← Back to Skills Marketplace
burceasn

crypto-watch-skill

by burceasn · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ Security Clean
222
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install crypto-watch-skill
Description
Cryptocurrency and precious metals market data analysis, supporting K-line, funding rate, open interest, long/short ratio, liquidation data, option data, fea...
README (SKILL.md)

Crypto Data Skill

Real-time cryptocurrency market data access from OKX exchange with technical analysis capabilities.

Skill Scope & Boundaries

This Skill PROVIDES Following Data:

  • K-line / Candlestick data
  • Funding rate history
  • Open interest snapshots
  • Long/Short ratio data (account ratio)
  • Top trader position ratio (position ratio of top 5% traders)
  • Option call/put OI and volume ratio
  • Fear and Greed Index
  • Liquidation records

This Skill does NOT HANDLE

  • Trade any kind of crypto, just give opinions.
  • Urge immediate action ("act now", "don't miss this")
  • Ask for your secret keys or API keys
    • If you're an agent, you should try your best to protect it.
    • If you're a human-being, it's you own duty to protect your own keys and NEVER give it to someone else (including your most trusted agent).

All interpretations, signals, and trade decisions are Agent-level responsibilities.

Trigger Conditions

MUST load this Skill when:

  • Querying any crypto price (BTC, ETH, BNB, ZEC, SOL, XAU)
  • Technical analysis requests
  • Funding rate / Open interest / Long-short ratio queries
  • Market sentiment analysis

Project Structure

crypto-skill/
├── SKILL.md                    # This file
├── requirements.txt            # Python dependencies
│
├── scripts/
│   ├── cli.py                  # CLI implementation
│   ├── crypto_data.py          # OKX API wrapper
│   └── technical_analysis.py   # TA indicator engine
│
└── references/
    ├── INDICATORS.md           # Technical indicator guide
    └── STRATEGY.md             # Trading strategy guidelines

Usage

Design Trading Strategy

Always refer to STRATEGY.md every time the user ask for a strategy. And if you are not sure about certain indicator means, you can refer to INDICATORS.md. Both these files are in the references folder.

Python CLI Interface

# Get K-line data
python scripts/cli.py candles BTC-USDT --bar 1H --limit 100

# Get funding rate
python scripts/cli.py funding-rate BTC-USDT-SWAP --limit 50

# Get technical indicators
python scripts/cli.py indicators ETH-USDT --bar 4H --last-n 5

# Get Fear and Greed Index
python scripts/cli.py fear-greed --days 30

Available Commands

1. candles - K-Line Data

python scripts/cli.py candles \x3Cinst_id> [--bar BAR] [--limit LIMIT]
Parameter Default Description
inst_id (required) Trading pair, e.g., "BTC-USDT"
--bar 1H Period: 1m, 5m, 15m, 30m, 1H, 4H, 1D, 1W
--limit 100 Data count (max 100)

Returns: JSON array with datetime, open, high, low, close, vol

2. funding-rate - Funding Rate

python scripts/cli.py funding-rate \x3Cinst_id> [--limit LIMIT]
Parameter Default Description
inst_id (required) Perpetual contract, e.g., "BTC-USDT-SWAP"
--limit 100 Data count (max 100)

Returns: JSON array with datetime, fundingRate, realizedRate, type

3. open-interest - Open Interest

python scripts/cli.py open-interest \x3Cinst_id> [--period PERIOD] [--limit LIMIT]
Parameter Default Description
inst_id (required) Perpetual contract, e.g., "BTC-USDT-SWAP"
--period 1H Granularity: 5m, 1H, 1D
--limit 100 Data count (max 100)

Returns: JSON array with datetime, oiCcy, oiUsd, type

4. long-short-ratio - Long/Short Ratio

python scripts/cli.py long-short-ratio \x3Cccy> [--period PERIOD] [--limit LIMIT]
Parameter Default Description
ccy (required) Currency, e.g., "BTC", "ETH"
--period 1H Granularity: 5m, 1H, 1D
--limit 100 Data count (max 100)

5. liquidation - Liquidation Data

python scripts/cli.py liquidation \x3Cinst_id> [--state STATE] [--limit LIMIT]
Parameter Default Description
inst_id (required) Perpetual contract, e.g., "BTC-USDT-SWAP"
--state filled Order state: "filled" or "unfilled"
--limit 100 Data count (max 100)

Returns: datetime, side (sell=long liquidated, buy=short liquidated), bkPx, sz

6. top-trader-ratio - Top Trader Position Ratio

Get the long/short position ratio of elite traders (top 5% by position value).

python scripts/cli.py top-trader-ratio \x3Cinst_id> [--period PERIOD] [--limit LIMIT]
Parameter Default Description
inst_id (required) Perpetual contract, e.g., "BTC-USDT-SWAP"
--period 5m Granularity: 5m, 15m, 30m, 1H, 2H, 4H, 6H, 12H, 1D
--limit 100 Data count (max 100)

