agentleFS
SKE-LabsSKE-Labs/agent-trading-skills/skills/chart-patterns/channel-trading/SKILL.md

channel-trading

Skill17 starsChanged 4 months agoApache-2.0View on GitHub

Trade within ascending, descending, and horizontal channels. Use when range trading, riding trends with defined boundaries, or finding breakout setups.

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, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Channel Bounce: Wait for price at boundary + reversal candle + RSI divergence via get_indicators(indicator_code="rsi", symbol=<symbol>, …

    line 66
  2. Very specific:

    Channel Breakout: Wait for candle close outside channel.

    line 68
  3. Distinctive:

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

    line 83
  4. Distinctive:

    Stop applying the fade rule after its predeclared closed-bar breakout invalidation.

    line 93

≈ “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

Channel Trading

Channels define parallel price boundaries for trading bounces or anticipating breakouts.

Pattern Structure

Ascending Channel (Bullish)

  • Both lines slope upward — buy at lower line, sell at upper
  • Break below = reversal signal

Descending Channel (Bearish)

  • Both lines slope downward — sell at upper line, cover at lower
  • Break above = reversal signal

Horizontal Channel (Range)

  • Parallel horizontal lines — classic range trading
  • Break either direction = new trend

Workflow

1. Get Swing Point Data

Fetch exact timestamps and prices for swing highs/lows (need 2+ per line):

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

2. Draw the Channel (2 parallel trend lines)

Draw both channel boundaries as separate trend lines in parallel calls:

# Upper channel boundary (connecting swing highs)
draw_chart_analysis(action="create", drawing={
    "type": "trend",
    "points": [
        {"time": <high1_time>, "price": <high1_price>},
        {"time": <high2_time>, "price": <high2_price>}
    ],
    "options": {"text": "Channel R"}
})

# Lower channel boundary (connecting swing lows)
draw_chart_analysis(action="create", drawing={
    "type": "trend",
    "points": [
        {"time": <low1_time>, "price": <low1_price>},
        {"time": <low2_time>, "price": <low2_price>}
    ],
    "options": {"text": "Channel S"}
})

3. Confirm and Enter

Channel Bounce: Wait for price at boundary + reversal candle + RSI divergence via get_indicators(indicator_code="rsi", symbol=<symbol>, exchange=<exchange>, interval=<interval>). Stop beyond boundary.

Channel Breakout: Wait for candle close outside channel. Confirm with get_indicators(indicator_code="mfi", symbol=<symbol>, exchange=<exchange>, interval=<interval>) for volume. Target = channel width projected from breakout. Mark breakout level:

draw_chart_analysis(action="create", drawing={
    "type": "breakout",
    "points": [
        {"time": <break_time>, "price": <break_price>},
        {"time": <target_time>, "price": <break_price>}
    ],
    "options": {"text": "Breakout"}
})

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: Lo, Mamaysky & Wang found that some objectively defined chart patterns contain incremental information, while emphasizing that visual pattern recognition is subjective.

Key Rules

  • Minimum 4 total touch points (2 per line) to validate a channel
  • Trade WITH channel direction: buy support in ascending, sell resistance in descending
  • Channel midline acts as interim S/R — price rejecting at midline signals weakening momentum
  • Stop applying the fade rule after its predeclared closed-bar breakout invalidation.
  • Record incomplete boundary traversals as a feature; do not declare weakening without tested evidence.

Related Skills

  • multi-timeframe-analysis — HTF channels define trend; LTF channels refine entries
  • triangle-patterns — Converging channels become triangles

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.