agentleFS
krzysukrzysu/market-skills/skills/market-liquidity-sweep/SKILL.md

market-liquidity-sweep

Skill3 starsChanged 4 months agoMITView on GitHub

Detects whether a fakeout occurred: price wicks through S/R without close beyond, immediate reclaim, old high/low taken then reversed, above-avg volume on rejection candle. Classifications: SUPPORT_SWEEP, RESISTANCE_SWEEP, DOUBLE_TEST.

The file

Files
SKILL.md

market-liquidity-sweep

L2 pattern detection skill that composes L1 indicators to detect liquidity sweeps and fakeouts.

When NOT to use

  • This is pattern detection, not a trade idea — feed a fired pattern into strategy-liquidity-sweep or run-all-l3 before acting.
  • A sweep is a liquidity event, not a reversal — do not enter long on every support sweep; require accumulation confirmation (market-accumulation) and volume reversal (market-volume).
  • On a trending tape a sweep can be a continuation retest rather than a fakeout; confirm the broader structure with market-trend first.

Quick Start

uv run skills/market-liquidity-sweep/scripts/run.py SPY
uv run skills/market-liquidity-sweep/scripts/run.py SPY --json

Flags

FlagDefaultNotes
TICKER (positional)—Required. Supports provider:ticker (e.g. hl:LIT, yf:AAPL).
--jsonhumanEmit JSON to stdout.
--source=PROVIDERauto-detectForce a data provider (see README).
--interval=INTERVAL1d1m/2m/5m/15m/30m/1h/2h/4h/8h/12h/1d/3d/1wk/1M.
--period=PERIOD1y1d/5d/1mo/3mo/6mo/1y/2y/5y/10y/ytd/max.

Both timeframe flags are validated — bad values exit 2 with a friendly error. For intraday (--interval=1h), bump --period to 6mo or 1y; yfinance caps hourly at ~2y and anything sub-hour at ~60d.

Sub-Signals

Sub-signalWeightSource L1Logic
Wick through S/R without close beyond0.35market-s-rsits_on_level is False; low of last 3 bars below nearest_support or high above nearest_resistance; close back within range
Immediate reclaim0.30market-s-rAfter wick-through, latest close is back above support or below resistance
Old high/low taken then reversed0.20market-trendLast bar high exceeded swing_high but close below it, or low broke swing_low but close above it
Above-avg volume on rejection candle0.15market-volumeHighest volume in last 5 bars > 1.5× SMA(20) of volume

Classifications

ClassificationMeaning
SUPPORT_SWEEPPrice wicked below support then reclaimed
RESISTANCE_SWEEPPrice wicked above resistance then reclaimed
DOUBLE_TESTOld high/low taken and reversed without clear S/R direction

Output

  • pattern.present (bool)
  • pattern.confidence (1–5)
  • pattern.classification (SUPPORT_SWEEP / RESISTANCE_SWEEP / DOUBLE_TEST)
  • pattern.type always "SWEEP"
  • signals — per-signal {"present": bool, "weight": float}
  • input_scores — raw L1 outputs
  • narrative — one-sentence explanation

Output envelope (AXI)

--json output follows the canonical AXI envelope — {data, count, errors, help[]}. Default schema is the per-skill minimal fields (3-6 essentials); pass --fields=<csv> to project or --full for the full payload. count is the item count, help[] is contextual next-step command templates. Lib.py return shapes (L1Result / L2Result / L3Result / L3Idea / RegimeSignal) are unchanged — the envelope wraps them at the scripts/run.py boundary.

Home view (no-arg mode)

No-arg mode prints the home view from $XDG_DATA_HOME/market-skills/<skill>_last.json (last successful run). Errors are not cached.

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.