Stock Trend Scanner

Stock technical analysis scanner based on swing trading principles with multi-timeframe resonance. Use when user asks to scan, analyze, or check stocks for b...

Security Scan

The skill's code and instructions match a stock-scanner's stated purpose, but the package comes from an unknown source, the provided script in the prompt was truncated (so not fully verifiable), and dependencies/network access are not fully declared — review before running.

Purpose & Capability

Name, description, SKILL.md, and the included Python script consistently implement a multi-timeframe stock scanner using yfinance/pandas/numpy. The requested capabilities (fetch historical quotes, compute MACD, moving averages, support/resistance) align with the stated purpose.

Instruction Scope

SKILL.md instructs running the included Python script and explicitly mentions yfinance (no API key). The runtime instructions do not request unrelated files, env vars, or external endpoints beyond Yahoo Finance. However SKILL.md does not list required Python packages (pandas, numpy, yfinance) or how to install them; the script will perform network requests to fetch market data.

Install Mechanism

No install spec (instruction-only skill) which lowers systemic risk. However a non-trivial Python script is included and will be executed locally; the SKILL.md does not provide a vetted install or dependency list. That means users must install Python packages themselves (preferably in a virtualenv).

Credentials

The skill declares no environment variables, no credentials, and no config paths. The script also does not read env vars or local config in the visible portion — requested access is proportionate to a data-fetching scanner (network access to Yahoo via yfinance).

Persistence & Privilege

always is false, the skill is user-invocable, and it does not request persistent system privileges or modify other skills' configurations in the visible files. Autonomous invocation is allowed (platform default) but not combined with other concerning privileges.

What to consider before installing

What to consider before installing/use: - The code and SKILL.md are coherent with a stock scanner and the script uses yfinance to fetch market data (expected network access). - The package has no listed author/homepage and was published by an unknown owner ID — lower trust by provenance alone. - The prompt-provided script was truncated at generate_signal; you should inspect the entire script file locally (especially any code after generate_signal) for hidden network calls, credential usage, or subprocess execution before running. - Install and run only in a contained environment (Python virtualenv or VM). Ensure dependencies (python3, pandas, numpy, yfinance) come from official sources (pip) and pin versions. - If you plan to run it against sensitive systems or provide it credentials, do not proceed until you have audited the full source. If you only need analysis without executing code, consider reimplementing the logic or using a well-known vetted tool/service.

Stock Scanner - 多周期共振趋势扫描器

Quick Start

python3 scripts/stock_scanner.py [SYMBOLS...]

Examples:

python3 scripts/stock_scanner.py AAPL TSLA NVDA
python3 scripts/stock_scanner.py AMD TSM LITE
python3 scripts/stock_scanner.py  # uses default: ["TSLA"]

Features

• Multi-timeframe resonance: Monthly/Weekly/Daily trend alignment
• MACD analysis: Crossover detection (golden cross/bearish cross) across timeframes
• Volume-price analysis: Identifies volume spikes with price movement
• Support/resistance levels: Auto-calculated key price levels
• Composite scoring: Buy/Sell/Hold signals with detailed reasoning

Signal System

Score	Signal
≥5	💎 Strong Buy
3-4	✅ Buy
-2 to 2	👀 Hold/Watch
-3 to -4	❌ Sell
≤-4	🔴 Strong Sell

Resonance Levels

• 🌟🌟🌟 Perfect resonance (all 3 timeframes aligned)
• 🌟🌟 Dual timeframe resonance
• 👍 Daily/Weekly same direction
• ⚠️ Daily/Weekly conflict

Output Example

See references/sample_output.md for complete output format.

Notes

• Uses yfinance for stock data (no API key needed)
• Data periods: Daily 1y, Weekly 2y, Monthly 5y
• Scores weight: Daily 50%, Weekly 30%, Monthly 20%
• Works best for US stocks with sufficient trading history