Financial Machine Learning
by bytesagain1
Explore curated financial ML tools for trading, risk models, and predictions. Use when building models, benchmarking accuracy, or researching quant tools.
安装
claude skill add --url github.com/openclaw/skills/tree/main/skills/bytesagain1/financial-machine-learning文档
Financial Machine Learning
An AI toolkit for logging, tracking, and managing financial machine learning operations. Each command records timestamped entries to its own log file for auditing and review.
Commands
Core Operations
| Command | Description |
|---|---|
configure <input> | Log a configuration entry (view recent entries if no input given) |
benchmark <input> | Log a benchmark entry for performance testing |
compare <input> | Log a compare entry for model comparison tasks |
prompt <input> | Log a prompt entry for prompt engineering tasks |
evaluate <input> | Log an evaluate entry for model evaluation |
fine-tune <input> | Log a fine-tune entry for model fine-tuning tasks |
analyze <input> | Log an analyze entry for data analysis |
cost <input> | Log a cost entry for cost tracking |
usage <input> | Log a usage entry for usage monitoring |
optimize <input> | Log an optimize entry for optimization tasks |
test <input> | Log a test entry for testing tasks |
report <input> | Log a report entry for reporting |
Utility Commands
| Command | Description |
|---|---|
stats | Show summary statistics across all log files |
export <fmt> | Export all data in json, csv, or txt format |
search <term> | Search all log entries for a term (case-insensitive) |
recent | Show the 20 most recent entries from history |
status | Health check — version, data dir, entry count, disk usage |
help | Show available commands |
version | Show version (v2.0.0) |
Data Storage
All data is stored in ~/.local/share/financial-machine-learning/:
- Each command writes to its own log file (e.g.,
configure.log,benchmark.log,fine-tune.log) - All actions are also recorded in
history.logwith timestamps - Export files are written to the same directory as
export.json,export.csv, orexport.txt - Log format:
YYYY-MM-DD HH:MM|<input>(pipe-delimited)
Requirements
- Bash (no external dependencies)
- Works on Linux and macOS
When to Use
- When you need to track financial ML experiments (benchmarks, fine-tuning, evaluations)
- To maintain an audit trail of model configurations and prompt engineering
- When comparing model performance across different runs
- For tracking costs and usage across ML operations
- To search or export historical experiment records
- When building a log of optimization and testing iterations
Examples
# Log ML operations
financial-machine-learning configure "set learning_rate=0.001"
financial-machine-learning benchmark "GPT-4 accuracy test on portfolio data"
financial-machine-learning fine-tune "BERT model on earnings calls"
financial-machine-learning evaluate "backtest Q3 predictions"
financial-machine-learning compare "LSTM vs transformer on forex data"
financial-machine-learning cost "API usage March 2025: $142"
financial-machine-learning optimize "hyperparameter sweep batch 3"
financial-machine-learning prompt "risk assessment template v2"
# View recent entries for a command (no args)
financial-machine-learning benchmark
financial-machine-learning cost
# Search and export
financial-machine-learning search "BERT"
financial-machine-learning export csv
financial-machine-learning stats
financial-machine-learning recent
financial-machine-learning status
Configuration
Set FINANCIAL_MACHINE_LEARNING_DIR environment variable to change the data directory. Default: ~/.local/share/financial-machine-learning/
Output
All commands output to stdout. Redirect with financial-machine-learning report > output.txt.
Powered by BytesAgain | bytesagain.com | hello@bytesagain.com
相关 Skills
面试体系设计
by alirezarezvani
按岗位、级别和团队设计面试流程，生成能力矩阵、题库与评分标准，分析面试官偏差并校准招聘门槛，适合搭建或优化企业招聘体系。
✎ 团队招人没章法时，用它快速搭建岗位化面试流程、题库与评分标准，还能兼顾校准面试偏差，招聘更稳更准。
抽认卡
by BytesAgain
Spaced repetition study tool with deck management. Use when you need flashcard.
教程文档
by anderskev
Tutorial patterns for documentation - learning-oriented guides that teach through guided doing
相关 MCP 服务
by boosted-chat
Flight search & booking for AI agents. 400+ airlines, $20-50 cheaper than OTAs.
by jjlabsio
Search company disclosures and financial statements from the Korean market. Retrieve stock profiles, market classifications, and historical trading data across major exchanges. Accelerate equity research with accurate, date-specific insights for Korean securities.
✎ 做韩国股研时，用它能一站查公司披露、财报和历史行情，按日期精确追溯关键信息，比手动翻交易所高效太多。
by jjlabsio
检索韩国市场公司的披露文件与财务报表，并获取股票概况等关键信息。
✎ 想研究韩股公司时，它能一站式拉取披露、财报和股票概况，省去跨站查资料的麻烦，对跨境投研尤其省时。