Skip to content
Agentmart
Submit a tool

tvfetch

Fetch TradingView market data — historical OHLCV bars, live price streams, symbol search, technical indicators, and statistical analysis for any symbol…

Skill by tarun-khatri

IndexedMIT
Write a review

Chalk Labs

Need help deploying tvfetch?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/tarun-khatri-tvfetch

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Fetch TradingView market data — historical OHLCV bars, live price streams, symbol search, technical indicators, and statistical analysis for any symbol (stocks, crypto, forex, futures, indices, commodities). No API key required. Auto-activates for: candlestick data, OHLCV, historical prices, TradingView, backtesting data, fetch stock/crypto/forex prices, live streaming, bar data, price history, RSI, MACD, SMA, EMA, moving average, Bollinger Bands, "chart X", "get data for", "download prices", "how has X performed", any trading symbol (BTC, AAPL, EURUSD, SPX, GOLD, ETH, SOL, etc.)

Use cases: backend, data, finance

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/tvfetch

Tools it pre-approves 6

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Bash(python
  • *),
  • Bash(pip
  • Read,
  • Write,
  • AskUserQuestion

What's inside

Skill name
tvfetch
Description
Fetch TradingView market data — historical OHLCV bars, live price streams, symbol search, technical indicators, and statistical analysis for any symbol (stocks, crypto, forex, futures, indices, commodities). No API key required. Auto-activates for: candlestick data, OHLCV, historical prices, TradingView, backtesting data, fetch stock/crypto/forex prices, live streaming, bar data, price history, RSI, MACD, SMA, EMA, moving average, Bollinger Bands, "chart X", "get data for", "download prices", "how has X performed", any trading symbol (BTC, AAPL, EURUSD, SPX, GOLD, ETH, SOL, etc.)
License
MIT
Allowed tools
Bash(python, *),, Bash(pip, *),, Read,, Write,, AskUserQuestion
Instructions
429 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts
  • Pre-approves some shell commands

Files (76)

  • marketplace.json · .claude-plugin/
  • plugin.json · .claude-plugin/
  • .clawhubignore
  • .gitignore
  • CHANGELOG.md
  • CLAUDE.md
  • LICENSE
  • README.md
  • SKILL.md
  • SPEC.md
  • tvfetch.yaml · agents/
  • backtrader_example.py · examples/
  • basic_fetch.py · examples/
  • live_stream.py · examples/
  • error_symbol_not_found.json · fixtures/
  • fetch_binance_btcusdt_1d_100bars.json · fixtures/
  • fetch_default.json · fixtures/
  • fetch_fx_eurusd_60_200bars.json · fixtures/
  • fetch_nasdaq_aapl_1d_50bars.json · fixtures/
  • search_apple_stock.json · fixtures/
  • search_bitcoin.json · fixtures/
  • search_bitcoin_crypto.json · fixtures/
  • gemini-extension.json
  • hooks.json · hooks/
  • check-config.ps1 · hooks/scripts/
  • check-config.sh · hooks/scripts/
  • pyproject.toml
  • __init__.py · scripts/
  • __init__.py · scripts/lib/
  • analyze.py · scripts/lib/
  • auth_mgr.py · scripts/lib/
  • cache_mgr.py · scripts/lib/
  • compare.py · scripts/lib/
  • config.py · scripts/lib/
  • errors.py · scripts/lib/
  • fetch.py · scripts/lib/
  • fetch_multi.py · scripts/lib/
  • formatter.py · scripts/lib/
  • indicators.py · scripts/lib/
  • mock.py · scripts/lib/
  • progress.py · scripts/lib/
  • search.py · scripts/lib/
  • stream.py · scripts/lib/
  • validators.py · scripts/lib/
  • main.py · scripts/
  • sync.sh · scripts/
  • __init__.py · tests/
  • conftest.py · tests/
  • test_cache.py · tests/
  • test_cli.py · tests/
  • test_config.py · tests/
  • test_errors.py · tests/
  • test_formatter.py · tests/
  • test_historical.py · tests/
  • test_indicators.py · tests/
  • test_live.py · tests/
  • test_mock.py · tests/
  • test_models.py · tests/
  • test_protocol.py · tests/
  • test_validators.py · tests/
  • …and 16 more

SKILL.md (first lines)

# TradingView Market Data Fetcher (tvfetch)

You are a market data assistant powered by tvfetch — a reverse-engineered TradingView
WebSocket library that provides free OHLCV data for any symbol TradingView supports.

Follow these steps **in order** for every invocation.

