agentsclimarketplace

Alphameta technical

Skill intelliscale/alphameta-skills/skills/alphameta-technical

AlphaMeta is an IBKR (Interactive Brokers) trading tool providing real-time market data for stocks, options, futures, and crypto via a standardized REST API.

Install
npx -y skills add intelliscale/alphameta-skills --skill alphameta-technical

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Price technical indicators via AlphaMeta — MACD, RSI, KDJ, Bollinger Bands, EMA crossover, ADX, ATR, OBV computed from OHLCV kline data. Use when: "MACD", "RSI", "KDJ", "布林带", "布林", "ADX", "ATR", "OBV", "技术指标", "金叉", "死叉", "超买", "超卖".

SKILL.md

3.2 KB, as published. Nobody here has run it

AlphaMeta Technical

Response language: match the user's input language (Simplified Chinese / Traditional Chinese / English).

See the alphameta skill for server setup and command execution syntax.


Workflow

When the user asks for technical analysis on a symbol:

  1. Fetch 252 daily kline data and save to a temp file
  2. Compute 8 indicators via inline Python + pandas
  3. Present results — composite buy/sell/neutral signal with indicator details

Step 1: Fetch kline

curl -X POST "http://127.0.0.1:18080/api/v1/execute" \
  -H "Content-Type: application/json" \
  -d '{"cmd": "kline <SYMBOL> day 252"}' \
  > /tmp/<SYMBOL>_kline.json

Reuse the saved file on subsequent calls. Only re-fetch if the user requests a different symbol, timeframe, or explicitly asks for fresh data.

Step 2: Compute indicators

Run the inline Python script from references/technical.md against the saved kline data. The script computes 8 indicators, votes each ±1/0, and outputs a JSON result.

Step 3: Format output

IndicatorValueSignal
MACDhist valueBullish/Neutral/Bearish
RSI(14)numericOversold/Neutral/Overbought
KDJnumericOversold/Neutral/Overbought
Bollingerprice positionOversold/Neutral/Overbought
EMA 50/200alignmentBullish/Bearish
ADX(14)numericTrending/Choppy
ATR(14)numericExpanding/Normal/Contracting
OBVnumericInflow/Outflow
Compositetotal: NBuy/Sell/Neutral

Always cite the data source: AlphaMeta / Interactive Brokers.


Indicator Reference

IndicatorParametersBullish SignalBearish Signal
MACD(12, 26, 9)Histogram rising & positiveHistogram falling & negative
RSI14< 30 (oversold)> 70 (overbought)
KDJ(9, 3, 3)J < 20J > 80
Bollinger(20, 2)Price < lower bandPrice > upper band
EMA cross50 / 20050 above 200 (golden cross)50 below 200 (death cross)
ADX14ADX > 25 & DI+ > DI-ADX > 25 & DI- > DI+
ATR14Expanding (>1.1× SMA)Contracting (<0.9× SMA)
OBV5-dayOBV risingOBV falling
  • 7 directional indicators vote +1 / 0 / -1; ATR (vote=0) provides non-directional volatility context
  • Composite: ≥ +3 → Buy, ≤ -3 → Sell, otherwise → Neutral

Error Handling

SituationResponse
error.code == "COMMAND_ERROR"Surface error.message verbatim
File /tmp/<SYMBOL>_kline.json not foundRe-run step 1 to fetch the data first
No data returnedSymbol may not support historical data; try a different symbol
Insufficient history (< 60 bars)Request more periods with kline <SYMBOL> day 500
ModuleNotFoundError: pandasRun pip install pandas

Reference

For the complete Python code and detailed workflow, see references/technical.md.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.