agentleFS
SKE-LabsSKE-Labs/agent-trading-skills/skills/technical-strategies/supply-demand-zones/SKILL.md

supply-demand-zones

Skill17 starsChanged 4 months agoApache-2.0View on GitHub

Define and test supply/demand-style base-and-departure candle zones. Use when planning support/resistance hypotheses without inferring unfilled institutional inventory.

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

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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:

    Treat retest count as a feature.

    line 33
  2. Distinctive:

    Wait for price to enter zone, look for rejection candle (pin bar, engulfing), enter on confirmation

    line 41
  3. Distinctive:

    Use LTF to find order block or FVG within the zone for tighter stop

    line 44
  4. Distinctive:

    Check for oversold/overbought at zone.

    line 69
  5. Distinctive:

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

    line 75
  6. Distinctive:

    Treat the construct as a support/resistance zone, not unfilled institutional orders.

    line 85
  7. Distinctive:

    Test retest age/count and lower-timeframe refinement for incremental net value.

    line 86
  8. Distinctive:

    Keep broken, never-retested, and expired zones in the denominator.

    line 87

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Supply & Demand Zone Trading

Supply/demand zones are candle-range heuristics around a base before a directional departure. OHLC data alone does not reveal institutional accumulation, distribution, or resting inventory.

Zone Identification

Demand Zone (Buy Area)

  • Price dropped, formed a base under a predeclared bar/range rule, then rallied by a normalized departure threshold
  • Zone = the consolidation base before the rally (draw from base low to base high)

Supply Zone (Sell Area)

  • Price rallied, formed a base under the same rule, then dropped by a normalized threshold
  • Zone = the consolidation base before the drop (draw from base high to base low)

Zone Quality

FactorStrong ZoneWeak Zone
DepartureLarge/small ATR-normalized move over fixed bars
Time at baseBar count and range/ATR
RetestsCount, depth, and age
ContextObjective higher-timeframe state

Treat retest count as a feature. Estimate first and later retest outcomes with a fixed expiry; do not assume monotonic weakening.

Entry Strategies

Set & Forget

  • Limit order at zone edge, stop beyond opposite edge

Confirmation Entry

  • Wait for price to enter zone, look for rejection candle (pin bar, engulfing), enter on confirmation

Refined Zone Entry

  • Use LTF to find order block or FVG within the zone for tighter stop

Workflow

  1. Get candle data on HTF (4H/Daily) to identify zones:
    get_candles_around_date(symbol=<symbol>, exchange=<exchange>, interval=<interval>, date=<date>)
  2. Mark zones on chart:
    draw_chart_analysis(action="create", drawing={
        "type": "demand",
        "points": [
            {"time": <zone_start_time>, "price": <zone_top>},
            {"time": <zone_end_time>, "price": <zone_bottom>}
        ],
        "options": {"text": "Fresh Demand Zone"}
    })
  3. Confirm with indicators:
    get_indicators(indicator_code="rsi", symbol=<symbol>, exchange=<exchange>, interval=<interval>)
    Check for oversold/overbought at zone.
  4. Wait for price to return to zone. Enter with confirmation or limit order. Stop beyond zone. Target: next opposing zone.

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: Empirical limit-order clustering research supports price barriers at clustered levels, but candle zones do not reveal unfilled institutional inventory.

Key Rules

  • Define base, departure, zone bounds, retest, expiry, and invalidation without hindsight.
  • Normalize departure by ATR, ticks, and bars; do not call it order imbalance without order-flow evidence.
  • Treat the construct as a support/resistance zone, not unfilled institutional orders.
  • Test retest age/count and lower-timeframe refinement for incremental net value.
  • Keep broken, never-retested, and expired zones in the denominator.

Related Skills

  • volume-profile-trading — volume profile HVNs confirm S/D zone strength
  • fibonacci-trading — Fib retracements into S/D zones provide high-confluence entries

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.