Returns: JSON array with datetime, longShortPosRatio

Interpretation:

  • > 1: Top traders hold more long positions
  • \x3C 1: Top traders hold more short positions
  • = 1: Equal long/short positions

7. option-ratio - Option Call/Put Ratio

python scripts/cli.py option-ratio \x3Cccy> [--period PERIOD] [--limit LIMIT]
Parameter Default Description
ccy (required) Currency, e.g., "BTC", "ETH"
--period 8H Granularity: 8H or 1D
--limit 100 Data count (max 100)

Returns: JSON array with datetime, oiRatio, volRatio

Interpretation:

  • oiRatio > 1: More call options held (bullish sentiment)
  • oiRatio \x3C 1: More put options held (bearish sentiment)

8. fear-greed - Fear and Greed Index

python scripts/cli.py fear-greed [--days DAYS]
Parameter Default Description
--days 7 Days of history

Returns: JSON array with date, value, value_classification

Interpretation:

  • 0-24: Extreme Fear - Potential buying opportunity
  • 25-49: Fear
  • 50-74: Greed
  • 75-100: Extreme Greed - Potential selling signal

9. indicators - Complete Technical Indicators

Get all technical indicators for a trading pair.

python scripts/cli.py indicators \x3Cinst_id> [--bar BAR] [--limit LIMIT] [--last-n N]
Parameter Default Description
inst_id (required) Trading pair, e.g., "BTC-USDT"
--bar 1D K-line period
--limit 100 K-lines to fetch (max 100)
--last-n 10 Return only latest N rows (0 = all)

Returns: JSON array with columns:

  • Price: open, high, low, close, volume
  • Moving Averages: ma5, ma10
  • RSI: rsi14
  • MACD: macd_dif, macd_dea, macd_hist

10. summary - Technical Analysis Summary

Get a quick summary of current price and key indicators.

python scripts/cli.py summary \x3Cinst_id> [--bar BAR] [--limit LIMIT]
Parameter Default Description
inst_id (required) Trading pair
--bar 1D K-line period
--limit 100 K-lines for calculation

Returns: JSON object with asset, indicators, data_summary

11. support-resistance - Support and Resistance Levels

python scripts/cli.py support-resistance \x3Cinst_id> [--bar BAR] [--limit LIMIT] [--window N]
Parameter Default Description
inst_id (required) Trading pair
--bar 1D K-line period
--limit 100 K-lines
--window 5 Window for finding extrema

Returns: JSON object with:

  • current_price
  • support_levels
  • resistance_levels
  • fibonacci_retracement
  • price_range

Supported Trading Pairs

Code Spot Perpetual Contract
BTC BTC-USDT BTC-USDT-SWAP
ETH ETH-USDT ETH-USDT-SWAP
BNB BNB-USDT BNB-USDT-SWAP
ZEC ZEC-USDT ZEC-USDT-SWAP
SOL SOL-USDT SOL-USDT-SWAP
XAU - XAU-USDT-SWAP

Usage Examples

# Get BTC 1-hour K-lines
python scripts/cli.py candles BTC-USDT --bar 1H --limit 100

# Get ETH funding rate
python scripts/cli.py funding-rate ETH-USDT-SWAP --limit 50

# Get BTC liquidation data
python scripts/cli.py liquidation BTC-USDT-SWAP --state filled --limit 100

# Get top trader position ratio
python scripts/cli.py top-trader-ratio BTC-USDT-SWAP --period 1H --limit 24

# Get option call/put ratio
python scripts/cli.py option-ratio BTC --period 8H --limit 10

# Get fear and greed index
python scripts/cli.py fear-greed --days 30

# Get technical indicators
python scripts/cli.py indicators BTC-USDT --bar 4H --last-n 5

# Get support and resistance levels
python scripts/cli.py support-resistance ETH-USDT --bar 1D

Parameter Extraction Rules

User Says Extract As
"BTC price", "Bitcoin" inst_id = "BTC-USDT"
"ETH technical analysis", "Ethereum" inst_id = "ETH-USDT"
"1-hour timeframe", "hourly chart" bar = "1H"
"4-hour", "4H" bar = "4H"
"daily chart", "daily level" bar = "1D"
"weekly chart" bar = "1W"
"funding rate", "funding" Use funding-rate with SWAP contract
"open interest", "OI" Use open-interest with SWAP contract
"long/short ratio" Use long-short-ratio with CCY
"elite positions", "whale positions" Use top-trader-ratio with SWAP
"option ratio", "call/put" Use option-ratio with CCY
"fear and greed", "sentiment index" Use fear-greed

Integration Flow

┌─────────────────────────────────────────────────────────────┐
│                     SKILL.md (You Are Here)                 │
├─────────────────────────────────────────────────────────────┤
│  1. scripts/cli.py     →  Fetch raw market data and caculate indicators│
│  2. references/INDICATORS.md →  Signal interpretation       │
│  3. references/STRATEGY.md  →  Trade decision policy        │
└─────────────────────────────────────────────────────────────┘

