agentleFS
SKE-LabsSKE-Labs/agent-trading-skills/skills/technical-strategies/ichimoku-cloud/SKILL.md

ichimoku-cloud

Skill17 starsChanged 4 months agoApache-2.0View on GitHub

Calculate and test correctly shifted Ichimoku components. Use when evaluating price/cloud, TK-cross, Chikou, and cloud-state features without future leakage or confirmation-count scoring.

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

5 rules. About 0 are common, 4 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

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

    line 89
  2. Distinctive:

    Treat inside-cloud status as a testable filter, not a universal prohibition.

    line 97
  3. Very specific:

    Test 9/26/52 and chosen timeframes on the intended session.

    line 98
  4. Distinctive:

    Use cloud edges as candidate coordinates and stop only at thesis invalidation.

    line 99
  5. Distinctive:

    Do not convert component agreement directly into confidence or size.

    line 100

≈ “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

Ichimoku Cloud Trading

Ichimoku Kinko Hyo provides trend, momentum, and S/R in one indicator system.

Components

ComponentFormulaUse
Tenkan-sen(9H + 9L) / 2Fast signal line
Kijun-sen(26H + 26L) / 2Slow signal line
Senkou A(Tenkan + Kijun) / 2, plotted 26 aheadCloud boundary
Senkou B(52H + 52L) / 2, plotted 26 aheadCloud boundary
Chikou SpanClose plotted 26 periods backConfirmation

Cloud (Kumo) Analysis

Cloud ColorMeaning
Green (A > B)Senkou A above Senkou B; bullish-context feature
Red (A < B)Senkou A below Senkou B; bearish-context feature
Thin/thick cloudRelative spread between Senkou spans; test any S/R interpretation

Signals

TK Cross (Tenkan/Kijun)

  • Bullish feature: Tenkan crosses above Kijun; record cloud location as context
  • Bearish feature: Tenkan crosses below Kijun; record cloud location as context

Price vs Cloud

  • Above cloud = bullish bias
  • Below cloud = bearish bias
  • Inside cloud = overlap state; apply the calibrated policy

Chikou Span Confirmation

  • Chikou above price (26 bars ago) = bullish
  • Chikou below price (26 bars ago) = bearish

Component State Checklist

ConditionBullishBearish
Price positionAbove cloudBelow cloud
TK crossBullishBearish
Chikou spanAbove priceBelow price
Cloud aheadGreenRed

These components share the same price history and are not independent votes. Preserve the four states but assign strength only if a calibrated model supports it.

Workflow

  1. Get at least 120 closed candles to calculate components and their plotted shifts:
    get_candles(symbol=<symbol>, exchange=<exchange>, interval=<interval>, count=120)
    Compute rolling highest-high/lowest-low midpoints. Plot Senkou spans 26 bars ahead and Chikou 26 bars back. When backtesting, compare each decision timestamp only with values computable then; never use the future plotted location as future information.
  2. Assess price versus the correctly aligned current cloud, not the unshifted calculations
  3. Record TK cross and Chikou relation as correlated features
  4. Apply the predeclared closed-bar entry and structural invalidation; a line touch is not enough.
  5. Mark on chart:
    draw_chart_analysis(action="create", drawing={
        "type": "support",
        "points": [
            {"time": <start_time>, "price": <kijun_price>},
            {"time": <end_time>, "price": <kijun_price>}
        ],
        "options": {"text": "Kijun Support"}
    })

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 finds results vary by market and testing design; Ichimoku settings and confirmation rules require the same out-of-sample scrutiny.

Key Rules

  • Treat inside-cloud status as a testable filter, not a universal prohibition.
  • Test 9/26/52 and chosen timeframes on the intended session; no 4H minimum is universal.
  • Use cloud edges as candidate coordinates and stop only at thesis invalidation.
  • Do not convert component agreement directly into confidence or size.

Related Skills

  • multi-timeframe-analysis — Ichimoku across timeframes for alignment
  • moving-average-crossover — TK cross is analogous to MA crossovers; combine for confirmation

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.