agentleFS
krzysukrzysu/market-skills/skills/market-snapshot/SKILL.md

market-snapshot

Skill3 starsChanged 4 months agoMITView on GitHub

Single-call chart-visual sanity check (Supertrend 10/3 + RSI 14 + MA alignment). Use to cross-check a higher-TF L3 idea against the lower-TF chart structure before entry. Audit 2026-06-21 #5b #5.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    After a 1d L3 idea fires (swing-scan / batch), before flagging [OPPORTUNITY] ENTRY

    line 22
  2. Distinctive:

    When cross-TF disagreement (Pattern D) is detected — fetch this on the lower TF to determine whether the higher-TF idea is real or noise

    line 23

≈ “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-snapshot

Lean chart-visual cross-check designed for batch evaluation. Returns the three signals a chart-watcher checks before pulling the trigger: Supertrend direction, RSI position, and EMA alignment. The agrees_with_idea field summarizes whether all three agree on direction — the LLM agent brain uses this to downgrade 1d L3 ideas that contradict the 4h chart structure.

When to use

  • After a 1d L3 idea fires (swing-scan / batch), before flagging [OPPORTUNITY] ENTRY
  • When cross-TF disagreement (Pattern D) is detected — fetch this on the lower TF to determine whether the higher-TF idea is real or noise

When NOT to use

  • For full L2/L3 analysis — use run-all-l2 / run-all-l3 instead. This skill returns only three visual signals, not the full pattern detection suite.
  • For 220+ candle trend analysis (EMA200, deep HH/HL) — use market-trend.

Usage

# Sanity-check a 1d idea on 4h
uv run skills/market-snapshot/scripts/run.py VVVUSD --interval=4h --period=6mo --json

# Quick visual read on 1h
uv run skills/market-snapshot/scripts/run.py HYPEUSD --interval=1h --period=1mo

Output schema

{
  "ticker": "VVVUSD",
  "interval": "4h",
  "current_price": 14.41,
  "supertrend": {"value": 14.92, "direction": "down", "period": 10, "multiplier": 3.0},
  "rsi":        {"value": 40, "signal": "NEUTRAL"},
  "ma_alignment": "TANGLED",
  "agrees_with_idea": false
}

Cross-check interpretation

supertrendrsima_alignmentagrees_with_idea
upnot OVERBOUGHTFULL_BULL / PARTIAL_BULLtrue (bullish consensus)
downnot OVERSOLDFULL_BEAR / PARTIAL_BEARfalse (bearish consensus)
mixed—TANGLEDnull (inconclusive)

Layer rules

  • Lives between L0 (providers) and L1 (single-skill indicators). Calls market-rsi and market-trend via the skill loader so signals stay consistent with the rest of the pipeline.
  • Output is read-only — never gates trades on its own. Always pair with a full L2/L3 verdict from run-all-l2 / run-all-l3.

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.