agentleFS
krzysukrzysu/market-skills/skills/market-trend-quality/SKILL.md

market-trend-quality

Skill3 starsChanged 4 months agoMITView on GitHub

Assesses trend health by composing L1 indicators: EMA alignment, HH/HL integrity, pullback depth, impulse vs retrace ratio, and volume confirmation on impulse bars. Classifications: HEALTHY_UPTREND, HEALTHY_DOWNTREND, WEAKENING, DEGRADING, TANGLED.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Do not enter off a WEAKENING / DEGRADING / TANGLED classification — those say structure is breaking down, not that a reversal trade exists.

    line 21

≈ “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

market-trend-quality

L2 pattern detection skill that composes L1 indicators to assess the health and quality of a trend.

When NOT to use

  • This is pattern detection, not a trade idea — treat HEALTHY_UPTREND / WEAKENING as input to an L3 strategy (strategy-trend-follow) or run-all-l3, not as an entry.
  • Do not enter off a WEAKENING / DEGRADING / TANGLED classification — those say structure is breaking down, not that a reversal trade exists.
  • For raw EMA alignment + HH/HL structure use market-trend; this skill is the health lens L3 strategies key off, not a standalone signal.

Layering

This is the only L2 trend skill after the consolidation:

  1. market-trend (L1) — raw EMA alignment + HH/HL structure (closest to candles)
  2. market-trend-quality (this skill, L2) — structural health — what L3 strategies key off

market-trend-analysis was deprecated in favour of this skill to eliminate the cross-skill conflict that fired Pattern U every tick.

Schema invariants:

  • pattern.present is True iff pattern.classification is non-None
  • The 4-sub fallback (line 202 of lib.py) ensures 4+ present sub-signals always classifies, even when signed_score < 0.75 — a deep pullback can drag signed_score below threshold while the directional signal is still strong.
  • The 3-sub branch (line 207 of lib.py) catches 3 present sub-signals with weighted_sum > 0.30.
  • HEALTHY_UPTREND requires trend_score >= 3 AND hh_intact=True AND ema_bullish=True. If any of those fail, classifier cascades to WEAKENING / DEGRADING / TANGLED.

Quick Start

uv run skills/market-trend-quality/scripts/run.py SPY
uv run skills/market-trend-quality/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
EMA alignment0.25market-trendalignment field: FULL_BULL, FULL_BEAR, etc.
HH/HL integrity0.25market-trendhigher_high and higher_low both intact for uptrend, both broken for downtrend
Pullback depth (shallow vs deep)0.20market-trend + market-fibonacciCompare price distance to fib support levels to gauge retracement depth
Impulse vs retrace ratio0.15derived from candles6-bar recent return vs 6-bar prior return, normalized by ATR(14). Bounce (recent > 0, prior < 0) → +0.15; decline-decel (recent > 0, prior > 0, recent < abs(prior)) → −0.075. Requires an actual reversal for the bullish path — continued selling at a slower pace does not count as a bounce.
Volume confirmation0.15market-volumeHigh volume + OBV rising → +0.15; high volume + OBV falling → −0.15 (distribution); quiet accumulation (vr in [0.7, 1.5] with OBV rising or price > EMA50) → +0.075; low volume + OBV falling → −0.15.

Classifications

ClassificationMeaning
HEALTHY_PULLBACK_UPTRENDHealthy uptrend in pullback phase — bullish EMA alignment, recent bounce off the lows, price back above EMA50. Entry: bounce confirmation.
HEALTHY_UPTRENDStrong uptrend with score >= 3, intact HH/HL, and bullish EMA alignment
HEALTHY_DOWNTRENDStrong downtrend with score <= -3, broken HH/HL, and bearish EMA alignment
WEAKENINGTrend score 1-2 or -1 to -2 with conflicting sub-signals. Also used as a fallback when the sub-signal sum is strongly directional (≥0.75 / ≤−0.75) but the L1 trend_score didn't reach the HEALTHY_* gate — ensures pattern.present is never false when sub-signals are strongly aligned. Also fires for 3 present sub-signals with weighted_sum > 0.30 (mirrors the bug-scan Shape #1 trigger and the ALGO 4h liquidity-sweep fix).
DEGRADINGHH/HL structure breaking down and EMA alignment becoming tangled
TANGLEDNo clear alignment or directional conviction

HEALTHY_PULLBACK_UPTREND is checked first (before HEALTHY_UPTREND) — if the conditions are met, it wins regardless of the underlying trend_score.

Output

  • pattern.present (bool)
  • pattern.confidence (1–5)
  • pattern.classification (HEALTHY_PULLBACK_UPTREND / HEALTHY_UPTREND / HEALTHY_DOWNTREND / WEAKENING / DEGRADING / TANGLED)
  • pattern.type always "TREND_QUALITY"
  • 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.