skillSkill
- market-dataSkill
- portfolio-riskSkill
- strategy-developmentSkill
- technical-analysisSkill
- yanchixia-short-termSkill
- yeren-trading-systemSkill
The file
Files
Documentation Generation
Creates clear, structured documentation for financial codebases.
Real Code Reference
tradinglearn/main.py— interactive CLI entry, good candidate for README docstradinglearn/strategies/macd_strategy.py— needs strategy documentation (params, logic, usage)tradinglearn/pytdx2/CLAUDE.md— example of good project-level documentationtradinglearn/pytdx2/demo.py— usage examples for all API calls
Output Types
- Strategy docs: parameters, logic description, assumptions, expected performance
- API docs: function signatures with parameter descriptions, return types, examples
- README: project overview, quick start, installation, dependencies
- Inline comments: explain non-obvious financial logic, formula references
Strategy Documentation Template
# Strategy Name
## Overview
One-sentence description of the core idea.
## Signal Logic
How entry/exit signals are generated, with formulas.
## Parameters
| Parameter | Default | Description |
|-----------|---------|-------------|
| fast | 12 | Short EMA period |
## Risk Management
Stop-loss, position sizing, and risk controls.
## Usage
\`\`\`python
strategy = MyStrategy(param=value)
signals = strategy.generate_signals(data)
\`\`\`Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

