Skip to content
Get packs

Guide · Agent skill

How to use the Technical Indicator Signal Engine agent skill

Updated · written with AI from the project's own documentation and checked against our catalogue data

The technical-basic skill gives an AI agent a ready-made set of classic chart indicators (EMA, ADX, Bollinger Bands, RSI, OBV and a volume ratio) that it can compute on price data you supply. It combines them by simple voting into one composite signal: 1 for long, -1 for short, or 0 to stand aside. This guide explains what agent skills are, how to install this one, how to ask for it in plain language, and where it should and should not be used.

Technical Indicator Signal EngineHKUDS/Vibe-Trading · MIT

Quick start

  1. 1Download the ZIP. Download the technical-basic ZIP file from this page.
  2. 2Unzip into the skills folder. Unzip it into ~/.claude/skills/ for personal use, or into .claude/skills/ inside a project.
  3. 3Or upload in the Claude apps. In the Claude apps, go to Settings → Capabilities → Skills and upload the skill.
  4. 4Install Python dependencies. Run pip install pandas numpy requests in your environment.
  5. 5Provide OHLCV data. Give the agent a dataset with open, high, low, close and volume values.
  6. 6Ask in plain language. Request the composite signal or specific indicators and describe the output you want.
  7. 7Review the vote. Check the individual indicator values to understand why the signal is 1, -1 or 0.

What is an agent skill and what does this one do?

An agent skill is a folder of instructions and supporting files that an AI agent can load when a task matches the skill's description. This skill is documented in a SKILL.md file and ships with an example script, example_signal_engine.py.

Once installed, the agent can calculate three groups of indicators on open, high, low, close and volume data: trend (EMA 12/26 and ADX 14), mean reversion (Bollinger Bands 20,2 and RSI 14) and volume-price (OBV and a volume ratio). Each group votes, and the combined result is returned as a signal.

  • Long (1): trend is bullish, RSI is not overbought and OBV is rising.
  • Short (-1): trend is bearish, RSI is not oversold and OBV is falling.
  • Stand aside (0): the signals are mixed.

Install the technical-basic skill

You can install the skill in either of two ways. Download the ZIP file from this page and then choose the option that fits your setup.

For a personal setup, unzip the download into ~/.claude/skills/. To limit the skill to one project, unzip it into the .claude/skills/ folder inside that project. Alternatively, in the Claude apps, open Settings, go to Capabilities and upload the skill under Skills.

  • Personal: unzip into ~/.claude/skills/
  • Single project: unzip into .claude/skills/ in the project folder
  • Claude apps: Settings → Capabilities → Skills, then upload

Install the Python dependencies

The skill needs Python with pandas, numpy and requests. The source lists requests in the install instructions, but the shown script excerpt does not use it. Install the dependencies with the command below.

pip install pandas numpy requests

How do you trigger the skill with a natural request?

You do not need a special command. Describe the task in plain words and give the agent your price data. The agent decides to use the skill when your request matches its description, which covers composite technical signals from OHLCV data.

Good requests name the data, the indicators or the output you want. For example, you might ask the agent to compute the composite signal for a CSV of daily closes and volumes, or to show the RSI and Bollinger Band values before giving the signal.

  • Compute the technical indicator signal for this OHLCV file and tell me the latest value.
  • Run the trend, mean-reversion and volume checks on this data and explain the vote.
  • Use the technical-basic skill to add EMA, ADX and RSI columns to my dataframe.

How can you tune the indicators?

All parameters have defaults and can be overridden when the engine is created. Common overrides are the EMA periods, the ADX threshold, the RSI oversold and overbought levels, and the Bollinger Band standard deviation multiplier. Use this to test variations or to match a particular trading convention you are studying.

  • ema_fast 12, ema_slow 26
  • adx_period 14, adx_threshold 25.0
  • bb_window 20, bb_std 2.0
  • rsi_period 14, rsi_oversold 30, rsi_overbought 70
  • vol_ma_period 20, obv_ma_period 20

Safety notes: scripts and network

This skill runs scripts. It does not use the network, according to its listing, so it only computes on data you provide. It does not place orders or connect to a broker. Read example_signal_engine.py before running it on sensitive files, as you would with any script.

The signals are outputs of a fixed formula, not advice. The source shows no performance evidence for this three-indicator vote, and markets change. Do not trade real money on these signals without your own testing.

Tips for getting useful results

Supply clean OHLCV data with consistent timestamps and no gaps you have not accounted for. The indicators are built for price and volume series, so do not feed them other kinds of time series. Keep the default parameters as a baseline, then change one thing at a time so you can see what each change does.

  • Check that your data includes open, high, low, close and volume columns.
  • Compare the composite signal against the individual indicator values to understand the vote.
  • Backtest on data outside the period you used to choose parameters.

What people use it for

  • Computing a baseline composite signal on a stock's daily OHLCV history to use as a starting point for a backtest.
  • Adding EMA, ADX, RSI and Bollinger Band columns to a pandas dataframe for analysis.
  • Studying how OBV and the volume ratio are computed from price and volume data.
  • Testing how changing the RSI thresholds or ADX threshold changes the signal output.
  • Teaching students how EMA, ADX, RSI, Bollinger Bands and OBV are calculated.

Frequently asked questions

Is the technical-basic skill free to use?

The skill is published under the MIT licence, as stated on this page. Check the licence file in the source repository for full terms before reuse.

What do I need to run the technical-basic skill?

You need Python with pandas, numpy and requests installed, plus OHLCV price data (open, high, low, close, volume) that you supply. The skill runs scripts and does not use the network.

How do I install the technical-basic agent skill?

Download the ZIP from this page and unzip it into ~/.claude/skills/ for personal use or into .claude/skills/ in a project. In the Claude apps, you can instead upload it under Settings → Capabilities → Skills.

Does the skill place trades or connect to my broker?

No. The skill only computes signals from data you provide and does not place orders. It is not designed for live trading or broker execution.

Are the signals profitable?

The source gives no performance evidence for this fixed three-indicator vote. Treat the output as a transparent baseline to test, not a source of reliable profit.

What are the alternatives to this skill?

Any pandas-based indicator library or your own calculation of EMA, ADX, RSI, Bollinger Bands and OBV can do similar work. This skill is useful mainly because its indicators and voting logic are short and easy to read.

New agent skills, repos and AI tools — every week

The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.

Our verdict

Choose this skill if you want a transparent, readable baseline of classic indicators and a simple composite vote to test, extend or learn from. Skip it if you need reliable profits, live trading or broker execution, or if your data is not price and volume history, since its performance is unproven here and it only computes signals.

Download the skill