Agent Skills › staskh/trading_skills › insider-trading

insider-trading

GitHub

获取一只或多只股票的SEC Form 4内部人交易活动。支持查询高管买卖、交易详情及情绪分析，默认回溯90天，结果按净买入值排序。

.claude/skills/insider-trading/SKILL.md staskh/trading_skills

Trigger Scenarios

查询内部人买入或卖出行为查看高管交易记录评估内部人市场情绪搜索Form 4申报数据

Install

npx skills add staskh/trading_skills --skill insider-trading -g -y

More Options

Non-standard path

npx skills add https://github.com/staskh/trading_skills/tree/main/.claude/skills/insider-trading -g -y

Use without installing

npx skills use staskh/trading_skills@insider-trading

指定 Agent (Claude Code)

npx skills add staskh/trading_skills --skill insider-trading -a claude-code -g -y

安装 repo 全部 skill

npx skills add staskh/trading_skills --all -g -y

预览 repo 内 skill

npx skills add staskh/trading_skills --list

SKILL.md

Frontmatter

{
    "name": "insider-trading",
    "description": "Get insider trading activity (SEC Form 4 filings) for one or more stocks. Use when user asks about insider buying\/selling, executive transactions, insider sentiment, or Form 4 activity.",
    "dependencies": [
        "trading-skills"
    ]
}

Insider Trading

Fetch recent insider transactions from Yahoo Finance (SEC Form 4 data).

Instructions

Note: If uv is not installed or pyproject.toml is not found, replace uv run python with python in all commands below.

uv run python scripts/insider_trading.py SYMBOLS [--days DAYS]

Arguments

SYMBOLS - Single ticker or comma-separated list (e.g., NVDA or NVDA,PLTR,GOOG)
--days - Trailing days to look back (default: 90)

Output

Returns JSON with:

transactions - List of insider trades with insider name, role, transaction type, shares, price, value, date, ownership type
summary - Net sentiment (net_buying, net_selling, neutral), buy/sell counts and values

For multiple symbols, results are ranked by net buying value (most buying first).

Use Cases

"Show me insider buys for NVDA in the last 90 days"
"Compare insider activity across NVDA, PLTR, GOOG"
"Which of these stocks has the most insider selling recently?"

Dependencies

yfinance

Timezone

All timestamps and time-based calculations must use the America/New_York timezone. All JSON output must include generated_at (NY time string) and data_delay fields.