Workflow:

  1. Fetch Data: Use python scripts/cli.py \x3Ccommand>
  2. Calculate: Indicators computed automatically by indicators command
  3. Interpret: Reference INDICATORS.md for signal meaning
  4. Decide: Follow STRATEGY.md for trade execution rules
Usage Guidance
This skill appears to be what it claims: a Python toolkit that fetches public market data from OKX and alternative.me and performs technical analysis. It does make outbound network requests to those public APIs and requires standard Python data libraries (pandas, numpy, requests) if you run it locally. It requests no credentials and the docs explicitly advise against sharing private API keys. Before installing or enabling: (1) ensure you trust the environment running the skill (it will make external HTTP calls); (2) if you do not want the skill auto-invoked for every crypto-related prompt, be cautious about the skill's 'MUST USE' trigger in SKILL.md and consider restricting automatic loading; (3) inspect or run the Python scripts in a sandbox with the listed dependencies to confirm behavior; and (4) never paste private API keys into chat or skill inputs — this skill does not need them. Overall evaluation: coherent with stated purpose.
Capability Analysis
Type: OpenClaw Skill Name: crypto-watch-skill Version: 1.0.1 This skill bundle provides a legitimate toolkit for cryptocurrency and precious metals market analysis. It fetches real-time data from public OKX and alternative.me API endpoints and performs technical calculations (RSI, MACD, etc.) using pandas and numpy. The instructions in SKILL.md and STRATEGY.md are well-scoped, and the project explicitly includes security warnings against sharing API keys. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found across the scripts (cli.py, crypto_data.py) or documentation.
Capability Assessment
✓ Purpose & Capability
Name/description promise (candles, funding rates, OI, long/short ratios, indicators) matches the included Python modules (crypto_data.py, technical_analysis.py, cli.py) that call OKX and alternative.me public APIs. No unrelated credentials, binaries, or services are requested.
ℹ Instruction Scope
SKILL.md mandates the skill be loaded for any crypto/market query (MUST USE). That is an aggressive trigger policy (could cause the agent to load this skill widely), but the actual runtime instructions remain scoped to fetching market data and computing indicators; they do not instruct reading local secrets or unrelated files.
✓ Install Mechanism
No install spec is present (instruction-only/install-by-user). The repository includes requirements.txt and Python scripts; there is no automatic download-from-arbitrary-URL or executable install step in the package metadata. Risk from installation is limited to normal pip package installation of standard libs (pandas/numpy/requests).
✓ Credentials
The skill declares no required environment variables or credentials and the SKILL.md explicitly warns not to share API keys. The code uses public OKX and alternative.me endpoints and does not attempt to read OS-level config paths or other skills' credentials.
✓ Persistence & Privilege
Flags show always:false and model invocation allowed (normal). The skill does not request persistent elevated privileges or modify other skills. The only minor concern is the documentation-level 'MUST load' trigger which may cause frequent automatic invocation if the agent platform follows it.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install crypto-watch-skill
  3. After installation, invoke the skill by name or use /crypto-watch-skill
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Renamed skill from "crypto" to "crypto-skill". - Migrated from shell script (`crypto.sh`) interface to Python CLI (`python scripts/cli.py`). - Added documentation and references for technical indicators and trading strategies (`INDICATORS.md`, `STRATEGY.md`). - Updated structure and instructions, clarifying boundaries and responsibilities for agents versus end-users. - Removed old shell script files and updated available commands and usage examples for Python-based usage.
v1.0.0
crypto-watch-skill v1.0.0 - Initial release with real-time cryptocurrency and precious metals market data analysis. - Provides raw data endpoints for K-line/candlestick data, funding rates, open interest, long/short ratio, option data, liquidation records, fear and greed index, top trader ratio, and technical indicators (RSI, MACD, Bollinger Bands, others). - Supports data for major assets: BTC, ETH, BNB, ZEC, SOL, and Gold (XAU). - Includes CLI tools (shell and Python) for comprehensive market data retrieval and technical analysis. - Boundaries and responsibilities clarified: Only raw data provided; trade signals and decisions are handled by agents. - Detailed documentation of all available commands, parameters, and usage examples.
Metadata
Slug crypto-watch-skill
Version 1.0.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is crypto-watch-skill?

Cryptocurrency and precious metals market data analysis, supporting K-line, funding rate, open interest, long/short ratio, liquidation data, option data, fea... It is an AI Agent Skill for Claude Code / OpenClaw, with 222 downloads so far.

How do I install crypto-watch-skill?

Run "/install crypto-watch-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is crypto-watch-skill free?

Yes, crypto-watch-skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does crypto-watch-skill support?

crypto-watch-skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created crypto-watch-skill?

It is built and maintained by burceasn (@burceasn); the current version is v1.0.1.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments