TV Signal Screener

Screen markets across 6 asset classes using TradingView data. API pre-filters + pandas computed signals. YAML-driven strategies.

Security Scan

The skill's code, install steps, and runtime instructions are consistent with a TradingView-based screener and do not request unnecessary credentials or unusual system access.

Purpose & Capability

Name/description (TradingView screener) align with the included Python scripts and YAML-driven signals. Required packages (tvscreener, pandas, pyyaml) are appropriate for the stated functionality. No environment variables, external credentials, or unrelated binaries are requested.

Instruction Scope

SKILL.md only instructs installing dependencies into a skill-local venv and running the provided scripts. The code operates on local YAML signal files and uses the tvscreener library to fetch market data. One area to be aware of: user-supplied expression signals are evaluated via pandas.eval after lightweight validation — this is expected for the feature but means you should only run expressions/signals from trusted sources.

Install Mechanism

Install uses a provided install.sh to create a local virtual environment and pip-install requirements from scripts/requirements.txt (PyPI packages). This is a standard, traceable install method for Python code; no downloads from arbitrary URLs or archive extraction are performed.

Credentials

The skill declares no required env vars, no primary credential, and no config paths. The runtime code does not attempt to read system credentials or unrelated config files. Dependency on a third-party tvscreener package is expected and proportional.

Persistence & Privilege

The skill does not request always:true and does not modify other skills or global agent settings. It creates a venv inside its directory for its own use, which is normal.

Assessment

This skill appears coherent and implements a YAML-driven TradingView screener that installs dependencies into a local venv and runs Python scripts. Before installing: (1) review and trust the source — there is no homepage and the registry/source metadata is minimal; (2) be aware that the skill depends on the third‑party tvscreener PyPI package (audit that package if you have concerns); (3) only use signal YAML files you trust — expressions are validated but are evaluated via pandas.eval, so untrusted expressions may be risky; (4) run the install and scripts in an isolated environment (container or VM) if you want to limit blast radius. Overall the files and instructions match the stated purpose and request no disproportionate access.

TradingView Screener

Screen stocks, crypto, forex, bonds, futures, and coins using TradingView's market data. Zero auth required.

Setup (Run Once)

Before first use, run the install script to create a venv and install dependencies:

bash skills/tradingview-screener/install.sh

This creates .venv/ inside the skill directory with all required packages.

Execution

All scripts use the skill's own venv:

skills/tradingview-screener/.venv/bin/python3 skills/tradingview-screener/scripts/<script>.py [args]

Windows:

skills/tradingview-screener/.venv/Scripts/python.exe skills/tradingview-screener/scripts/<script>.py [args]

Modes

Mode	Description	Script
Screen	One-time scan with filters, columns, sort	screen.py
Signal	YAML-driven signal detection (pre-filters + computed signals)	signal-engine.py

Quick Start

Screen Mode

skills/tradingview-screener/.venv/bin/python3 skills/tradingview-screener/scripts/screen.py \
  --asset-class stock --limit 20 \
  --filters '[{"field":"MARKET_CAPITALIZATION","op":">","value":1000000000}]' \
  --columns NAME,PRICE,CHANGE_PERCENT,VOLUME \
  --sort-by VOLUME --sort-order desc

Signal Mode

# List available signals
skills/tradingview-screener/.venv/bin/python3 skills/tradingview-screener/scripts/signal-engine.py --list

# Run a signal
skills/tradingview-screener/.venv/bin/python3 skills/tradingview-screener/scripts/signal-engine.py --signal golden-cross

Asset Classes

Class	Screener	Field Enum
stock	StockScreener	StockField
crypto	CryptoScreener	CryptoField
forex	ForexScreener	ForexField
bond	BondScreener	BondField
futures	FuturesScreener	FuturesField
coin	CoinScreener	CoinField

Signal Types (Computed)

Type	Description	Key Params
crossover	Fast field crosses slow field	fast, slow, direction
threshold	Field crosses a value	field, op, value
expression	Pandas expression on DataFrame	expr
range	Field between min/max bounds	field, min, max

Filter Operators

>, >=, <, <=, ==, !=, between (value: [min, max]), isin (value: [...])

Common Stock Fields

NAME, PRICE, CHANGE_PERCENT, VOLUME, MARKET_CAPITALIZATION, SECTOR, SIMPLE_MOVING_AVERAGE_50, SIMPLE_MOVING_AVERAGE_200, RELATIVE_STRENGTH_INDEX_14, MACD_LEVEL_12_26, AVERAGE_VOLUME_30_DAY

Use StockField.search("keyword") in Python to discover more fields (13,000+ available).

Pre-built Signals

Signal	File	Description
Golden Cross	state/signals/golden-cross.yaml	SMA50 above SMA200 (bullish)
Oversold Bounce	state/signals/oversold-bounce.yaml	RSI < 30 + price rising
Volume Breakout	state/signals/volume-breakout.yaml	Volume > 2x avg + momentum

Output Format

**Stock Screener** | 15 results | Sorted by VOLUME desc

| NAME | PRICE | CHANGE_PERCENT | VOLUME |
|------|-------|----------------|--------|
| AAPL | 185.50 | 2.3 | 80000000 |
...

Timeframes

1, 5, 15, 30, 60, 120, 240, 1D, 1W, 1M

Pass --timeframe 60 to apply hourly interval to technical indicators.

References

• API Guide - Screener types, filters, field discovery
• Signals Guide - YAML schema, signal type configs
• Strategy Templates - Pre-built screening strategies
• Field Presets - Common field groups per asset class