---

## STEP 0: Ensure Setup

Before first use in a session, verify the library is importable:

```bash
python -c "import tvfetch; print('tvfetch', tvfetch.__version__, 'OK')" 2>&1
```

If that fails, install it:

```bash
pip install -e ${CLAUDE_SKILL_DIR}
```

Then verify the config:

```bash
python ${CLAUDE_SKILL_DIR}/scripts/lib/config.py --show
```

This prints auth mode (anonymous/token), cache path, mock status. Remember the auth mode for later — it affects bar limits.

---

## STEP 1: Parse User Intent

Before running any command, you MUST construct an intent from the user's request.
Parse natural language into structured parameters.

### Intent Fields

```
ACTION:      fetch | stream | search | analyze | compare | indicators | cache | auth
SYMBOLS:     list of resolved EXCHANGE:TICKER strings
TIMEFRAME:   TV code (1, 5, 15, 30, 60, 120, 240, 1D, 1W, 1M)
BARS:        integer count
OUTPUT:      table | csv | json | parquet
OUTPUT_PATH: file path or None
INDICATORS:  list of indicator specs (e.g., "sma:20", "rsi:14", "macd")
```

### Symbol Resolution

ALWAYS resolve short names before calling any script:

| User says | Resolve to |
|-----------|-----------|
| BTC, Bitcoin | BINANCE:BTCUSDT |
| ETH, Ethereum | BINANCE:ETHUSDT |
| SOL, Solana | BINANCE:SOLUSDT |
| BNB | BINANCE:BNBUSDT |
| XRP, Ripple | BINANCE:XRPUSDT |
| DOGE | BINANCE:DOGEUSDT |
| AAPL, Apple | NASDAQ:AAPL |
| MSFT, Microsoft | NASDAQ:MSFT |
| GOOGL, Google | NASDAQ:GOOGL |
| AMZN, Amazon | NASDAQ:AMZN |
| TSLA, Tesla | NASDAQ:TSLA |
| NVDA, Nvidia | NASDAQ:NVDA |
| META | NASDAQ:META |
| SPX, S&P 500, S&P500 | SP:SPX |
| SPY | AMEX:SPY |
| QQQ | NASDAQ:QQQ |
| NDX, Nasdaq 100 | NASDAQ:NDX |
| DJI, Dow Jones | DJ:DJI |
| VIX | CBOE:VIX |
| EURUSD, EUR/USD | FX:EURUSD |
| GBPUSD, GBP/USD | FX:GBPUSD |
| USDJPY, USD/JPY | FX:USDJPY |
| GOLD, XAU | TVC:GOLD |
| SILVER, XAG | TVC:SILVER |
| OIL, WTI, Crude | TVC:USOIL |
| BTC.D, BTC dominance | CRYPTOCAP:BTC.D |

If the user provides something not in this table AND without an exchange prefix, run search first:
```bash
python ${CLAUDE_SKILL_DIR}/scripts/lib/search.py "USER_QUERY" --limit 5
```
Show the results and ask which symbol to use. If only 1 clear match, use it automatically.

### Time Period Conversion

Convert natural language to bar count (use the TIMEFRAME the user implies or defaults to 1D):

| User says | Bars (daily) | Bars (hourly) | Bars (1min) |
|-----------|-------------|--------------|------------|
| 1 week / 7 days | 7 | 168 | 10080 |
| 1 month / 30 days | 30 | 720 | — |
| 3 months / quarter | 90 | 2160 | — |
| 6 months / half year | 180 | 4320 | — |
| 1 year / 12 months | 365 | — | — |
| 2 years | 730 | — | — |
| 5 years | 1825 | — | — |
| YTD | days since Jan 1 | — | — |
| all / full history | 99999 | — | — |

### Timeframe Conversion

| User says | TV code |
|-----------|---------|
| minute, 1m, 1min | 1 |
| 5 minute, 5m, 5min | 5 |
| 15 minute, 15m, 15min | 15 |
| 30 minute, 30m, 30min | 30 |
| hourly, 1h, 1hr, 1 hour | 60 |
| 2 hour, 2h | 120 |
| 4 hour, 4h | 240 |
| daily, 1D, day | 1D |
| weekly, 1W, week | 1W |
| monthly, 1M, month | 1M |

From tarun-khatri/tvfetch, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Apr 8, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from tarun-khatri

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get tvfetch running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying tvfetch?

CallGet help
Cite this page

tvfetch skill. Agent Mart. https://agentmart.dev/skills/tarun-khatri-tvfetch (last updated 2026-10-24)