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

breakout-trading

Skill17 starsChanged 4 months agoApache-2.0View on GitHub

Define and test closed-bar consolidation breakouts. Use when measuring boundaries, normalized break buffers, relative participation, retests, invalidation, and net execution costs.

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

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Look for tight range with 3+ touches on support/resistance.

    line 30
  2. Distinctive:

    Use the consolidation-height projection as a scenario, not a forecast.

    line 57
  3. Distinctive:

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

    line 65
  4. Distinctive:

    Do not move a stop to breakeven merely because volume declines.

    line 76

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Breakout Trading

Captures explosive moves when price breaks out of consolidation zones or key support/resistance levels.

Identification

Types: Horizontal (flat S/R, 3+ touches), Pattern (triangle/wedge/flag completion), Trendline (trend change signal).

Participation Confirmation

Measure breakout-bar volume against the same instrument's time-of-day baseline or a predeclared rolling median. Treat relative volume, RSI, and MACD as candidate filters to validate, not confidence grades or independent votes. Require a closed bar beyond the level by a volatility- or tick-normalized buffer; do not use future follow-through to label the original entry.

Workflow

1. Identify Consolidation

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

Look for tight range with 3+ touches on support/resistance.

2. Mark the Level

draw_chart_analysis(action="create", drawing={
    "type": "resistance",
    "points": [
        {"time": <first_touch_time>, "price": <level_price>},
        {"time": <current_time>, "price": <level_price>}
    ],
    "options": {"text": "Breakout Level (<price>)"}
})

3. Check Volume and Momentum

get_indicators(indicator_code="mfi", symbol=<symbol>, exchange=<exchange>, interval=<interval>)
get_indicators(indicator_code="rsi", symbol=<symbol>, exchange=<exchange>, interval=<interval>)
get_indicators(indicator_code="macd", symbol=<symbol>, exchange=<exchange>, interval=<interval>)

Record the close-to-level distance in ATR or ticks, relative volume, spread, and momentum progression. Apply only filter thresholds fixed before the evaluation sample.

4. Entry and Target

Use the consolidation-height projection as a scenario, not a forecast. Choose and test one entry rule: closed-bar break or first retest within a predeclared bar window. Put invalidation back inside the range plus the tested buffer; size from that distance and modeled slippage.

5. Report to Orchestrator

Breakout type, volume multiple, entry recommendation, measured move target, stop level, false breakout risk assessment.

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: Opening-range breakout research finds conditional evidence for a specified rule, while the broader technical-analysis review warns about data snooping and costs.

Key Rules

  • Require a closed-bar trigger; a wick alone is not an entry under this rule.
  • Freeze the participation, buffer, retest-window, and invalidation definitions before testing.
  • A close back inside the range invalidates the setup only if that exact rule was specified in advance.
  • Do not move a stop to breakeven merely because volume declines; compare that management rule out of sample.
  • Report valid, watch, or no trade when the trigger, liquidity, or cost gate is missing.

Related Skills

  • momentum-trading -- ride the continuation after consolidation breaks
  • pullback-trading -- time the retest entry after breakout

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.