agentleFS
SKE-LabsSKE-Labs/agent-trading-skills/skills/day-trading/range-trading/SKILL.md

range-trading

Skill17 starsChanged 4 months agoApache-2.0View on GitHub

Define and test trades near objective range boundaries. Use when measuring range width versus ATR/costs, rejection triggers, breakout invalidation, and target logic without inferring accumulation.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No clear HH/HL or LH/LL structure

    line 19
  2. Distinctive:

    Use ADX level/slope as one contextual feature, calibrated to the instrument and timeframe.

    line 40
  3. Distinctive:

    Buy at support: Wait for rejection candle (hammer, engulfing), stop below support, target resistance

    line 73
  4. Distinctive:

    Sell at resistance: Wait for rejection candle (shooting star, engulfing), stop above resistance, target support

    line 74
  5. Distinctive:

    Treat the setup as a testable hypothesis, not a prediction.

    line 84
  6. Distinctive:

    Treat relative-volume expansion as breakout risk to evaluate, not proof of direction.

    line 95

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Range Trading

Profit from price oscillating between clear support and resistance in non-trending markets.

Identification

Range Characteristics

  • Price bouncing between two levels with 2+ touches each side
  • No clear HH/HL or LH/LL structure
  • Volume decreasing during range
  • Width large enough that the planned payoff exceeds round-trip costs and slippage

Range Quality

FactorStrongWeak
BouncesClean, multiple (3+)Sloppy, few
WidthWide relative to ATR and costsToo narrow after costs
DurationMulti-day/weekFew hours
VolumeLow, stableErratic

Workflow

1. Confirm Ranging Regime

get_indicators(indicator_code="dmi", symbol=<symbol>, exchange=<exchange>, interval=<interval>)

Use ADX level/slope as one contextual feature, calibrated to the instrument and timeframe. It does not by itself confirm a range or authorize another strategy.

2. Identify Range Boundaries

get_candles_around_date(symbol=<symbol>, exchange=<exchange>, interval=<interval>, date=<date>)

Find flat support/resistance with 2+ touches each side.

3. Mark Range Levels

draw_chart_analysis(action="create", drawing={
    "type": "support",
    "points": [
        {"time": <first_touch>, "price": <support_level>},
        {"time": <current>, "price": <support_level>}
    ],
    "options": {"text": "Range Support"}
})
draw_chart_analysis(action="create", drawing={
    "type": "resistance",
    "points": [
        {"time": <first_touch>, "price": <resistance_level>},
        {"time": <current>, "price": <resistance_level>}
    ],
    "options": {"text": "Range Resistance"}
})

4. Trade at Boundaries

  • Buy at support: Wait for rejection candle (hammer, engulfing), stop below support, target resistance
  • Sell at resistance: Wait for rejection candle (shooting star, engulfing), stop above resistance, target support
  • Define the boundary band as an ATR- or range-normalized interval fixed before testing
  • Set the target from tested exit logic and require positive payoff after costs; the opposite boundary is a scenario, not a promised destination

5. Report to Orchestrator

Range boundaries, width, number of touches, entry recommendation, stop level, target level. Flag if breakout appears imminent.

Evidence and Validation

  • Treat the setup as a testable hypothesis, not a prediction. Define thresholds, entry, invalidation, and exit before evaluating outcomes.
  • Calibrate on the same instrument, venue, session, and timeframe. Use closed candles and a held-out or walk-forward sample; record every variant tried.
  • Include spread, fees, slippage, borrow or funding, partial fills, and latency. Reject the setup when net expectancy is not positive or depends on one narrow parameter.
  • Return observed inputs, missing data, cost assumptions, entry, invalidation, exit, and a valid, watch, or no-trade status.
  • Research basis: The technical-analysis evidence review supports market-specific testing and warns that rule selection and costs can erase apparent profits.

Key Rules

  • Trade only inside the predeclared boundary band; report no trade in the middle.
  • Define the rejection trigger numerically and use closed bars.
  • Invalidate on the tested close-plus-buffer rule beyond the range, not on a wick.
  • Treat relative-volume expansion as breakout risk to evaluate, not proof of direction.
  • Reject a range whose available width cannot cover costs and the required payoff.

Related Skills

  • breakout-trading -- when the range breaks, switch to breakout strategy
  • momentum-trading -- ADX rising above 25 signals transition from range to trend

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.